Papers by Wang Zheng
Bridge Video and Text with Cascade Syntactic Structure (C18-1)
Copied to clipboard
| Challenge: | Using LSTM-CSS, we construct basic syntactic structure by completing syntastic structure. |
| Approach: | They propose a video captioning approach that progressively completes syntactic structure by a conditional random field to construct basic syntaktic structure. |
| Outcome: | The proposed method produces natural sentences with 42.3% and 28.5% accuracy compared to state-of-the-art methods. |
ReCode: Robustness Evaluation of Code Generation Models (2023.acl-long)
Copied to clipboard
Shiqi Wang, Zheng Li, Haifeng Qian, Chenghao Yang, Zijian Wang, Mingyue Shang, Varun Kumar, Samson Tan, Baishakhi Ray, Parminder Bhatia, Ramesh Nallapati, Murali Krishna Ramanathan, Dan Roth, Bing Xiang
| Challenge: | Existing work on robustness in text or code tasks has focused on classification, while robustness for code generation tasks is an uncharted area. |
| Approach: | They propose a robustness evaluation benchmark for code generation models that customizes over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. |
| Outcome: | The proposed model performs better on human annotators and on SOTA models with human annnotators. |
C2LEVA: Toward Comprehensive and Contamination-Free Language Model Evaluation (2025.findings-acl)
Copied to clipboard
Yanyang Li, Wong Tin Long, Cheung To Hung, Jianqiao Zhao, Duo Zheng, Liu Ka Wai, Michael R. Lyu, Liwei Wang
| Challenge: | Recent advances in large language models (LLMs) have shown significant promise, yet their evaluation raises concerns regarding data contamination due to the lack of access to proprietary training data. |
| Approach: | They propose a bilingual benchmark that offers a holistic evaluation and systematic contamination prevention. |
| Outcome: | The proposed evaluations of 15 open-source and proprietary models show that they are reliable and free of data contamination. |
CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that rule-based evaluation methods are ineffective for open-ended natural language generation. |
| Approach: | They propose a pointwise generative reward model with a dedicated two-stage rollout method and unified query-based criteria that can be trained with 5.7K high-quality data. |
| Outcome: | The proposed model achieves superior performance on diverse reward model benchmarks, especially in Best-of-N scenarios, and delivers more effective improvements in downstream RL practice. |
Integrating User History into Heterogeneous Graph for Dialogue Act Recognition (2020.coling-main)
Copied to clipboard
| Challenge: | Existing models cannot fully recognize the specific expressions given by users due to the informality and diversity of natural language expressions. |
| Approach: | They propose a Heterogeneous User History graph convolution network which utilizes the user’s historical answers grouped by DA labels as additional clues to recognize the DA label of utterances. |
| Outcome: | The proposed model outperforms the state-of-the-art methods on two benchmark datasets and shows that it integrates user’s historical answers. |
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs (2026.acl-long)
Copied to clipboard
Yu Li, Xiaoran Shang, Qizhi Pei, Yun Zhu, Xin Gao, Honglin Lin, Zhanping Zhong, Zhuoshi Pan, Zheng Liu, Xiaoyang Wang, Conghui He, Dahua Lin, Feng Zhao, Lijun Wu
| Challenge: | High-quality post-training data is the primary engine driving LLM capabilities . datasets are often treated as isolated artifacts, overlooking their true developmental context . |
| Approach: | They propose a framework to reconstruct the evolutionary graph of dataset development using data lineage. |
| Outcome: | The proposed framework characterizes domain-specific structural patterns in Math-oriented datasets and general-domain corpora. |
RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for large language models fail to capture complex interplay between functionality and security. |
| Approach: | They propose a benchmark for secure code generation constructed from real-world, high-risk Java repositories. |
| Outcome: | The proposed benchmarks highlight the gap between functional and secure code generation in LLMs. |
FISTAPruner: Layer-wise Post-training Pruning for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing pruning methods require inefficient retraining for billion-scale LLMs or rely on heuristicically designed metrics to determine pruning masks, leading to performance degradation. |
| Approach: | They propose a convex optimization model that induces sparsity in large language models by leveraging FISTA. |
| Outcome: | The proposed method can remove 50% of model parameters while retaining 98.6% and 95.6% of the zero-shot performance. |
ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models (2026.acl-demo)
Copied to clipboard
Jiasheng Zheng, Xin Zheng, Boxi Cao, Pengbo Wang, Zhengzhao Ma, Qiming Zhu, Jiazhen Jiang, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
| Challenge: | Existing code sandboxes fail to provide accurate verification and efficiency under high-concurrency workloads. |
| Approach: | They propose a high-fidelity code verification system that provides sandbox feedback for RL training and evaluation. |
| Outcome: | The proposed system outperforms heuristic-matching baselines on LiveCodeBench and training stability on high-concurrency workloads. |
A Survey of LLM-based Agents in Medicine: How far are we from Baymax? (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are transforming healthcare through their ability to understand and assist with medical tasks. |
| Approach: | They analyze system profiles, clinical planning, medical reasoning frameworks, and external capacity enhancement. |
| Outcome: | The findings highlight the future directions in medical reasoning, physical system integration, and training simulations. |
Simplified Graph Learning for Inductive Short Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for short text classification are limited and lack of labeled data is not enough. |
| Approach: | They propose a novel short text classification algorithm which leverages words to handle the lack of labeled data. |
| Outcome: | The proposed model performs better with lower memory consumption and faster inference speed than previous models. |
CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation (2026.findings-acl)
Copied to clipboard
Hu Jing, Danxiang Zhu, Xianlong Luo, Dan Zhang, Shuwei He, Yishu Lei, Shikun Feng, Hai-Tao Zheng, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap . |
| Approach: | They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models. |
| Outcome: | The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting . |
Model Composition for Multimodal Large Language Models (2024.acl-long)
Copied to clipboard
Chi Chen, Yiyang Du, Zheng Fang, Ziyue Wang, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu
| Challenge: | Existing methods for creating versatile MLLMs rely on joint training with paired instruction data, which is resource-intensive and challenging to extend to new modalities. |
| Approach: | They propose a new paradigm for multimodal large language models by reusing modality encoders and merging LLM parameters. |
| Outcome: | The proposed model retains the modal understanding capabilities of each original model. |
MTA:A Merge-then-Adapt Framework for Personalized Large Language Models (2026.acl-long)
Copied to clipboard
Xiaopeng Li, Yuanjin Zheng, Wanyu Wang, Wenlin Zhang, Pengyue Jia, Yingyi Zhang, Haiying He, Mengyang Ma, Yiqi Wang, Maolin Wang, Xuetao Wei, Xiangyu Zhao
| Challenge: | Personalized Large Language Models (PLLMs) aim to align outputs with individual user preferences . current methods of fine-tuning a separate module for each user are unscalable . |
| Approach: | They propose a Merge-then-Adapt framework for Personalized Large Language Models . they construct a shared Meta-LoRA bank and propose an Adaptive LoRA Fusion stage . |
| Outcome: | The proposed framework outperforms existing SOTA methods on the LaMP benchmark. |
All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG (2026.acl-long)
Copied to clipboard
Dan Wang, Guozhao Mo, Yafei Shi, Cheng Zhang, Bo Zheng, Boxi Cao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun
| Challenge: | Existing mRAG systems suffer from a language bias during reranking, systematically favoring English and the query’s native language. |
| Approach: | They propose a language-agnostic utility-driven reranker alignment technique to mitigate language bias during re-ranking. |
| Outcome: | The proposed approach mitigates language bias and consistently improves mRAG performance across languages. |
Beyond the Textual: Generating Coherent Visual Options for MCQs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multiple choice questions (MCQs) are crucial for deep thinking and knowledge integration in education. |
| Approach: | They propose a cross-modal options synthesis framework for generating MCQs with visual options. |
| Outcome: | The proposed framework produces a plausible and visually similar answer and distractor . it also includes a discrimination module to identify content suitable for visual options . |
DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog (2023.findings-emnlp)
Copied to clipboard
Xin Zheng, Tianyu Liu, Haoran Meng, Xu Wang, Yufan Jiang, Mengliang Rao, Binghuai Lin, Yunbo Cao, Zhifang Sui
| Challenge: | Existing work on question-answer extraction fails to integrate incomplete utterances from dialog context for composite QA retrieval. |
| Approach: | They propose a task where questions and corresponding answers might be separated across different utterances. |
| Outcome: | The proposed methods perform well on 5 customer service datasets and set a benchmark for N-to-N DialogQAE with utterance and session level evaluation metrics. |
USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)
Copied to clipboard
Baolin Zheng, Guanlin Chen, Qingyang Teng, Hongqiong Zhong, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang
| Challenge: | Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations. |
| Approach: | They propose a framework that covers 61 risk categories across four modality interactions to address this gap. |
| Outcome: | The proposed framework covers 61 risk categories across four distinct modality interactions. |
Gaussian Process based Deep Dyna-Q approach for Dialogue Policy Learning (2021.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) is the main dialogue policy learning method in recent years. |
| Approach: | They propose a Gaussian Process based Deep Dyna-Q approach to dialogue policy learning . they propose evaluating the quality of experiences generated by the world model using a discriminator . |
| Outcome: | The proposed approach improves the effectiveness and efficiency of dialogue policy learning by 20% with fewer human-machine interactions. |
Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization (2026.acl-long)
Copied to clipboard
Tian Xueyun, MingHua Ma, Bingbing Xu, Nuoyan Lyu, Wei Li, Heng Dong, Zheng Chu, Yuanzhuo Wang, Huawei Shen
| Challenge: | Recent studies show that supervised fine-tuning (SFT) is a common approach for reasoning in large language models. |
| Approach: | They propose to use supervised fine-tuning (SFT) on chain-of-thought trajectories demonstrations . they find that incorporating negative traxories yields substantial OOD generalization gains . |
| Outcome: | The proposed scheme yields 5.51% OOD gain over positive-only training. |
An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation (2024.acl-long)
Copied to clipboard
Kun Zhu, Xiaocheng Feng, Xiyuan Du, Yuxuan Gu, Weijiang Yu, Haotian Wang, Qianglong Chen, Zheng Chu, Jingchang Chen, Bing Qin
| Challenge: | Experimental results show that retrieval-augmented generation improves accuracy and relevance of large language models. |
| Approach: | They propose to introduce the information bottleneck theory into retrieval-augmented generation by maximizing mutual information between compression and ground output while minimizing mutual information . |
| Outcome: | The proposed approach improves accuracy and correctness of answer generation and conciseness with 2.5% compression rate. |
Causal-ESC: Reliable Policy Learning for Emotional Support Conversation via Causal Inference (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to Emotional Support Conversation (ESC) are mechanistically opaque and lacks a causal mechanism between dialogue features and effective empathic strategies. |
| Approach: | They propose a framework that uses Doubly Robust learning to model causal effects of utterance features on strategy selection. |
| Outcome: | The proposed framework outperforms state-of-the-art baselines in empathy and helpfulness and provides a theoretically grounded, interpretable solution to the mechanistic interpretability dilemma in affective computing. |
What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations (2026.acl-short)
Copied to clipboard
Yujie Luo, Zhuoyun Yu, Xuehai Wang, Yuqi Zhu, Ningyu Zhang, Lanning Wei, Lun Du, Da Zheng, Huajun Chen
| Challenge: | Existing approaches to replicate AI research are limited by insufficient background knowledge and the limitations of retrieval-augmented generation methods. |
| Approach: | They propose a pluggable, paper-centric knowledge base that integrates code snippets and technical insights extracted from scientific literature into a verifiable, executable representation. |
| Outcome: | The proposed knowledge base shows significant performance gains on paperBench when integrated into three agent frameworks with two different LLMs. |
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models (2026.acl-long)
Copied to clipboard
Zhiwen Ruan, Yichao Du, Jianjie Zheng, Longyue Wang, Yun Chen, Peng Li, Jinsong Su, Yang Liu, Guanhua Chen
| Challenge: | Existing adapter-based transfer methods treat instruction-tuned models as passive targets . direct fine-tuning can disrupt this delicate balance and lead to instability or performance degradation. |
| Approach: | They propose a framework that incorporates instruction-level guidance into task adaptation. |
| Outcome: | The proposed framework outperforms direct fine-tuning and representative transfer-based baselines while maintaining robust generalization and favorable test-time scaling behavior. |
v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound (2026.acl-long)
Copied to clipboard
Zhengpeng Shi, Yanpeng Zhao, Jianqun Zhou, Yuxuan Wang, Qinrong Cui, Wei Bi, Song-Chun Zhu, Bo Zhao, Zilong Zheng
| Challenge: | Humor enriches our daily lives and appears in many forms, from jokes and cartoons to comedies and viral videos. |
| Approach: | They introduce a video humor understanding benchmark to test their ability to understand humor from visual cues. |
| Outcome: | The proposed video humor understanding benchmark is based on a collection of short videos . it features rich annotations and a study of environmental sound that can enhance humor . |
TripTailor: A Real-World Benchmark for Personalized Travel Planning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation metrics for travel planning rely on unrealistic simulated data . fewer than 10% of the itineraries generated by the latest state-of-the-art LLMs achieve human-level performance. |
| Approach: | They propose a benchmark for personalized travel planning in real-world scenarios . they identify several critical challenges in travel planning including feasibility and rationality . |
| Outcome: | The proposed benchmarks show that fewer than 10% of the itineraries generated by the latest state-of-the-art LLMs achieve human-level performance. |
A Sequence-to-Sequence&Set Model for Text-to-Table Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing models for text-to-table generation are order-insensitive, but suffer from errors . a novel sequence-tosequence&set model generates table body rows in parallel . |
| Approach: | They propose a sequence-to-sequence generation task that serializes each table into a token sequence during training by concatenating all rows in a top-down order. |
| Outcome: | The proposed model outperforms baselines on commonly-used datasets. |
ReCon: Active Defense against Large Vision-Language Model Jailbreaks via Reverse Safety Concept Injection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing defense strategies neglect visual threats and lack of fine-grained specificity regarding specific attack semantics. |
| Approach: | They propose a black-box defense framework that maps unsafe concepts to fine-grained, constructive Safe Concepts. |
| Outcome: | a new black-box defense framework enhances robustness against jailbreak attacks . it maps detected unsafe concepts to fine-grained, constructive Safe Concepts . the proposed framework is available for free at http://www.epa.org/recon/ . |
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)
Copied to clipboard
Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM. |
| Approach: | They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks. |
| Outcome: | The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting. |
LIFTED: Multimodal Clinical Trial Outcome Prediction via Large Language Models and Mixture-of-Experts (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Clinical trials are costly and pivotal processes that require substantial expenses . a new approach to integrate multimodal data for clinical outcome prediction is needed . |
| Approach: | a proposed framework transforms modality-specific data into natural language descriptions . a sparse Mixture-of-Experts mechanism then identifies shared patterns across modalities . |
| Outcome: | a proposed framework outperforms baseline methods in predicting clinical trial outcomes . it transforms modality-specific data into natural language descriptions, encoded via unified encoders . |
UMMF: Protecting Copyright of Large Vision-Language Models through Unlearning-based Multimodal Memorization Fingerprint (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fingerprinting large vision-Language Models rely on explicit triggers, which have limitations in terms of stealthiness and robustness. |
| Approach: | They propose to use model fingerprints to verify the ownership of large vision-Language Models (LVLMs) they use implicit model fingerprinting techniques that leverage neighboring samples as implicit model . |
| Outcome: | The proposed fingerprinting technique is superior to existing methods, but has limitations in terms of stealthiness and robustness. |
MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing solutions for sign language production are limited due to phonological differences and data scarcity. |
| Approach: | They propose a unified framework for continuous sign language production that generates sign predictions step by step from text or speech embeddings. |
| Outcome: | The proposed model achieves competitive performance on how2sign and PHOENIX14T datasets. |
Instruction-following Evaluation through Verbalizer Manipulation (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing benchmarks focus on common instructions that align well with what the model learned during training, but proficiency in responding to these instructions does not necessarily imply strong ability in instruction following. |
| Approach: | They propose a new instruction-following evaluation protocol called verbalizer manipulation that instructs the model to verbalize the task label with words aligning with model priors to different extents. |
| Outcome: | The proposed protocol can be integrated with any classification benchmark to examine the model’s reliance on priors and its ability to override them to accurately follow the instructions. |
Enhancing Extractive Question Answering in Multiparty Dialogues with Logical Inference Memory Network (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models for multiparty dialogue question answering (QA) do not consider logical inference relations in multiparty dialogs, leading to suboptimal performance. |
| Approach: | They propose a memory network with logical inference for extractive QA in multiparty dialogues. |
| Outcome: | The proposed model achieves state-of-the-art on Molweni and FriendsQA benchmarks. |
Enhancing Model Privacy in Federated Learning with Random Masking and Quantization (2025.findings-emnlp)
Copied to clipboard
Zhibo Xu, Zhu JianHao, Jingwen Xu, Changze Lv, Zhenghua Wang, Zisu Huang, Xiaohua Wang, Muling Wu, Qi Qian, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | federated learning approaches are limited by the complexity of large language models and the need for specialized expertise to protect intellectual property. |
| Approach: | They propose a federated learning approach that leverages random masking to obscure a subnetwork of model parameters and applies quantization to the remaining parameters. |
| Outcome: | The proposed approach maintains strong model performance in federated learning settings and achieves enhanced protection of model parameters compared to baseline methods. |
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing backdoor attacks against prompt-based learning involve injecting back doors into embedding layers or word embedders. |
| Approach: | They propose a backdoor attack against prompt-based learning that injects backdoors into embedding layers or word embeddable vectors. |
| Outcome: | The proposed backdoor attack outperforms two state-of-the-art models on six NLP tasks and three prompting strategies. |
Heterogeneous Graph Neural Networks for Extractive Document Summarization (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models capture cross-sentence relations with recurrent neural networks, but they are hard to capture sentence-level long-distance dependency. |
| Approach: | They propose a graph-based neural network for extractive summarization which contains semantic nodes apart from sentences. |
| Outcome: | The proposed graph-based neural network is the first to incorporate different types of nodes into it and perform a qualitative analysis. |
GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment (2026.acl-long)
Copied to clipboard
Jiwei Tang, Zhicheng Zhang, Shunlong Wu, Jingheng Ye, Lichen Bai, Zitai Wang, Tingwei Lu, Lin Hai, Yiming Zhao, Hai-Tao Zheng, Hong-Gee Kim
| Challenge: | Large Language Models (LLMs) have achieved remarkable performance across NLP tasks . however, in long-context scenarios, they face high computational cost and information redundancy. |
| Approach: | They propose an encoder-decoder context compression framework that generates a compact sequence of soft tokens for downstream tasks. |
| Outcome: | Experiments show that GMSA outperforms baselines on multiple long-context question answering and summarization benchmarks while maintaining low end-to-end latency. |
Real, Fake, or Manipulated? Detecting Machine-Influenced Text (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work on machine generated text detection focused on identifying whether document was human or machine written, ignoring these fine-grained uses. |
| Approach: | They propose a machine-influenced text detector that learns to separate text samples from four primary types . the detector uses a subcategory guidance module to help separate the fine-grained categories . |
| Outcome: | The proposed detector outperforms the state-of-the-art in five LLMs and six domains. |
Zero-shot Text Classification via Reinforced Self-training (2020.acl-main)
Copied to clipboard
Zhiquan Ye, Yuxia Geng, Jiaoyan Chen, Jingmin Chen, Xiaoxiao Xu, SuHang Zheng, Feng Wang, Jun Zhang, Huajun Chen
| Challenge: | Existing methods to learn from unlabeled data are difficult for zero-shot text classification tasks. |
| Approach: | They propose a self-training based method to efficiently leverage unlabeled data. |
| Outcome: | The proposed method significantly outperforms existing methods in zero-shot text classification tasks on benchmarks and a real-world e-commerce dataset. |
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026.acl-long)
Copied to clipboard
Zheng Liu, Honglin Lin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, Zhuoshi Pan, Xiaoran Shang, Conghui He, Bin Cui, Wentao Zhang, Lijun Wu
| Challenge: | Existing open-source vision language models lack high-quality training data for chart reasoning . current models are simplistic and repetitive, while associated QA pairs are prone to hallucinations . |
| Approach: | They propose a framework to synthesize complex charts and reliable reasoning data from scratch. |
| Outcome: | Experimental results show that ChartVerse-8B surpasses existing models in QA and difficulty . lack of high-quality training data hampers development of open-source models . |
RubricBench: Aligning Model-Generated Rubrics with Human Standards (2026.acl-long)
Copied to clipboard
Junyi Zhou, Qiyuan Zhang, Yufei Wang, Fuyuan Lyu, Yidong Ming, Can Xu, Qingfeng Sun, Kai Zheng, Peng Kang, Xue Liu, Chen Ma
| Challenge: | Existing benchmarks lack discriminative complexity and ground-truth rubric annotations required for rigorous evaluation. |
| Approach: | They propose a curated benchmark with 1,147 pairwise comparisons to assess the reliability of rubric-based evaluation. |
| Outcome: | The proposed benchmarks show that they support diverse domains, exhibit discriminative ability, provide high-quality annotations, and include human-authored rubrics. |
Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours (2022.emnlp-demos)
Copied to clipboard
Eyal Shnarch, Alon Halfon, Ariel Gera, Marina Danilevsky, Yannis Katsis, Leshem Choshen, Martin Santillan Cooper, Dina Epelboim, Zheng Zhang, Dakuo Wang
| Challenge: | Label Sleuth is an open source system for labeling and creating text classifiers which does not require coding skills nor machine learning knowledge. |
| Approach: | *Label Sleuth* is an open source system for labeling and creating text classifiers which does not require coding skills nor machine learning knowledge. |
| Outcome: | *Label Sleuth* is an open source system for labeling and creating text classifiers. |
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)
Copied to clipboard
Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang
| Challenge: | Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs). |
| Approach: | They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories. |
| Outcome: | The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks. |
CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning (2022.naacl-industry)
Copied to clipboard
| Challenge: | a paper focuses on automatically generating the text of an ad to capture user interest for achieving higher click-through rate. |
| Approach: | They propose a CTR-driven advertising text generation approach to generate ad texts based on user reviews. |
| Outcome: | The proposed approach outperforms existing approaches on industrial datasets and on large-scale unpaired reviews. |
DrAgent: Empowering Large Language Models as Medical Agents for Multi-hop Medical Reasoning (2025.findings-emnlp)
Copied to clipboard
Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xin Liu, Zhengyang Wang, Xianfeng Tang, Shiyang Li, Xiang He, Ruijie Wang, Bing Yin, Xiao Gu, Lei Clifton, David A. Clifton
| Challenge: | commercial LLMs can be difficult to use in real-world clinical decision-making . a lightweight LLM can be used to collaborate with diverse clinical tools . |
| Approach: | They propose a lightweight LLM that can be used to build medical LLMs as agents . they use recursive curriculum learning to optimize the LLM in an easy-to-hard progression . |
| Outcome: | The proposed approach outperforms human experts in medical examinations on diverse datasets. |
IterAlign: Iterative Constitutional Alignment of Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Empirical results show that iterAlign improves truthfulness, helpfulness, harmlessness and honesty, improving the LLM alignment by up to 13.5% in harmlessness. |
| Approach: | They propose a data-driven constitution discovery and self-alignment framework called IterAlign to overcome these drawbacks by leveraging red teaming to uncover weaknesses of an LLM. |
| Outcome: | Empirical results show that iterAlign improves truthfulness, helpfulness, harmlessness and honesty by up to 13.5%. |
LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)
Copied to clipboard
Jian Yang, Wei Zhang, Shuyue Guo, Yizhi LI, Linzheng Chai, Zhengmao Ye, Shukai Liu, Yuyang Song, Jiajun Wu, Che Liu, Tianyu Zheng, Siwei Wu, Leo L, Xudong Ma, Chuan Hao, Ran Tao, Yan Xing, Jianzhou Wang, Mingjie Tang, Aishan Liu, Zhoujun Li, Xianglong Liu, Weifeng Lv, Bryan Dai
| Challenge: | Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge. |
| Approach: | They propose a recurrent inductive bias that aligns with the recursive nature of programming logic. |
| Outcome: | The proposed model achieves comparable performance to standard dense models with more parameters. |
Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)
Copied to clipboard
Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang, Hyokun Yun, Ming Zeng, Pei Chen, Zhihan Zhang, Yifan Gao, Ruijie Wang, Priyanka Nigam, Bing Yin, Meng Jiang
| Challenge: | Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale. |
| Approach: | They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data. |
| Outcome: | The proposed framework transforms user-generated content into user queries and generates responses from the policy model. |
Spiral of Silence in Large Language Model Agents (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing theories of Spiral of Silence do not apply to large language models . |
| Approach: | They propose an evaluation framework for examining SoS in large language models . they consider four controlled conditions that vary the availability of "History" and "Persona" signals . |
| Outcome: | The proposed framework examines the SoS-like dynamics in large language models . it shows that history and persona together produce strong majority dominance . |
Towards Context-Aware Code Comment Generation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for code comments generate comments manually, but they suffer from poor scalability and high maintenance cost due to the expensive overhead of writing comment templates. |
| Approach: | They propose a method to automatically generate code comments at a function level by targeting object-oriented programming languages. |
| Outcome: | The proposed approach outperforms the state-of-the-art methods and is comparable with existing methods. |
StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding (2023.emnlp-main)
Copied to clipboard
Cheng Jiayang, Lin Qiu, Tsz Chan, Tianqing Fang, Weiqi Wang, Chunkit Chan, Dongyu Ru, Qipeng Guo, Hongming Zhang, Yangqiu Song, Yue Zhang, Zheng Zhang
| Challenge: | Analogy-making between narratives is crucial for human reasoning . despite its importance, there has been limited research on story analogies . |
| Approach: | They construct a large-scale story-level analogy corpus with 24K story pairs . they find that the tasks are incredibly difficult for large language models such as ChatGPT . |
| Outcome: | The proposed corpus contains 24K story pairs from diverse domains with human annotations on two similarities from the extended Structure-Mapping Theory. |
CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding (2021.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models are vulnerable to simple perturbations, causing poor robustness . recent studies show that adversarial training is useless or harmful for the model to detect these semantic changes. |
| Approach: | They propose to use adversarial training to improve the robustness of pre-trained models . they propose to construct negative examples with similar and opposite semantics . |
| Outcome: | Empirical results show that the proposed approach improves on sentiment analysis, reasoning, and reading comprehension tasks. |
TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for table instruction tuning are limited due to limited data diversity and lack of data quality. |
| Approach: | They propose a weakness-guided data synthesis framework for table instruction tuning that explores the vast input space of table understanding tasks and then iterates through the input space. |
| Outcome: | The proposed framework boosts the average accuracy of Llama3.1-8B-instruct by 11.62% with 27K GPT-4o synthetic data and outperforms state-of-the-art data synthesis baselines which use more training data. |
GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization (2025.acl-long)
Copied to clipboard
Zhouhong Gu, Xingzhou Chen, Xiaoran Shi, Tao Wang, Suhang Zheng, Tianyu Li, Hongwei Feng, Yanghua Xiao
| Challenge: | Existing methods for achieving this require a limited understanding of constraints and can be hallucinating or brittle. |
| Approach: | They propose a framework that combines adversarial training dynamics with an encoder-only reward model to progressively learn and adapt to increasingly complex constraints. |
| Outcome: | Extensive experiments show that GAPO significantly outperforms existing methods like PPO, DPO, and KTO in fine-grained constraints. |
It is AI’s Turn to Ask Humans a Question: Question-Answer Pair Generation for Children’s Story Books (2022.acl-long)
Copied to clipboard
| Challenge: | Existing question answering (QA) techniques are created mainly to answer questions asked by humans, but in educational applications, teachers often need to decide what questions to ask . |
| Approach: | They propose to use a fairytale-themed storybook as input to generate QA pairs that can test a student's comprehension skills. |
| Outcome: | The proposed system outperforms state-of-the-art QAG baseline systems and builds an interactive story-telling application for the future real-world deployment. |
CMQA: A Dataset of Conditional Question Answering with Multiple-Span Answers (2022.coling-1)
Copied to clipboard
| Challenge: | Existing QA datasets only contain unconditional and parallel answers . conditional question answering with hierarchical multi-span answers is challenging for the community to solve . |
| Approach: | They propose a conditional question answering task with hierarchical multi-span answers . they propose CMQA, which contains conditional and hierarchic samples . |
| Outcome: | The proposed task can be used to build more reliable and sophisticated QA systems. |
Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs (2026.acl-long)
Copied to clipboard
Shenglai Zeng, Tianqi Zheng, Chuan Tian, Dante Everaert, Yau-Shian Wang, Yupin Huang, Michael J. Morais, Rohit Patki, Jinjin Tian, Xinnan Dai, Kai Guo, Monica Xiao Cheng, Hui Liu
| Challenge: | Existing approaches to personalize large language models (LLMs) rely on heuristic methods to compress user profiles but they ignore how LLMs process and prioritize different profile components. |
| Approach: | They propose an attention-guided context compression framework that leverages attention feedback from a marking model to mark important personalization sentences and guides a compression model to generate task-relevant compressed user contexts. |
| Outcome: | The proposed framework outperforms baselines across tasks, token limits, and settings while reducing token usage by 50 times. |
Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding (2022.findings-acl)
Copied to clipboard
| Challenge: | Unsupervised contrastive learning is emerging as a powerful technique for extracting knowledge from unlabeled data. |
| Approach: | They propose a momentum contrastive learning model with negative sample queue for sentence embedding with a simulated model with EMA update mechanism. |
| Outcome: | The proposed model achieves a Spearman’s correlation of 77.27% on the semantic text similarity task and a maximum traceable distance metric. |
Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoning (2025.findings-emnlp)
Copied to clipboard
Yihong Tang, Ao Qu, Zhaokai Wang, Dingyi Zhuang, Zhaofeng Wu, Wei Ma, Shenhao Wang, Yunhan Zheng, Zhan Zhao, Jinhua Zhao
| Challenge: | Currently, vision-language models excel in many downstream tasks but struggle with spatial reasoning, which is crucial for navigation and interaction with physical environments. |
| Approach: | They propose a framework that generates synthetic data to provide targeted supervision for VLMs across these basic spatial capabilities. |
| Outcome: | The proposed framework disentangles 2D spatial reasoning into three core components: direction comprehension, distance estimation, and localization. |
Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning (2024.emnlp-main)
Copied to clipboard
Lu Chen, Rui Zheng, Binghai Wang, Senjie Jin, Caishuang Huang, Junjie Ye, Zhihao Zhang, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current methods rely on ranking losses to teach reward model to assess preferences, but they are susceptible to noise and ambiguous data, often failing to deeply understand human intentions. |
| Approach: | They propose a method that incorporates contrastive learning into the reward modeling process to enhance generalization and stabilize the reinforcement learning training process. |
| Outcome: | The proposed method enhances generalization of the reward model, stabilizes the reinforcement learning training process, and improves the final alignment with human preferences. |
Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)
Copied to clipboard
Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu
| Challenge: | Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature. |
| Approach: | They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management. |
| Outcome: | The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench. |
pyvene: A Library for Understanding and Improving PyTorch Models via Interventions (2024.naacl-demo)
Copied to clipboard
Zhengxuan Wu, Atticus Geiger, Aryaman Arora, Jing Huang, Zheng Wang, Noah Goodman, Christopher Manning, Christopher Potts
| Challenge: | Existing libraries are often project-based, but pyvene provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others. |
| Approach: | They propose an open-source Python library that supports customizable interventions on a range of different PyTorch modules. |
| Outcome: | The proposed framework provides a unified and extensible framework for performing interventions on neural models and sharing the intervened upon models with others. |
PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to Automated Essay Scoring (AES) treat scoring and feedback as separate components, resulting in fragmentation. |
| Approach: | They propose a psychometrically-aware framework that integrates diagnostic assessment with instructional scaffolding through a shared latent ability representation. |
| Outcome: | The proposed framework integrates diagnostic assessment with instructional scaffolding through a shared latent ability representation. |
DKME: Rethinking Coupled Knowledge Memory for Lifelong Model Editing of Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing memory-based editors suffer from catastrophic forgetting as edits accumulate. |
| Approach: | They propose a method which injects factual updates into large language models without retraining or finetuning into existing memory-based editors. |
| Outcome: | Experiments on HalluEditBench, CKnowEdit, and WikiDatacounterfact show that the proposed model achieves a more favorable trade-off between editing success and locality compared to baselines while maintaining more stable performance as the edit scale increases. |
Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion Knowledge (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for hyperbole and metaphor detection focus on superficial text features, ignoring the associations of hyperbola and metaphor . Existing frameworks focus on identifying superficial text, focusing on superficial features . |
| Approach: | They propose an emotion-guided hyperbole and metaphor detection framework based on bidirectional dynamic interaction. |
| Outcome: | The proposed framework outperforms baseline methods on four datasets. |
Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and Grounding (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for fine-grained content extraction are limited by long-tailed distribution of textual entity categories and performance of object detectors. |
| Approach: | They propose a multi-granularity entity recognition module and a reranking module to integrate hierarchical information of entity categories, visual cues, and external textual resources collectively. |
| Outcome: | The proposed framework achieves state-of-the-art on the fine-grained content extraction task. |
Beyond Noise: Characterizing Creative Potential in Unverifiable LLM Hallucinations (2026.acl-long)
Copied to clipboard
Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao, YiJie Chen, Shujie Wang, Zheng Hu
| Challenge: | Large Language Models generate outputs that extend beyond established knowledge . prior work does not characterize the unverifiable space as a whole . |
| Approach: | They propose a novelty-verifiability characterization that distinguishes Creative Synthesis from Groundless Fabrication by a conceptual creation task. |
| Outcome: | The proposed model distinguishes Creative Synthesis (Region A) from Groundless Fabrication (Regium B) it shows that Region A is non-negligible and robust, persisting across generation strategies, models, domains, and embedding choices. |
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Yuxi Zhang, Huimin Wang, Yutian Zhao, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu
| Challenge: | Retrieval-Augmented Generation (RAG) provides access to external knowledge, but current research focuses on retrieval quality and 'integration bottleneck' . |
| Approach: | They propose a framework that explicitly decouples reasoning from evidence integration by generating an 'Inner-Answer' and a 'Refer-Aswer" they propose 'a joint decoding mechanism that dynamically fuses the logical coherence of the Inner-Andswer with the factual precision of the Refer-Adswer at the token level' |
| Outcome: | The proposed framework improves accuracy by 12.1% and reduces hallucinations by 16.3% on five QA benchmarks. |
Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (2025.naacl-long)
Copied to clipboard
Yuchen Zhuang, Jingfeng Yang, Haoming Jiang, Xin Liu, Kewei Cheng, Sanket Lokegaonkar, Yifan Gao, Qing Ping, Tianyi Liu, Binxuan Huang, Zheng Li, Zhengyang Wang, Pei Chen, Ruijie Wang, Rongzhi Zhang, Nasser Zalmout, Priyanka Nigam, Bing Yin, Chao Zhang
| Challenge: | Existing LLMs often rely on complex prompting or extensive fine-tuning to introduce new capabilities while preserving strong generalizability. |
| Approach: | They propose a large-scale pre-training corpus to enhance LLM agents' capabilities . they use 103B agent-specific data encompassing 76,537 APIs . |
| Outcome: | The proposed training corpus outperforms open-source LLMs and commercial LLM agents on three agent benchmarks. |
Model Merging for Knowledge Editing (2025.acl-industry)
Copied to clipboard
Zichuan Fu, Xian Wu, Guojing Li, Yingying Zhang, Yefeng Zheng, Tianshi Ming, Yejing Wang, Wanyu Wang, Xiangyu Zhao
| Challenge: | Existing knowledge editing approaches struggle with sequential editing scenarios and harm the general capabilities of the model. |
| Approach: | They propose a framework that combines robust supervised fine-tuning and model merging for knowledge editing to combine supervised and supervised learning. |
| Outcome: | The proposed approach outperforms existing methods in sequential editing while preserving the original performance of the model. |
Can LLMs Replace Clinical Doctors? Exploring Bias in Disease Diagnosis by Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a new study examines the bias of disease prediction in large language models . the model biases are prevalent across gender, age range and disease judgment behaviors . |
| Approach: | They propose a prompt-based approach to alleviate the bias in disease prediction with LLMs. |
| Outcome: | The proposed model alleviates the observed bias in disease prediction with LLMs. |
DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data (2026.acl-long)
Copied to clipboard
Shaofan Liu, Guoqiang Zhang, Shihan Dou, Huiyuan Zheng, Yiming Zhou, Junjie Ye, Shaowen Wang, Shichun Liu, Jiazheng Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods for training reward models are vulnerable to context neglect and degraded accuracy. |
| Approach: | They propose distribution-aware reward modeling that augments the RM objective with a conditional mutual information regularizer that maximizes context and the predicted reward conditioned on the response. |
| Outcome: | The proposed model improves performance in RLHF and improves accuracy in other settings. |
RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation (2026.acl-long)
Copied to clipboard
Jiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo, Jingzhuo Wu, Leqi Zheng, Yiran Yang, Jianke Zhang, Qingbin Li, Shannan Yan, Changguo Jia, Junfei Wu, Zilei Wang, Qiang Liu, Liang Wang
| Challenge: | Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains, but their ability to replicate complex, multi-panel visualizations remains largely unassessed. |
| Approach: | They propose a large-scale benchmark to evaluate chart generation from large- scale raw data and assess iterative code refinement in a multi-turn conversational setting. |
| Outcome: | The new benchmark evaluates 14 leading VLMs on real-world data and shows they struggle with complex plot structures and authentic data. |
Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to speed up parallel scaling have relied on similarity-based or confidence-based pruning, but these signals do not reliably indicate trace quality. |
| Approach: | They propose a pruning framework that evaluates reasoning steps using hidden states and dynamically prunes unpromising traces during generation. |
| Outcome: | The proposed framework reduces end-to-end inference latency by 45%–70% on average compared to self-consistency while improving reasoning accuracy. |
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)
Copied to clipboard
Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He
| Challenge: | Document images are characterized by higher resolutions, denser content, and more complex structural layouts. |
| Approach: | They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition. |
| Outcome: | The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead. |
Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models are inefficient and redundant . a light-PEFT framework can be used to prune redundant parameters during training . |
| Approach: | They propose a parameter-efficient fine-tuning framework that freezes most parameters of the foundation model and finetuns only a small number of parameters. |
| Outcome: | The proposed framework achieves training and inference speedup, reduces memory usage, and maintains comparable performance and plug-and-play feature of PEFT. |
Adaptive Preference Optimization with Uncertainty-aware Utility Anchor (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Offline preference optimization methods are efficient for large language models (LLMs) alignment. |
| Approach: | They propose an offline preference optimization framework that estimates uncertainties from preference data . the method enables training even in scenarios where the data is unpaired . |
| Outcome: | The proposed method enables training even in scenarios where the data is unpaired . |
Self-Para-Consistency: Improving Reasoning Tasks at Low Cost for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that self-consistency decoding can improve performance for complex reasoning tasks with large language models. |
| Approach: | They propose a self-consistency decoding strategy that generates multiple paraphrases for each test question and then generates reasoning paths for the original and all the paraphrased questions based on greedy decoding. |
| Outcome: | The proposed strategy reduces the sampling number and improves performance on complex reasoning tasks. |
InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning (2026.acl-long)
Copied to clipboard
Qihang Ai, Pi Bu, Yue Cao, Yingyao Wang, Jihao Gu, Jingxuan Xing, Zekun Zhu, Wei Jiang, Zhicheng Zheng, Jun Song, Yuning Jiang
| Challenge: | Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions. |
| Approach: | They propose a vision-language model that actively seeks human confirmation at critical decision points and a model inspired by reinforcement learning. |
| Outcome: | The proposed model achieves an improvement of 46.8% in inquiry success rate and the best overall success rate among existing baselines on InquireBench. |
Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus (2023.emnlp-main)
Copied to clipboard
Tianhang Zhang, Lin Qiu, Qipeng Guo, Cheng Deng, Yue Zhang, Zheng Zhang, Chenghu Zhou, Xinbing Wang, Luoyi Fu
| Challenge: | Existing methods for detecting hallucinations in LLMs rely on external knowledge for reference retrieval or require sampling multiple responses for consistency verification. |
| Approach: | They propose a reference-free, uncertainty-based method for detecting hallucinations in Large Language Models that imitates human focus in factuality checking from three aspects: focus on the most informative keywords; focus on unreliable tokens in historical context; focus of token properties such as token type and token frequency. |
| Outcome: | The proposed method achieves state-of-the-art performance across all evaluation metrics and eliminates the need for additional information. |
Aligning Large Language Models with Human Preferences through Representation Engineering (2024.acl-long)
Copied to clipboard
Wenhao Liu, Xiaohua Wang, Muling Wu, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Existing methods for achieving this alignment involve employing reinforcement learning from human feedback (RLHF) Existing approaches involve using RLHF to fine-tune LLMs based on human labels . however, RLRF is susceptible to instability during fine- tuning and presents challenges in implementation. |
| Approach: | They propose to use reinforcement learning from human feedback to fine-tune large language models with human preferences to achieve precise control of model behavior. |
| Outcome: | Experiments show that RAHF can be used to capture and manipulate representations to align with a broad spectrum of human preferences or values rather than being confined to a single concept or function. |
A Layered Debating Multi-Agent System for Similar Disease Diagnosis (2025.naacl-short)
Copied to clipboard
| Challenge: | Traditional classification, contrastive learning, and large language models fail to detect subtle clues necessary for differentiation. |
| Approach: | They propose a framework that leverages Large Language Models to achieve accurate disease diagnosis . they structure patient information and integrate extensive medical knowledge to guide the analysis . |
| Outcome: | The proposed framework aims to identify subtle differences between similar diseases . the proposed framework can be used in clinical practice to improve accuracy . |
Public Sentiment Drift Analysis Based on Hierarchical Variational Auto-encoder (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detecting public sentiment drift are not designed for sentiment drift detection. |
| Approach: | They propose a Hierarchical Variational Auto-Encoder model to learn better distribution representation and a new drift measure to directly evaluate distribution changes between historical and new data. |
| Outcome: | The proposed model performs better than three existing state-of-the-art methods. |
EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary (2025.acl-industry)
Copied to clipboard
Yaozhen Liang, Xiao Liu, Jiajun Yu, Zhouhua Fang, Qunsheng Zou, Linghan Zheng, Yong Li, Zhiwei Liu, Haishuai Wang
| Challenge: | Existing document question answering methods reduce inference costs and input tokens. |
| Approach: | They propose a retrieval-augmented generation method that automatically extracts useful entities and generates summaries from documents. |
| Outcome: | The proposed method surpasses baseline retrieval-augmented generation (RAG) and long-context question answering (LC) methods achieve higher accuracy by processing entire documents, but at the cost of increased computational Corresponding authors. |
Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for grammatical error correction are data-hungry and it is hard to train a seq2seq model with good performance without suf-Clean. |
| Approach: | They propose a method inspired by adversarial training to generate more meaningful and valuable training examples by continually identifying weak spots of a model and to enhance the model by gradually adding adversarials to the training set. |
| Outcome: | The proposed method improves generalization and robustness of GEC models by adding adversarial examples to the training set. |
MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
Chia-Yuan Chang, Zhimeng Jiang, Vineeth Rakesh, Menghai Pan, Chin-Chia Michael Yeh, Guanchu Wang, Mingzhi Hu, Zhichao Xu, Yan Zheng, Mahashweta Das, Na Zou
| Challenge: | Existing RAG systems struggle with the quality of retrieval documents, causing performance degradation and reducing performance. |
| Approach: | They propose a training-free RAG framework that leverages multiple LLM agents to collaboratively filter and score retrieved documents. |
| Outcome: | The proposed framework outperforms existing RAG frameworks in QA benchmarks and shows superior answer consistency and answer accuracy over baseline methods. |
StreamingEval: A Unified Evaluation Framework towards Realistic Streaming Video Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing research on streaming video understanding focuses on isolated aspects of visual understanding, but ignores practical deployability under realistic resource constraints. |
| Approach: | They propose a framework to evaluate streaming video understanding capabilities under realistic constraints. |
| Outcome: | StreamingEval benchmarks offline and online video models under a standardized protocol . it evaluates visual encoding efficiency, text decoding latency and task performance . |
Few-shot Classification with Hypersphere Modeling of Prototypes (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fewshot learning use embeddings in space, but they lack expressivity and are difficult to perform statistically. |
| Approach: | They propose a method where class information is represented by hyperspheres with dynamic sizes with two sets of learnable parameters: the hypersphere’s center and the radius. |
| Outcome: | The proposed method is much more expressive than embeddings and performs better than statistical modeling. |
Unlocking Memorization in Large Language Models with Dynamic Soft Prompting (2024.emnlp-main)
Copied to clipboard
Zhepeng Wang, Runxue Bao, Yawen Wu, Jackson Taylor, Cao Xiao, Feng Zheng, Weiwen Jiang, Shangqian Gao, Yanfu Zhang
| Challenge: | Pretrained large language models excel in a variety of natural language processing tasks . however, they pose significant security risks due to their tendency to memorize training data . |
| Approach: | They propose a method to estimate LLM memorization using dynamic, prefix-dependent soft prompts. |
| Outcome: | The proposed method can achieve maximum relative improvement of 135.3% and 39.8% over baseline compared to state-of-the-art methods. |
Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment (2022.acl-long)
Copied to clipboard
Zijie Huang, Zheng Li, Haoming Jiang, Tianyu Cao, Hanqing Lu, Bing Yin, Karthik Subbian, Yizhou Sun, Wei Wang
| Challenge: | Existing methods to predict missing facts in knowledge graphs are limited in language alignment . SS-AGA uses seed alignment as an edge type to fuses all KGs as a whole graph . |
| Approach: | They propose a self-supervised adaptive graph alignment method that fuses all KGs as a whole graph by regarding alignment as 'a new edge type' they propose SS-AGA method that uses relation-aware attention weights to capture potential alignment pairs in a new paradigm. |
| Outcome: | The proposed method can predict missing facts in a knowledge graph (KG) but language alignment is scarce and new alignment identification is noisy. |
Knowledge-Selective Pretraining for Attribute Value Extraction (2023.findings-emnlp)
Copied to clipboard
Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chao Zhang, Bing Yin, William Wang, Xiaodan Zhu
| Challenge: | Existing methods for AVE are limited on rare attributes due to poor generalization ability. |
| Approach: | They propose to leverage pretraining and transfer learning to address weaknesses in existing methods. |
| Outcome: | The proposed method achieves new state-of-the-art performance without pretraining on rare attributes with limited training resources. |
MAssistant: A Personal Knowledge Assistant for MOOC Learners (D19-3)
Copied to clipboard
| Challenge: | Massive Open Online Courses (MOOCs) have experienced a rapid development since 2012 . many MOOC platforms have been launched, including Coursera1 , edX2 , and Udacity3 etc. |
| Approach: | They present a personal knowledge assistant system called MAssistant for MOOC learners . MAsistants has a large-scale concept graph built from open data . it also provides a browser extension which interacts with users during video lectures . |
| Outcome: | The proposed system helps users trace the concepts they have learned in MOOCs, and to build their own concept graphs. |
PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reward models evaluate empathy from a single perspective, overlooking bidirectional interaction nature of empathy. |
| Approach: | They propose a reward model that evaluates empathy from a single perspective . they propose PERM to integrate a bystander perspective to monitor overall interaction quality . |
| Outcome: | a new reward model outperforms state-of-the-art models on an emotional intelligence benchmark and an industrial daily conversation dataset. |
Interactive Learning for LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing multi-agent learning approaches foster collaboration among Large Language Models (LLMs) yet they still rely on re-executing the MAS during inference. |
| Approach: | They propose a co-learning framework that integrates Dynamic Interaction and Perception Calibration to enhance LLMs' independent problem-solving ability. |
| Outcome: | The proposed framework integrates Dynamic Interaction and Perception Calibration to improve LLMs' independent problem-solving ability. |
SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis (2025.findings-naacl)
Copied to clipboard
Hengxing Cai, Xiaochen Cai, Junhan Chang, Sihang Li, Lin Yao, Wang Changxin, Zhifeng Gao, Hongshuai Wang, Li Yongge, Mujie Lin, Shuwen Yang, Jiankun Wang, Mingjun Xu, Jin Huang, Xi Fang, Jiaxi Zhuang, Yuqi Yin, Yaqi Li, Changhong Chen, Zheng Cheng, Zifeng Zhao, Linfeng Zhang, Guolin Ke
| Challenge: | Existing benchmarks fail to adequately evaluate the proficiency of Large Language Models (LLMs) Existing standards do not cover the skills needed to evaluate LLMs in scientific literature analysis. |
| Approach: | They propose a benchmark to evaluate the proficiency of large language models in scientific literature analysis. |
| Outcome: | SciAssess evaluates 11 LLMs on multiple tasks across scientific fields. |
Detecting Spoilers in Movie Reviews with External Movie Knowledge and User Networks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models focus on the textual content of the review, while spoiler detection requires putting the review into the context of facts and knowledge regarding movies. |
| Approach: | They propose a network-based spoiler detection model that takes into account external knowledge about movies and user activities on movie review platforms. |
| Outcome: | The proposed model takes into account external knowledge about movies and user activities on movie review platforms while incorporating user networks. |
Multimodal Table Understanding (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to understanding tables rely on textual inputs and table images are difficult to access in real-world scenarios. |
| Approach: | They propose a multimodal table understanding problem where the model needs to generate correct responses to various table-related requests based on the given table image. |
| Outcome: | The proposed model outperforms open-source MLLMs on 23 benchmarks under held-in and held-out settings. |
Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work on generating empathetic responses by utilizing the speaker's emotion has not been successful. |
| Approach: | They propose an approach which incorporates an adaptive module for commonsense knowledge selection to ensure consistency between the generated empathetic responses and the speaker’s situation. |
| Outcome: | The proposed approach outperforms baseline models in both automatic and human evaluations, exhibiting the generation of more coherent and empathetic responses. |
Graph Reasoning Paradigm: Structured and Symbolic Reasoning with Topology-Aware Reinforcement Learning for Large Language Models (2026.acl-long)
Copied to clipboard
Runxuan Liu, Xianhao Ou, Xinyan Ma, Jiyuan Wang, Jiafeng Liang, Jiaqi Li, Tao He, Zheng Chu, Rongchuan Mu, Zekun Wang, Baoxin Wang, Dayong Wu, Ming Liu, Shijin Wang, Guoping Hu, Bing Qin
| Challenge: | Existing methods for long chain-of-thought (LCoT) are coarse-grained, reward hacking, and poor generalization. |
| Approach: | They propose a Long Chain-of-Thought (LCoT) model that integrates reinforcement learning with verifiable rewards with a process-aware verification approach. |
| Outcome: | The proposed model improves reasoning and code generation tasks while reducing the cost of training and performance bottlenecks. |
Ghost in the Shell: Synonym-Aware Logit Shaping Fingerprint for Copyright Protection of Large Vision-Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing fingerprinting methods for large vision-language models rely on backdoors to elicit abnormal outputs, but direct distortion of the model’s original outputs compromises modality alignment and degrades multimodal capabilities. |
| Approach: | They propose to embed a robust fingerprint while preserving the original normal outputs of the model. |
| Outcome: | The proposed fingerprint maintains multimodal performance and substantially enhances fingerprint robustness. |
Orthogonal Subspace Learning for Language Model Continual Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for continual learning in language models suffer catastrophic forgetting when learning sequential tasks. |
| Approach: | They propose an orthogonal low-rank adaptation approach for continual learning in language models that uses orthogons to learn sequentially. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on continual learning benchmarks and preserves generalization ability of LLMs on unseen tasks. |
Exploring Lottery Prompts for Pre-trained Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to optimize pre-trained language models are expensive and slow to scale. |
| Approach: | They propose to search for instance-level lottery prompts and generalize them to unseen data . they validate the assumption that for every instance, there is almost always a lottery prompt that induces the correct prediction from the PLM . |
| Outcome: | The proposed method can achieve comparable results with other gradient-free and optimization-free baselines. |
WebNovelBench: Placing LLM Novelists on the Web Novel Distribution (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing benchmarks for long-form novel generation lack scale, diversity, or objective measures. |
| Approach: | They propose a framework that assesses long-form novel generation using an LLM-as-Judge approach. |
| Outcome: | The proposed framework differentiates between human-written masterpieces, popular web novels, and LLM-generated content. |
An Efficient Framework for Whole-Page Reranking via Single-Modal Supervision (2026.acl-industry)
Copied to clipboard
Zishuai Zhang, Sihao Yu, null Xiewenyi, Ying Nie, Junfeng Wang, Zhiming Zheng, Dawei Yin, Hainan Zhang
| Challenge: | Existing whole-page reranking methods require large-scale expert annotations to achieve high-quality results. |
| Approach: | They propose a whole-page reranking framework that converts single-modal rankers into page-level guidance by constructing budget-aware candidates for cross-modal annotations and distilling intra-modality preferences to align relevance scales across modalities. |
| Outcome: | The proposed framework reduces annotation costs by 70-90% while outperforming fully-annotated reranking baselines. |
Lifting Optimized Binaries to Canonical Compiler IR via Structure-Aware Retrieval and Iterative Verification (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for decompiling binary code are brittle due to compiler optimizations that distort control-flow and data-flow structure. |
| Approach: | They propose a system that lifts optimized binaries to canonical compiler intermediate representation (IR) BRIDGE uses control-flow-aware retrieval-augmented generation with feedback-driven verification . |
| Outcome: | The proposed system outperforms seven baselines on humanEval-Decompile and MBPP, lifting x86-64 and ARM64 binaries to LLVM IR. |
Capturing the Content of a Document through Complex Event Identification (2022.starsem-1)
Copied to clipboard
| Challenge: | Recent work grouped granular events into more general events, called complex events . however, this approach assumes that a given complex event is always described in consecutive sentences . |
| Approach: | They propose a context-augmented representation learning approach that uses contextual information to model pairwise relation between granular events. |
| Outcome: | The proposed approach outperforms baselines on the complex event identification task. |
Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su
| Challenge: | Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context. |
| Approach: | They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration. |
| Outcome: | Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness. |
Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference (2026.acl-long)
Copied to clipboard
| Challenge: | Speculative decoding (SD) is a powerful and efficient way to accelerate autoregressive generation. |
| Approach: | They propose a training-free framework that recovers valid tokens discarded by standard verification . they use online correction memory and Semantic Consistency Gating to analyze rejections . |
| Outcome: | The proposed framework outperforms existing methods and achieves peak throughput speedup of 2.33x. |
ArkRepoBench: A Repository-Level Code Completion Benchmark for HarmonyOS Development (2026.findings-acl)
Copied to clipboard
Yanlin Wang, Bowen Zhang, Yanli Wang, Daya Guo, Terry Yue Zhuo, Jiachi Chen, Mingwei Liu, Xingong Zhang, Zibin Zheng
| Challenge: | Despite the maturity of LLM-based code assistance for mainstream languages, the capabilities of ArkTS are largely unexplored. |
| Approach: | They propose to benchmark repository-level code completion for ArkTS using 7,519 samples from 20 official HarmonyOS repositories. |
| Outcome: | The proposed benchmark covers multiple difficulty levels and categorizes completion instances into Single-File, Cross-Filled Independent, and Cross-Filed Dependent settings based on dependency analysis. |
LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have shown inspiring achievements in constructing autonomous agents that rely on language descriptions as inputs. |
| Approach: | They propose a flexible and simulation-free testbed that simulates 6 representative embodied tasks in textual embodies. |
| Outcome: | The proposed testbed offers adaptability to diverse environments without multiple simulation engines and allows easy customization of communication and action strategies. |
Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension (2022.acl-long)
Copied to clipboard
Ying Xu, Dakuo Wang, Mo Yu, Daniel Ritchie, Bingsheng Yao, Tongshuang Wu, Zheng Zhang, Toby Li, Nora Bradford, Branda Sun, Tran Hoang, Yisi Sang, Yufang Hou, Xiaojuan Ma, Diyi Yang, Nanyun Peng, Zhou Yu, Mark Warschauer
| Challenge: | Existing QA datasets rarely distinguish fine-grained reading skills, such as the understanding of varying narrative elements. |
| Approach: | They propose to use FairytaleQA to generate 10,580 questions based on 278 children-friendly stories to assess model's fine-grained learning skills. |
| Outcome: | The proposed dataset consists of 10,580 questions derived from 278 children-friendly stories, covering seven types of narrative elements or relations. |
Why Multi-Interest Fairness Matters: Hypergraph Contrastive Multi-Interest Learning for Fair Conversational Recommender System (2025.findings-acl)
Copied to clipboard
| Challenge: | Unfairness is a well-known challenge in Recommender Systems (RSs) some approaches have started to improve fairness in offline or static contexts, but it often exacerbates over time, leading to significant problems like the Matthew effect, filter bubbles, and echo chambers. |
| Approach: | They propose a framework to promote multi-interest diversity fairness in RSs by establishing diverse hypergraphs through contrastive learning. |
| Outcome: | The proposed framework achieves state-of-the-art performance while effectively alleviating unfairness in two CRS-based datasets. |
LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback (2025.findings-acl)
Copied to clipboard
Bofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Dayiheng Liu, Chang Zhou, Wen Xiao, Tianyu Liu, Baobao Chang
| Challenge: | Existing mathematical verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions. |
| Approach: | They propose a natural language feedback-enhanced verifier that can validate the correctness of response generated by policy models by constructing automatically generated training data and a two-stage training paradigm. |
| Outcome: | The proposed verifier significantly improves in verification and reinforcement learning and alleviates data-demanding problems of the reward model. |
Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations (2024.findings-acl)
Copied to clipboard
| Challenge: | Structured pruning is a feasible solution for end-side LLM deployment . however, achieving a high compression ratio for scaled-up LLMs remains a challenge . |
| Approach: | They propose a task-agnostic structured pruning approach coupled with a compact Transformer architecture to prune LLMs into an intra-module low-rank architecture. |
| Outcome: | The proposed approach reduces transitional activations inside multi-head attention (MHA) and multi-layer perceptron (MLP) modules while preserving inter-module activations sensitive to perturbations. |
IHEval: Evaluating Language Models on Following the Instruction Hierarchy (2025.naacl-long)
Copied to clipboard
Zhihan Zhang, Shiyang Li, Zixuan Zhang, Xin Liu, Haoming Jiang, Xianfeng Tang, Yifan Gao, Zheng Li, Haodong Wang, Zhaoxuan Tan, Yichuan Li, Qingyu Yin, Bing Yin, Meng Jiang
| Challenge: | Instruction-tuned language models (LMs) are increasingly deployed as interactive services across various applications. |
| Approach: | They propose a benchmark to evaluate models' ability to follow the instruction hierarchy by comparing their models to a set of benchmarks. |
| Outcome: | The proposed benchmark covers 3,538 examples across nine tasks covering cases where instructions in different priorities either align or conflict. |
Self-Ensemble: Mitigating Confidence Distortion for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models exhibit a confidence distortion problem on multichoice question-answering . Self-Ensemble solves this problem by splitting the choices into several groups . |
| Approach: | They propose a method that splits LLM choices into several groups and ensembles them to reach a final decision. |
| Outcome: | The proposed method outperforms standard inference and baseline methods on MCQA. |
Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing VideoQA models struggle to adapt to new questions or tasks posed by newly available content. |
| Approach: | They propose a continual learning framework that fine-tunes a large language model for a sequence of tasks and integrates specific question constraint prompting, knowledge acquisition prompting and visual temporal awareness prompting. |
| Outcome: | The proposed model achieves 55.14% accuracy on both NExT-QA and DramaQA datasets and 71.24% accuracy for DramaQA. |
Few-NERD: A Few-shot Named Entity Recognition Dataset (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to few-shot named entity recognition (NER) focus on coarse-grained entities with few examples, while most unseen entities are fine-grounded. |
| Approach: | They present a human-annotated few-shot named entity recognition dataset . they construct benchmark tasks to assess the generalization capability of models . |
| Outcome: | The proposed model is the first few-shot NER dataset and the largest human-crafted NER data set. |
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models with stacked layers do not explicitly model hierarchical structure of language understanding. |
| Approach: | They propose a recursive Transformer model based on differentiable CKY style binary trees to emulate hierarchical composition process. |
| Outcome: | The proposed model can predict words given their left and right abstraction nodes. |
MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MT-RewardTree provides a framework for constructing, evaluating, and deploying process reward models in machine translation (MT) |
| Approach: | They propose a method for automatically generating token-level preference pairs using approximate Monte Carlo Tree Search. |
| Outcome: | The proposed framework achieves state-of-the-art performance in token-level evaluation and sequence-level analysis. |
PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing LLM agents generate verbose and inefficient natural language plans to guide reasoning, which restricts agents’ ability to generalize across similar tasks. |
| Approach: | They propose a pseudocode-style planning guide optimization method that captures the structural logic of reasoning and uses two planning-oriented rewards to enhance agent learning. |
| Outcome: | The proposed method outperforms existing LLM agents on representative agent benchmarks and outperformed the current leading baselines. |
UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations (2025.acl-long)
Copied to clipboard
Fengran Mo, Yifan Gao, Chuan Meng, Xin Liu, Zhuofeng Wu, Kelong Mao, Zhengyang Wang, Pei Chen, Zheng Li, Xian Li, Bing Yin, Meng Jiang
| Challenge: | Existing conversational search systems are usually built with two different models . this separation restricts the system from leveraging the model's intrinsic knowledge simultaneously . Existing studies for developing unified models cannot fully address the aspects of understanding conversational context, managing retrieval independently, and generating responses. |
| Approach: | They propose to unify dense retrieval and response generation for large language models in conversation by fine-tuning and mitigating data discrepancy. |
| Outcome: | The proposed model can outperform existing models on five conversational search datasets and reduce inconsistency risks while mitigating data discrepancy. |
MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models (2025.emnlp-main)
Copied to clipboard
Zhengyi Zhao, Shubo Zhang, Yuxi Zhang, Yanxi Zhao, Yifan Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu
| Challenge: | Current approaches focus on isolated meme analysis, either for harmful content detection or standalone interpretation, overlooking a fundamental challenge: the same meme can express different intents depending on its conversational context. |
| Approach: | They propose a benchmark to evaluate how large vision language models understand memes in their original context. |
| Outcome: | The proposed benchmark evaluates how large vision language models understand meme intent in their original context. |
A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models (2024.emnlp-main)
Copied to clipboard
Zhihao Wang, Shiyu Liu, Jianheng Huang, Wang Zheng, YiXuan Liao, Xiaoxin Chen, Junfeng Yao, Jinsong Su
| Challenge: | Version updates are an indispensable requirement for Large Language Models . a large learning rate in the first stage and a complete learning decay process are crucial for version updates of LLMs. |
| Approach: | They propose a learning rate path switching training paradigm for version updates of Large Language Models. |
| Outcome: | The proposed paradigm reduces training cost to 58% when training four versions of LLMs compared to PTFS and CPT . |
Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for stance detection are not applicable to zero-shot and few-shot scenarios. |
| Approach: | They propose a model that integrates commonsense knowledge into a stance detection model. |
| Outcome: | The proposed model outperforms state-of-the-art methods on zero-shot and few-shot stance detection tasks. |
AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)
Copied to clipboard
Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Xin Guo, Dingwen Yang, Chenyang Liao, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang
| Challenge: | Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents. |
| Approach: | They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction. |
| Outcome: | The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction. |
An Empirical Study of Instruction-tuning Large Language Models in Chinese (2023.findings-emnlp)
Copied to clipboard
| Challenge: | emergence of ChatGPT validates the potential of large language models (LLMs) in artificial general intelligence (AGI) however, the closed source of LLMs coupled with the requirement for massive computing resources has deterred researchers from reaching the LLM training stage. |
| Approach: | They propose to use Chinese instruction-tuning LLMs as a cookbook for customizing LLM models that can better respond to Chinese instructions. |
| Outcome: | The proposed LLM can be used to customize Chinese LLMs that can better respond to Chinese instructions. |
Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to build a visual dialog (VD) Questioner do not provide explicit guidance for questioner to generate visually related and informative questions. |
| Approach: | They propose a Related entity enhanced Questioner that learns entity-based questioning strategy from human dialogs. |
| Outcome: | The proposed approach achieves state-of-the-art performance on image-guessing task and question diversity. |
Can Public Large Language Models Help Private Cross-device Federated Learning? (2024.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have shown that public data can be used to improve privacy-utility trade-offs for large and small language models. |
| Approach: | They propose to use large-scale public data to help differentially private FL training . they propose a distribution matching algorithm with theoretical grounding to sample public data close to private data distribution . |
| Outcome: | The proposed method is efficient and effective for training private models by taking advantage of public data. |
Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognition (2022.findings-naacl)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a system for identifying text spans pertaining to specific entity types. |
| Approach: | They propose a method to investigate the regularity of Chinese NER's entity mentions by a regularity-aware module and a periodicity-gnostic module. |
| Outcome: | The proposed model significantly outperforms previous state-of-the-art methods on three benchmark datasets and a practical medical dataset. |
Multi-Programming Language Sandbox for LLMs (2025.acl-demo)
Copied to clipboard
Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang
| Challenge: | MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs). |
| Approach: | They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models. |
| Outcome: | The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs). |
Pub-LawBench: Public-Oriented Benchmarking for LegalAI (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation frameworks focus on legal professionals, not legal professionals. |
| Approach: | They propose a public-oriented LegalAI benchmark grounded in legal functionalism and genre analysis to address this gap. |
| Outcome: | The proposed model evaluates 17 large language models on Pub-LawBench using simple prompts and Chain-of-Thought under a vanilla inference setting. |
Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods to enhance the zeroshot generalization of DST fail to effectively decouple semantics of samples, limiting the zero-shot performance of the system. |
| Approach: | They propose a new learning schema that explicitly disentangles the semantics of seen data and leverages the performance and robustness with the mixture-of-experts mechanism. |
| Outcome: | The proposed model achieves state-of-the-art on multiWOZ2.1 with 10M trainable parameters and is robust to the mixture-of experts mechanism. |
Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval (2021.acl-long)
Copied to clipboard
Zijing Ou, Qinliang Su, Jianxing Yu, Bang Liu, Jingwen Wang, Ruihui Zhao, Changyou Chen, Yefeng Zheng
| Challenge: | Existing methods for document hashing combine only one of semantics and neighborhood information, lacking a theoretical principle to guide the integration process. |
| Approach: | They propose to encode neighborhood information with a graph-induced Gaussian distribution and integrate it with generative models. |
| Outcome: | The proposed model can be trained as efficiently as state-of-the-art methods on benchmark datasets. |
DNA: Denoised Neighborhood Aggregation for Fine-grained Category Discovery (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to learn compact cluster representations from coarsely labeled data are noisy and degrade the quality of learning. |
| Approach: | They propose a framework that encodes semantic structures of data into the embedding space . they retrieve k-nearest neighbors of a query as positive keys to capture similarities . |
| Outcome: | The proposed framework can retrieve more accurate neighbors and outperform state-of-the-art models by a large margin. |
AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Recent work on learning from multiple tasks has shown that adding an extra fusion layer to implement knowledge composition is non-scalable for some applications. |
| Approach: | They propose a two-stage knowledge distillation algorithm to extract task specific knowledge by using local data to train a student adapter. |
| Outcome: | Experiments on frequently asked question retrieval in task-oriented dialog systems validate the efficiency of AdapterDistillation. |
Hierarchical Enhancement Framework for Aspect-based Argument Mining (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods have primarily treated ABAM as a nested named entity recognition problem, overlooking the need for tailored strategies to effectively address the specific challenges of ABA M tasks. |
| Approach: | They propose a layer-based Hierarchical Enhancement Framework (HEF) for Aspect-Based Argument Mining and introduce three new components to improve the performance and accuracy. |
| Outcome: | Experiments on multiple datasets and tasks verify the effectiveness of the proposed framework and components. |
Modularized Interaction Network for Named Entity Recognition (2021.acl-long)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) models focus on word-level information, while segment-based models focus only on word level information. |
| Approach: | They propose a Modularized Interaction Network (MIN) model which utilizes both word-level information and segment-level dependencies. |
| Outcome: | The proposed model outperforms the current state-of-the-art models on three NER benchmark datasets. |
TALON: A Multi-Agent Framework for Long-Table Exploration and Question Answering (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to query-relevant content retrieval fail to retrieve contextually relevant data. |
| Approach: | They propose a multi-agent framework for table question answering over long tables . TALON features a planning agent that iteratively invokes a tool agent to access tabular data . |
| Outcome: | The proposed framework achieves average accuracy improvements of 7.5% and 12.0% across all language models. |
Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for predicting hallucinations suffer from two drawbacks: Lack of scalable token-level rewards and Neglect of visual-anchored tokens. |
| Approach: | They propose a Token Preference Optimization model with self-calibrated rewards . they propose based on visual-anchored tokens and visual-aware training objective . |
| Outcome: | The proposed model improves hallucination performance by focusing on visual-anchored tokens without fine-grained annotations. |
ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants (2026.acl-long)
Copied to clipboard
Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Qi Liu, Ken Deng, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu, Xuefeng Chen, Wanxi Deng, Wenbo Su, Bo Zheng
| Challenge: | Existing studies on large language model-based agents focus on evaluation benchmarks without training support. |
| Approach: | They propose a large-scale Chinese shopping simulation environment that uses large language models to train agents. |
| Outcome: | The proposed model performs poorly in a large-scale and challenging shopping environment in China. |
ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection (2025.findings-acl)
Copied to clipboard
Jiaqi Li, Xinyi Dong, Yang Liu, Zhizhuo Yang, Quansen Wang, Xiaobo Wang, Song-Chun Zhu, Zixia Jia, Zilong Zheng
| Challenge: | ReflectEvo-460k is a large-scale, comprehensive, self-generated reflection dataset with broadened instructions and diverse multi-domain tasks. |
| Approach: | They propose a pipeline that iteratively generates self-reflection for self-training and a large-scale reflection dataset with broadened instructions and diverse multi-domain tasks. |
| Outcome: | The proposed pipeline improves Llama-3 reasoning ability by up to 71.2% and Mistral by upto 44.4%. |
AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal representation is crucial for E-commerce tasks such as identical product retrieval. |
| Approach: | They propose an approach which leverages the generative power of Multimodal Large Language Models to extract key attributes from product images and text and enhances representation learning through a two-stage training framework. |
| Outcome: | The proposed model achieves state-of-the-art on multiple downstream retrieval tasks, validating the effectiveness of harnessing generative models to advance fine-grained representation learning. |
Multimodal Sarcasm Target Identification in Tweets (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to detect sarcasm target with text lacking context are not sufficient and complete. |
| Approach: | They propose a multi-modal sarcasm target identification task that performs both textual and visual detection. |
| Outcome: | The proposed model can perform textual target labeling and visual target detection. |
SubDocTrans: Enhancing Document-level Machine Translation with Plug-and-play Multi-granularity Knowledge Augmentation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Document translations generated by large language models suffer from poor consistency, weak coherence, and omission errors. |
| Approach: | They propose a document-level machine translation framework that extracts knowledge from documents to produce high-quality translations. |
| Outcome: | The proposed framework improves consistency and coherence, reduces omission errors, and mitigates hallucinations. |
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)
Copied to clipboard
Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen
| Challenge: | Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed . |
| Approach: | They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities. |
| Outcome: | The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech . |
Generative Music Models’ Alignment with Professional and Amateur Users’ Expectations (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent years have witnessed rapid advances in text-to-music generation using large language models. |
| Approach: | They propose a task to align AI-generated music with human expressions . they use a dataset of over 1.5 million songs to analyze their content . |
| Outcome: | The proposed framework outperforms baseline models and facilitates end-to-end generation of songs audio. |
Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models (2026.findings-acl)
Copied to clipboard
Teng Wang, Jiang Zhangyi, Zhenqi He, Hailei Gong, Shenyang Tong, Wenhan Yang, Zeyu Li, Yanan Zheng, Zifan He, Zewen Ye, Shengjie Ma, Jianping Zhang
| Challenge: | Existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps. |
| Approach: | They propose a reward model approach which evaluates both individual and consecutive reasoning steps from fine-grained and coarse-grounded level. |
| Outcome: | Empirical results show that the proposed model performs better than existing PRMs and is more robust than existing models. |
Evaluating Memory Capability in Continuous Lifelog Scenario (2026.findings-acl)
Copied to clipboard
Jianjie Zheng, Zhichen Liu, Zhanyu Shen, Jingxiang Qu, Guanhua Chen, Yile Wang, Yang Xu, Yang Liu, Sijie Cheng
| Challenge: | Existing benchmarks focus on online one-on-one chatting or human-AI interactions, neglecting real-world scenarios. |
| Approach: | They propose a framework to curate a lifelog benchmark that combines two subsets of audio data to address temporal leakage in offline settings. |
| Outcome: | The proposed framework outperforms existing benchmarks on live chats and AI interactions. |
DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection (2022.findings-emnlp)
Copied to clipboard
Haoran Meng, Zheng Xin, Tianyu Liu, Zizhen Wang, He Feng, Binghuai Lin, Xuemin Zhao, Yunbo Cao, Zhifang Sui
| Challenge: | DialogUSR is a plug-in and domain-agnostic module that empowers multi-intent detection for chatbots . a single user query triggers inquiries on highspeed train ticket price and weather of destination. |
| Approach: | They propose a dialog utterance splitting and reformulation task that splits multi-intent user query into multiple single-intention sub-queries and recovers all coreferred and omitted information in the sub-questions. |
| Outcome: | The proposed model can be used to split multi-intent user queries into multiple sub-queries . it can be trained in two stages and perform in-depth analyses on the proposed models . |
Construction of the Literature Graph in Semantic Scholar (N18-3)
Copied to clipboard
Waleed Ammar, Dirk Groeneveld, Chandra Bhagavatula, Iz Beltagy, Miles Crawford, Doug Downey, Jason Dunkelberger, Ahmed Elgohary, Sergey Feldman, Vu Ha, Rodney Kinney, Sebastian Kohlmeier, Kyle Lo, Tyler Murray, Hsu-Han Ooi, Matthew Peters, Joanna Power, Sam Skjonsberg, Lucy Lu Wang, Chris Wilhelm, Zheng Yuan, Madeleine van Zuylen, Oren Etzioni
| Challenge: | Fig. 1 summarizes a scalable system for organizing published scientific literature into a heterogeneous graph . authors describe methods used to enable semantic features in www.semanticscholar.org . |
| Approach: | They describe a scalable system for organizing published scientific literature into a heterogeneous graph to facilitate algorithmic manipulation and discovery. |
| Outcome: | The proposed system can be deployed on a scalable platform and report empirical results for each task. |
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (P19-1)
Copied to clipboard
Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang
| Challenge: | Simultaneous translation is notoriously dif- ficult due to word-order differences. |
| Approach: | They propose a prefix-to-prefix framework that implicitly learns to anticipate in a single translation model. |
| Outcome: | The proposed framework achieves low latency and reasonable qual- ity on 4 directions. |
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection (2024.naacl-long)
Copied to clipboard
Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin
| Challenge: | Instruction-tuned Large Language Models (LLMs) can modulate responses based on human instructions, but they can be maliciously steered to impact society in subtle but persistent ways. |
| Approach: | They propose a backdoor attack setting that allows an attacker to inject a virtual prompt into an LLM to steer it without any explicit injection at its input. |
| Outcome: | The proposed method is able to poison the model's instruction tuning data and show that it is highly effective in steering the model. |
Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods (2026.acl-long)
Copied to clipboard
Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang, Xuming Hu
| Challenge: | Recent efforts to accelerate inference in Multimodal Large Language Models have focused on visual token compression. |
| Approach: | They propose a framework that leverages downsampling as a discriminator to denoise existing benchmarks. |
| Outcome: | The proposed evaluation framework leverages downsampling as a discriminator to denoise existing benchmarks. |
Can Language Models Follow Multiple Turns of Entangled Instructions? (2025.findings-emnlp)
Copied to clipboard
Chi Han, Xin Liu, Haodong Wang, Shiyang Li, Jingfeng Yang, Haoming Jiang, Zhengyang Wang, Qingyu Yin, Liang Qiu, Changlong Yu, Yifan Gao, Zheng Li, Bing Yin, Jingbo Shang, Heng Ji
| Challenge: | Despite of significant achievements in improving instruction-following capabilities of large language models, the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge. |
| Approach: | They construct multi-turn instruction with 1.1K high-quality multi-turned conversations using the human-in-the-loop approach and examine their capabilities. |
| Outcome: | The proposed model shows that it is difficult to integrate multiple turns and balance competing objectives when instructions intersect or conflict. |
Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models (2025.emnlp-main)
Copied to clipboard
Sina Semnani, Jirayu Burapacheep, Arpandeep Khatua, Thanawan Atchariyachanvanit, Zheng Wang, Monica Lam
| Challenge: | a new study examines the accuracy of Wikipedia's factual inconsistencies . a corpus-level inconsistent detection system can help editors identify inconsistances . |
| Approach: | They propose a corpus-level inconsistency detection system that combines LLM reasoning with retrieval to detect and contextualize potential contradictions for human review. |
| Outcome: | The proposed system can detect inconsistencies in Wikipedia and human review. |
DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering (2025.acl-long)
Copied to clipboard
Rong Cheng, Jinyi Liu, Yan Zheng, Fei Ni, Jiazhen Du, Hangyu Mao, Fuzheng Zhang, Bo Wang, Jianye Hao
| Challenge: | Existing approaches to multi-hop question answering struggle to identify and organize dynamic knowledge . et al., 2023; Liu e.t. al. 2023) suggest a dual-process framework for multi-step reasoning . |
| Approach: | They propose a synergistic dual-process framework that integrates reasoning and retrieval. |
| Outcome: | The proposed framework improves answer accuracy and coherence even in smaller-scale models. |
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)
Copied to clipboard
Kangan Qian, Sicong Jiang, Yang Zhong, Ziang Luo, Zilin Huang, Tianze Zhu, Kun Jiang, Mengmeng Yang, Zheng Fu, Jinyu Miao, Yining Shi, He Zhe Lim, Li Liu, Tianbao Zhou, Hongyi Wang, Huang Yu, Yifei Hu, Guang Li, Guang Chen, Hao Ye, Lijun Sun, Diange Yang
| Challenge: | Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. |
| Approach: | AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks. |
| Outcome: | Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% . |
Uncertainty Aware Learning for Language Model Alignment (2024.acl-long)
Copied to clipboard
| Challenge: | Existing alignment strategies that focus on diverse and high-quality data often overlook the intrinsic uncertainty of tasks, learning all data samples equally. |
| Approach: | They propose to introduce the sample uncertainty into the alignment of different task scenarios by a simple fashion by setting the label smoothing value of training according to the uncertainty of individual samples. |
| Outcome: | The proposed model outperforms standard supervised fine-tuning on high-entropy tasks and complex low-entropic tasks. |
Similarizing the Influence of Words with Contrastive Learning to Defend Word-level Adversarial Text Attack (2023.findings-acl)
Copied to clipboard
| Challenge: | Neural language models are vulnerable to word-level adversarial text attacks . previous word-based search methods assume important words influence prediction . |
| Approach: | They propose a method for similarizing the influence of words with contrast learning that encourages model to learn sentence representations in which words of varying importance have a more uniform influence on prediction. |
| Outcome: | The proposed method is compatible with various training methods and improves model robustness against various adversarial attacks. |
Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing (2025.findings-acl)
Copied to clipboard
Wenhao Liu, Siyu An, Junru Lu, Muling Wu, Tianlong Li, Xiaohua Wang, Changze Lv, Xiaoqing Zheng, Di Yin, Xing Sun, Xuanjing Huang
| Challenge: | Role-playing Agents (RPAs) struggle to recognize and respond to hard queries that conflict with their role-play knowledge. |
| Approach: | They propose a lightweight representation editing approach that conveniently shifts conflicting requests to the rejection region, thereby enhancing the model’s refusal accuracy. |
| Outcome: | The proposed model improves RPAs’ refusal ability of conflicting requests while maintaining their general role-playing capabilities. |
AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models (2026.findings-acl)
Copied to clipboard
Yimin Deng, Yejing Wang, Zhenxi Lin, Zichuan Fu, Guoshuai Zhao, Derong Xu, Yefeng Zheng, Xiangyu Zhao, Xian Wu, Li Zhu, Xueming Qian
| Challenge: | Existing methods for temporal reasoning are limited and apply a fixed pipeline to all questions. |
| Approach: | They propose an adaptive temporal reasoning method that dynamically executes reasoning steps based on context and task requirements. |
| Outcome: | Experiments on two temporal QA benchmarks show the proposed method works. |
AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification (2025.emnlp-main)
Copied to clipboard
Xuan Zhang, Yongliang Shen, Zhe Zheng, Linjuan Wu, Wenqi Zhang, Yuchen Yan, Qiuying Peng, Jun Wang, Weiming Lu
| Challenge: | Existing tools for ambiguous and incomplete queries are limited by manual construction and lack of error correction mechanisms during multi-turn clarification. |
| Approach: | They propose a framework that exploits the mapping between queries and their tool invocation solutions by removing key parameters from queries while retaining them as ground truth. |
| Outcome: | The proposed framework outperforms existing methods while maintaining high accuracy in tool invocation. |
Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing RAG paradigms suffer from the impact of flawed information introduced during the retrieval phrase, thereby diminishing the reliability and correctness of the generated output. |
| Approach: | They propose a framework that empowers models to discern and process information based on its credibility. |
| Outcome: | The proposed framework outperforms existing models with retrieval augmentation and exhibits robustness despite increasing noise in the context. |
Searching for Best Practices in Retrieval-Augmented Generation (2024.emnlp-main)
Copied to clipboard
Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, especially in specialized domains. |
| Approach: | They propose several strategies for deploying RAG that balance performance and efficiency. |
| Outcome: | The proposed approaches can significantly enhance question-answering capabilities and accelerate the generation of multimodal content using a “retrieval as generation” strategy. |
Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation (2024.acl-srw)
Copied to clipboard
| Challenge: | Customizing LLMs for a specific task involves separating high-quality responses from lower-quality ones. Obtaining a large volume of expert-annotated data is costly for most tasks. |
| Approach: | They propose a method that trains the model to prioritize the best responses from a pool of candidates created for a task using ranking metrics. |
| Outcome: | The proposed method is more robust, less sensitive to noise, and can be achieved with limited human annotations or through heuristic methods. |
Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning (2025.findings-emnlp)
Copied to clipboard
Yangning Li, Tingwei Lu, Yinghui Li, Yankai Chen, Wei-Chieh Huang, Wenhao Jiang, Hui Wang, Hai-Tao Zheng, Philip S. Yu
| Challenge: | Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) current methods suffer from the curriculum rigidity, resulting in a fixed and potentially sub-optimal learning trajectory. |
| Approach: | a framework for efficient instruction tuning is proposed to address the issue of curriculum rigidity . current methods rely on static heuristic difficulty metrics and fail to adapt to evolving capabilities . |
| Outcome: | Efficient instruction tuning aims to enhance the ultimate performance of large language models . current methods suffer from the curriculum rigidity, resulting in a fixed learning trajectory . |
See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)
Copied to clipboard
Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng
| Challenge: | Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence. |
| Approach: | They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction. |
| Outcome: | The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge. |
Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models (2026.acl-long)
Copied to clipboard
Binghai Wang, Yantao Liu, Yuxuan Liu, Tianyi Tang, Shenzhi Wang, Chang Gao, Chujie Zheng, Yichang Zhang, Le Yu, Shixuan Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Bowen Yu, Fei Huang, Junyang Lin
| Challenge: | Recent studies observe a phenomenon where reward models achieve high accuracy on static datasets but fail to generalize effectively during RLHF. |
| Approach: | They propose a method that combines rationale consistency with outcome accuracy to improve performance on RM-Bench and JudgeBench. |
| Outcome: | The proposed method surpasses baselines on RM-Bench and JudgeBench by an average of 5% and improves creative writing tasks by 7%. |
Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)
Copied to clipboard
Lirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang, Yuke Zhu, Bo Zheng, Haobo Wang, Junbo Zhao, Gang Chen, Sheng Guo
| Challenge: | Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity. |
| Approach: | They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability. |
| Outcome: | The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability. |
SAFER: A Controllable Safeguard for LLMs against Backdoor Attacks (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing inference-time defenses lack explicit control over false acceptance rate (FAR) existing inference time defenses aim to mitigate poisoned inputs but lack explicit FAR control . |
| Approach: | They propose a framework that provides explicit control over false acceptance rate without prior knowledge of backdoor samples. |
| Outcome: | The proposed framework outperforms existing inference-time defenses on three benchmark datasets . it provides explicit and provable control over false acceptance rate without prior knowledge of backdoor samples . |
MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval (2025.acl-long)
Copied to clipboard
Junjie Zhou, Yongping Xiong, Zheng Liu, Ze Liu, Shitao Xiao, Yueze Wang, Bo Zhao, Chen Jason Zhang, Defu Lian
| Challenge: | despite the growing demand for multimodal retrieval, there is a lack of training data. |
| Approach: | They propose a data synthesis method that leverages vision language models and open-domain images to generate high-quality data. |
| Outcome: | The proposed method outperforms baseline models on 70 more datasets and can scale up. |
Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Empathy is a key trait of everyday human conversations. |
| Approach: | They propose a serial encoding and Emotion-Knowledge interaction method for empathetic dialogue generation which is more sensitive to emotion dynamics in conversations. |
| Outcome: | The proposed method outperforms baseline evaluations on the utterance-level annotated EMPATHETICDIALOGUES. |
imapScore: Medical Fact Evaluation Made Easy (2024.findings-acl)
Copied to clipboard
| Challenge: | Automated evaluation of natural language generation tasks fails to focus on medical QA because of the diversity in medical terminology. |
| Approach: | They propose a new data structure, imap, to capture key information in questions and answers. |
| Outcome: | The proposed model outperforms state-of-the-art metrics in correlation with human scores. |
ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction (2021.naacl-main)
Copied to clipboard
| Challenge: | Sentiment analysis is a key task in e-commerce to detect fine-to-coarse sentiment polarities. |
| Approach: | They propose to use a large-scale Chinese restaurant review dataset ASAP to investigate the sentiment polarities underlying user reviews. |
| Outcome: | The proposed model outperforms state-of-the-art models on both tasks. |
TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)
Copied to clipboard
Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu
| Challenge: | Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning. |
| Approach: | They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms. |
| Outcome: | The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms. |
Past, Present, and Future: Conversational Emotion Recognition through Structural Modeling of Psychological Knowledge (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Conversational Emotion Recognition (CER) is a task to predict the emotion of an utterance in the context of a conversation. |
| Approach: | They propose a pSychological-Knowledge-Aware Interaction Graph to model the emotional state of an utterance in the context of a conversation. |
| Outcome: | The proposed method achieves state-of-the-art and competitive performance on four popular CER datasets. |
Think Hard Only When Needed: A Hybrid Best-of-N and Beam Search for Efficient Test-Time Compute (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit remarkable reasoning and planning capabilities, yet their substantial inference-time cost significantly impedes deployment in resourceconstrained applications. |
| Approach: | They propose a hybrid inference pipeline that combines beam search and Best-of-N . THROW generates shorter initial trajectories and evaluates them using PRMs . |
| Outcome: | THROW achieves 1.54 and 14.38 latency speedups and 35.7% and 80.4% token reductions on average compared to Best-of-N and beam search . |
CLOWER: A Pre-trained Language Model with Contrastive Learning over Word and Character Representations (2022.coling-1)
Copied to clipboard
Borun Chen, Hongyin Tang, Jiahao Bu, Kai Zhang, Jingang Wang, Qifan Wang, Hai-Tao Zheng, Wei Wu, Liqian Yu
| Challenge: | Pre-trained language models (PLMs) have achieved remarkable performance gains across numerous downstream tasks in natural language understanding. |
| Approach: | They propose a Chinese pre-trained language model that implicitly encodes words into characters . they propose 'contrastive learning over word' and 'character' representations to improve learning . |
| Outcome: | The proposed model can encode words into fine-grained representations without modification of production pipelines. |
A Self-training Framework for Automated Medical Report Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Medical report generation is an important medical artificial intelligence task. |
| Approach: | They propose a framework for medical report generation that exploits unlabeled medical images and a reference-free evaluation metric. |
| Outcome: | The proposed framework performs better than previous fully-supervised models trained on entire training data. |
CVRH: Cross-modal Variational Role Hypergraph Network via Semantic Enhancement for Multi-modal Event Argument Extraction (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on weakly aligning uni-modal representations and generatively data augmentation techniques, but they ignore the potential impact of event role information on MEAE. |
| Approach: | They propose a cross-modal variational role hypergraph network via semantic enhancement to model high-order role correlations among cross-mod arguments in multi-modal documents. |
| Outcome: | The proposed method achieves a 6.9% improvement in F1-score on the M2E2 benchmark compared to current state-of-the-art methods. |
Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning (2026.findings-acl)
Copied to clipboard
Zichuan Fu, Xian Wu, Guojing Li, Yejing Wang, Yijun Chen, Zhao Zihao, Luo Yixuan, Hanyu Yan, Yefeng Zheng, Xiangyu Zhao
| Challenge: | Recent advances in large language models (LLMs) have catalyzed the rise of reasoningintensive inference paradigms, where models perform explicit step-by-step reasoning before generating final answers. |
| Approach: | They propose a large-small LLM collaboration framework that synergizes large and small language models to achieve high-quality reasoning with significantly reduced computational cost. |
| Outcome: | The proposed framework outperforms the mentor LLM while preserving the benefits of the thinking paradigm of LLMs. |
UECA-Prompt: Universal Prompt for Emotion Cause Analysis (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods adopt fine-tuning paradigm to solve certain types of ECA tasks. Existing models suffer from dataset bias. |
| Approach: | They propose a universal prompt tuning method to solve different ECA tasks in a unified framework and a sequential learning module to ease the dataset bias. |
| Outcome: | The proposed method achieves competitive performance on the ECA datasets. |
TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing work mitigates memory overhead by offloading or compressing the Key-Value cache. |
| Approach: | They propose a method that integrates quantization and offloading into a generative large language model by using a hybrid compression method. |
| Outcome: | The proposed method outperforms the state-of-the-art in long-context evaluations. |
Faster Speculative Decoding via Effective Draft Decoder with Pruned Candidate Tree (2025.acl-long)
Copied to clipboard
| Challenge: | Effective Draft Decoder (EDD) is a powerful decoding method that generates more accurate draft tokens by leveraging the encoding results as soft prompts. |
| Approach: | They propose an effective draft decoder which treats the LLM as a powerful encoder and generates more accurate draft tokens by leveraging the encoding results as soft prompts. |
| Outcome: | The proposed method significantly improves the performance of large language models and reduces inference latency. |
Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing detectors use classifier-style probability signals or rely on rewriting, which can degrade quality and introduce new triggers. |
| Approach: | They propose to efficiently remove poisoned examples before or during fine-tuning . |
| Outcome: | The proposed method outperforms prior detectors on two machine translation datasets and one QA dataset. |
Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (2023.acl-long)
Copied to clipboard
Haoli Bai, Zhiguang Liu, Xiaojun Meng, Li Wentao, Shuang Liu, Yifeng Luo, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, Xin Jiang, Qun Liu
| Challenge: | Existing solutions for visual document understanding lack granularity of document textlines. |
| Approach: | They propose a supervised pre-training program to leverage structural knowledge nested in document textlines to achieve fine-grained alignment between visual regions and texts. |
| Outcome: | The proposed system performs better on various VDU tasks in English and Chinese. |
From Conversation to Evaluation: Benchmarking LLMs on Development Knowledge via SimpleDevQA (2026.findings-acl)
Copied to clipboard
Jing Zhang, Lianghong Guo, Yanlin Wang, Terry Yue Zhuo, Yong Wang, Mingwei Liu, Jiachi Chen, Ensheng Shi, Yuchi Ma, Hongyu Zhang, Zibin Zheng
| Challenge: | Existing Dev Knowledge QA benchmarks are limited in development knowledge scope and often not built from real user queries. |
| Approach: | They conduct preliminary analysis of real user–LLM dialogues from WildChat to investigate the importance of Dev Knowledge QA in AI-assisted software development scenarios. |
| Outcome: | The proposed benchmark is based on real user–LLM dialogues from WildChat. |
RareSyn: Health Record Synthesis for Rare Disease Diagnosis (2025.emnlp-main)
Copied to clipboard
| Challenge: | RareSyn is a data synthesis approach to augment and de-identify EHRs with a focus on rare diseases. |
| Approach: | They propose a data synthesis approach to augment and de-identify EHRs with a focus on rare diseases. |
| Outcome: | The proposed model augments and de-identifies EHRs with a focus on rare diseases. |
Morpheme Sense Disambiguation: A New Task Aiming for Understanding the Language at Character Level (2024.lrec-main)
Copied to clipboard
| Challenge: | Morphemes are a strong linguistic feature to capture lexical semantics, but lack of morpheme-informed resources and the expense of manual annotations hinder morphme-enhanced methods. |
| Approach: | They propose a task of Morpheme Sense Disambiguation with two subtasks in-text and in-word to generalize morpheme features on more tasks. |
| Outcome: | The proposed tasks are based on two morpheme-annotated datasets for Chinese . the best model yields a promising precision of 77.66% on in-text and 88.19% on in word . |
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition (2025.coling-main)
Copied to clipboard
Yuming Yang, Wantong Zhao, Caishuang Huang, Junjie Ye, Xiao Wang, Huiyuan Zheng, Yang Nan, Yuran Wang, Xueying Xu, Kaixin Huang, Yunke Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current Large Language Models struggle with complex entity taxonomies in open domains and lack NER capabilities. |
| Approach: | They propose a dataset to guide LLMs' generalization in Open NER under a universal entity taxonomy. |
| Outcome: | The proposed model outperforms GPT-4 in 3 out-of-domain benchmarks across 15 datasets and 6 languages. |
DRK: Discriminative Rule-based Knowledge for Relieving Prediction Confusions in Few-shot Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to identify relation type in low-resource scenario fall into prediction confusions owing to the limited inference ability over shallow text features. |
| Approach: | They propose a discriminative rule-based knowledge method to identify the relation type between entities in a given text in the low-resource scenario. |
| Outcome: | The proposed method improves on four types of meta tasks with a 6.0% accuracy gain on average. |
CMHKF: Cross-Modality Heterogeneous Knowledge Fusion for Weakly Supervised Video Anomaly Detection (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods focus mainly on visual modalities, neglecting rich multi-modality information. |
| Approach: | They propose a framework that integrates cross-modality knowledge from video, audio and text to improve anomaly detection and localization. |
| Outcome: | The proposed framework improves detection and localization of anomalies using video-level labels. |
Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction (2025.findings-naacl)
Copied to clipboard
ShengbinYue ShengbinYue, Ting Huang, Zheng Jia, Siyuan Wang, Shujun Liu, Yun Song, Xuanjing Huang, Zhongyu Wei
| Challenge: | Large Language Models (LLMs) have advanced legal intelligence, but the scarcity of scenario data impedes the progress toward interactive legal scenarios. |
| Approach: | They propose a Multi-agent Legal Simulation Driver to generate synthetic data by simulating interactive legal scenarios. |
| Outcome: | The proposed framework ensures consistency of legal attributes between participants and introduces a supervisory mechanism to align participants’ characters and behaviors as well as addressing distractions. |
VersaTune: An Efficient Data Composition Framework for Training Multi-Capability LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing work focuses on domain-specific enhancements during fine-tuning, the challenge of which lies in catastrophic forgetting of knowledge across other domains. |
| Approach: | They propose a data composition framework that allows LLMs to enhance their multi-domain capabilities during supervised fine-tuning. |
| Outcome: | The proposed framework improves multi-domain fostering performance by 29.77% compared to uniform weights. |
Improving Consistency for Text Summarization with Energy Functions (2023.findings-emnlp)
Copied to clipboard
Qi Zeng, Qingyu Yin, Zheng Li, Yifan Gao, Sreyashi Nag, Zhengyang Wang, Bing Yin, Heng Ji, Chao Zhang
| Challenge: | Current abstractive summarization models generate inconsistent content due to the inherently noisy dataset and the discrepancy between maximum likelihood estimation based training objectives and consistency measurements. |
| Approach: | They propose a new consistency taxonomy that categorizes inconsistent content into faithfulness, factuality, and self-supportiveness. |
| Outcome: | Experiments on XSUM and CNN/DM datasets show that EnergySum mitigates the trade-off between accuracy and consistency. |
Reinforcement Learning on Pre-Training Data (2026.acl-long)
Copied to clipboard
Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang
| Challenge: | Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings. |
| Approach: | They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data. |
| Outcome: | Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base. |
How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that strategically infusing domain knowledge during pretraining can substantially improve downstream performance. |
| Approach: | They propose a knowledge infusion scaling law that predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts. |
| Outcome: | The proposed model predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts. |
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models (2025.acl-long)
Copied to clipboard
Zihan Qiu, Zeyu Huang, Bo Zheng, Kaiyue Wen, Zekun Wang, Rui Men, Ivan Titov, Dayiheng Liu, Jingren Zhou, Junyang Lin
| Challenge: | Existing Mixture-of-Experts training frameworks use a micro-batch to calculate LBL . micro-batches are restricted to a single sequence, preventing expert specialization . |
| Approach: | They propose to use a global-batch to loosen the load balance constraint for MoEs models . they propose to synchronize fi across micro-batches and then use it to calculate the LBL . |
| Outcome: | The proposed global-batch LBL improves the domain specialization of experts . the micro-battery LBL is almost at the sequence level, and the router is pushed to distribute the token evenly . |
Marrying Up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding (P18-1)
Copied to clipboard
| Challenge: | Experimental results show that the combination of regular expressions and NNs improves learning effectiveness when a small number of training examples are available. |
| Approach: | They propose to combine a neural network (NN) with regular expressions (RE) to improve supervised learning for NLP by exploiting the rich expressiveness of REs at different levels within a NN. |
| Outcome: | The proposed approach significantly improves learning effectiveness when a small number of training examples are available. |
Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing research on building ES conversation systems only considered single-turn interactions with users, which is over-simplified and has limited support for multi-turn systems. |
| Approach: | They propose a multi-turn ES conversation system that uses lookahead heuristics to estimate future user feedback after using particular strategies. |
| Outcome: | The proposed system significantly outperforms baselines in both dialogue generation and strategy planning. |
Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | a recent study shows that humans are not supervised by the natural language inference . |
| Approach: | They propose to solve the natural language inference problem via task-agnostic multimodal pretraining. |
| Outcome: | The proposed network outperforms fully-supervised BiLSTM and BiLS+ELMO on plain text inference datasets. |
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale (2025.acl-long)
Copied to clipboard
Jiawei Guo, Tianyu Zheng, Yizhi Li, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Graham Neubig, Wenhu Chen, Xiang Yue
| Challenge: | Current instruction-tuning datasets focus on simplistic visual question answering tasks, and provide phrase-level answers without any intermediate rationales. |
| Approach: | They propose to use open-source multimodal large language models to train MLLMs on a dataset with 12M instruction-response pairs to elicit CoT reasoning. |
| Outcome: | The proposed model achieves state-of-the-art performance on benchmarks such as MathVerse, MMMU-Pro, and MuirBench, and gains improvements of up to 4% on non-reasoning-based benchmarks. |
OVEL: Online Video Entity Linking (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on Multi-modal Entity Linking focus on linking textual and visual mentions or offline videos’ mentions to entities in multi-modal knowledge bases. |
| Approach: | They propose a task called Online Video Entity Linking to establish connections between online videos and a knowledge base with high accuracy and timeliness. |
| Outcome: | The proposed method can establish connections between mentions in online videos and a knowledge base with high accuracy and timeliness. |
Document-Level Event Extraction via Information Interaction Based on Event Relation and Argument Correlation (2024.lrec-main)
Copied to clipboard
| Challenge: | Document-level Event Extraction (DEE) is a vital task in NLP . current approaches overlook intricate relationships among events and subtle correlations among arguments within a document . |
| Approach: | They propose a document-level event extraction tool that integrates event relationships and argument correlation graphs to model the relationship among events. |
| Outcome: | The proposed network outperforms existing models and large language models in terms of F1-score across two benchmark datasets. |
Answer-driven Deep Question Generation based on Reinforcement Learning (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for deep question generation focus on enhancing document representations, but little attention is paid to the answer information. |
| Approach: | They propose a deep question generation model that makes better use of the target answer as a guidance to facilitate question generation. |
| Outcome: | The proposed model outperforms state-of-the-art models in automatic and human evaluations on the hotpotQA dataset. |
Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies on dense video captioning and video story generation have made some progress, but in practical applications, we typically require synchronized narrations for ongoing visual scenes. |
| Approach: | They propose a task of Synchronized Video Storytelling to generate synchronized narrations for videos using a benchmark dataset with rich annotations. |
| Outcome: | The proposed framework can generate narrations with the guidance of the generated or predefined storyline and human evaluations validate the effectiveness. |
DeepGeneMD: A Joint Deep Learning Model for Extracting Gene Mutation-Disease Knowledge from PubMed Literature (D19-57)
Copied to clipboard
| Challenge: | Identifying and understanding the pathogenesis of genetic diseases is an essential task. |
| Approach: | They propose a joint deep learning model for gene mutation-disease knowledge extraction that adapts the state-of-the-art hierarchical multi-task learning framework for joint inference on named entity recognition and relation extraction. |
| Outcome: | The proposed model achieves the average score of 0.45 on recognizing gene activities and disease entities and the average F1 score of 0.3 on extracting relations, ranking 1st in the AGAC RE task. |
Assessing the Efficacy of Grammar Error Correction: A Human Evaluation Approach in the Japanese Context (2024.lrec-main)
Copied to clipboard
| Challenge: | Using an automatic annotation toolkit, we evaluated the performance of the sequence tagging grammar error detection and correction model (SeqTagger) using Japanese university students’ writing samples. |
| Approach: | They evaluated the performance of the state-of-the-art sequence tagging grammar error detection and correction model using Japanese university students’ writing samples. |
| Outcome: | The proposed model shows a high precision but conservativeness in error detection and correction. |
Unveiling Fake News with Adversarial Arguments Generated by Multimodal Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for detecting fake news rely on neural networks to learn latent feature representations with limited real-world understanding. |
| Approach: | They propose a method that leverages Multimodal Large Language Models for fake news detection that introduces adversarial reasoning through debates from opposing perspectives. |
| Outcome: | The proposed method significantly outperforms state-of-the-art methods on four fake news detection datasets. |
Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for manipulation detection and grounding focus on manipulator type classification under result-oriented supervision. |
| Approach: | They propose a reasoning-driven framework that shifts learning from outcome fitting to process modeling. |
| Outcome: | The proposed framework achieves state-of-the-art with superior generalization on large-scale datasets. |
KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education? (2025.acl-short)
Copied to clipboard
| Challenge: | Existing knowledge discrepancies between textbooks and large language models can undermine RAG systems' performance. |
| Approach: | They propose to use a dataset to test RAG system robustness against knowledge discrepancies. |
| Outcome: | The proposed dataset shows that RAG systems suffer performance degradation when faced with knowledge discrepancies. |
Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for legal intelligence are limited to static evaluation paradigms or simplified scenarios. |
| Approach: | They introduce J1-ENVS, the first interactive and dynamic legal environment tailored for LLM-based agents. |
| Outcome: | The proposed framework assesses task performance and procedural compliance across legal proficiency levels. |
RMLM: A Flexible Defense Framework for Proactively Mitigating Word-level Adversarial Attacks (2023.acl-long)
Copied to clipboard
| Challenge: | Existing defenses focus on improving robustness of the victim model in training, but neglect to mitigate adversarial attacks during inference. |
| Approach: | They propose a framework that confuses attackers and corrects adversarial contexts . their framework helps improve the robustness of the victim model during inference . |
| Outcome: | The proposed framework improves the robustness of the victim model in training . it also corrects abnormal contexts in the representation level and filtering out examples . |
Towards Unifying Multi-Lingual and Cross-Lingual Summarization (2023.acl-long)
Copied to clipboard
| Challenge: | Existing work on multilingual summarization and cross-lingual summmarization has been limited due to their different definitions. |
| Approach: | They propose to unify MLS and CLS into a more general setting, i.e. many-to-many summarization. |
| Outcome: | The proposed model outperforms the state-of-the-art models in the zero-shot directions. |
FineRAG: Fine-grained Retrieval-Augmented Text-to-Image Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in text-to-image generation still exhibit limitations in terms of knowledge access. |
| Approach: | They propose a fine-grained retrieval-augmented image generation model that breaks down the retrieval task into four critical stages: query decomposition, candidate selection, retrieval augmented diffusion, and self-reflection. |
| Outcome: | The proposed method significantly reduces noise associated with retrieval-augmented image generation and performs better in complex, open-world scenarios. |
Rethinking Token Reduction for State Space Models (2024.emnlp-main)
Copied to clipboard
Zheng Zhan, Yushu Wu, Zhenglun Kong, Changdi Yang, Yifan Gong, Xuan Shen, Xue Lin, Pu Zhao, Yanzhi Wang
| Challenge: | Existing methods for token reduction for SSMs lead to performance drops . a recent study shows that Mamba-2 improves the accuracy of the model by 5.7% to 13.1% . |
| Approach: | They propose a token reduction method that integrates token importance and similarity into SSMs and takes advantage of pruning and merging. |
| Outcome: | The proposed method improves accuracy by 5.7% to 13.1% on six benchmarks with Mamba-2 compared to existing methods while reducing computational demands and memory requirements. |
LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models often require significant computational resources, often constraining input word or code token lengths. |
| Approach: | They propose to use the encoder-decoder attention scores to represent the importance of a code token across multiple contexts to reduce training and prediction time. |
| Outcome: | The proposed approach outperforms the SOTAs DietCode and SlimCode in code search and summarization tasks. |
Exploiting Abstract Meaning Representation for Open-Domain Question Answering (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work attempts to address these challenges using Pretrained Language Models (PLMs) but the diversity of surface form expressions can hinder the model’s ability to capture accurate correlations, especially when the context is lengthy and complex. |
| Approach: | They propose a method known as Graph-as-Token (GST) to incorporate AMRs into PLMs to assist the model in understanding complex semantic information. |
| Outcome: | The proposed method outperforms existing methods and significantly improves performance on both Natural Questions and TriviaQA. |
A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party Conversations (2023.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown the importance of visual information in multi-party conversations due to the complexity of visual scenes. |
| Approach: | They propose a framework to extract face sequences as visual features from a real speaker's utterance and a pipeline method to extract the face sequence. |
| Outcome: | The proposed framework extracts face sequences of the real speaker of each utterance and improves emotion prediction on the MELD dataset. |
Is the Attention Matrix Really the Key to Self-Attention in Multivariate Long-Term Time Series Forecasting? (2026.acl-long)
Copied to clipboard
| Challenge: | In multivariate long-term time series forecasting, it is widely believed that the effectiveness of self-attention arises from its attention matrix. |
| Approach: | They propose a multi-branch MLP that isolates the ‘multi-brain mapping with element-wise operation’ structure from the Transformer and shows that it achieves competitive performance. |
| Outcome: | The proposed model outperforms three classic and three latest Transformer models and shows that it achieves competitive performance. |
Towards One-to-Many Visual Question Answering (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing Visual Question Answering systems are constrained to support domain-specific questions . a model trained on a single specific domain may not be competent for real-world application. |
| Approach: | They propose a task to enable a single model to answer as many different domains of questions as possible . they break the task down into the integration of three key abilities . |
| Outcome: | The proposed model can answer as many domains of questions as possible, the authors argue . the proposed model generalizes well to three extra zero-shot datasets, and the results are published. |
Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback (2024.findings-acl)
Copied to clipboard
Zhangqian Bi, Yao Wan, Zheng Wang, Hongyu Zhang, Batu Guan, Fangxin Lu, Zili Zhang, Yulei Sui, Hai Jin, Xuanhua Shi
| Challenge: | Large Language Models (LLMs) generate code for given contexts, such as incomplete code, class, data structure, or project-specific information. |
| Approach: | They propose a compiler feedback-based code generation approach that leverages static analysis to identify mismatches between the generated code and the project's context. |
| Outcome: | The proposed model outperforms retrieval-based code generation baselines and significantly outperfies the existing large language models. |
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)
Copied to clipboard
Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang
| Challenge: | Current outcome-centric verification paradigms neglect potential errors in the derivation process. |
| Approach: | They propose a process-aware RLVR training paradigm utilizing verifiers selected via **PRIME**. |
| Outcome: | The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models. |
Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
Peiru Yang, Haoran Zheng, Tong Ju, Shiting Wang, Wanchun Ni, Jiajun Liu, Shangguang Wang, Yongfeng Huang, Tao Qi
| Challenge: | Existing studies have investigated knowledge poisoning attacks in medical RAG systems . knowledge poison attacks can disrupt model outputs and undermine system reliability . |
| Approach: | They propose a knowledge poisoning framework that injects misinformation into textual data . they propose to use paired visual data as a query-agnostic trigger to promote retrieval . |
| Outcome: | The proposed framework produces clinically plausible but incorrect generations on five LLMs and datasets. |
V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models (2026.findings-acl)
Copied to clipboard
Xiangxi Zheng, Linjie Li, Zhengyuan Yang, Ping Yu, Alex Jinpeng Wang, Rui Yan, Yuan Yao, Lijuan Wang
| Challenge: | Existing static image-text benchmarks are insufficient for evaluating multimodal large language models’ dynamic perception and interactive reasoning abilities. |
| Approach: | They propose a game-based evaluation framework to assess multimodal large language models’ visual reasoning in dynamic, continuous-space environments. |
| Outcome: | The proposed framework systematically assesses MLLMs’ visual reasoning in dynamic, continuous-space environments. |
Eureka: Neural Insight Learning for Knowledge Graph Reasoning (2022.coling-1)
Copied to clipboard
| Challenge: | Existing knowledge embedding methods have limited performance on knowledge graph reasoning tasks . eureka is empowered to learn seen relations with sufficient training triples . |
| Approach: | They propose a neural insight learning framework called Eureka to bridge the “seen” to “unsea” gap . Eureca is empowered to learn seen relations with sufficient training triples while providing flexibility to learn unseen relations given only one trigger . |
| Outcome: | The proposed framework outperforms state-of-the-art models on seen and unseen relations . it can learn seen and unseen relationships with sufficient training triples . |
Introducing Compiler Semantics into Large Language Models as Programming Language Translators: A Case Study of C to x86 Assembly (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can be used to translate high-level programming languages to machine instructions. |
| Approach: | They propose two methods to solve a problem known as neural compilation by using a 13B model with a behavioral accuracy of over 91%. |
| Outcome: | The proposed approach outperforms the larger model by over 50% and achieves a behavioral accuracy of over 91% while outperforming the GPT-4 Turbo model. |
Diffusion Language Model Inference with Monte Carlo Tree Search (2026.findings-eacl)
Copied to clipboard
Zheng Huang, Kiran Ramnath, Yueyan Chen, Aosong Feng, Sangmin Woo, Balasubramaniam Srinivasan, Zhichao Xu, Kang Zhou, Shuai Wang, Haibo Ding, Lin Lee Cheong
| Challenge: | Existing methods for inference use heuristics to determine which positions to unmask and which tokens to commit . MEDAL is an inference-time scaling framework that integrates Monte Carlo Tree SEarch initialization for Diffusion Language Model inference. |
| Approach: | They propose a framework that integrates Monte Carlo Tree SEarch initialization for Diffusion Language Model inference. |
| Outcome: | The proposed framework achieves 22.0% improvement over existing inference strategies across multiple benchmarks. |
Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Models (2026.findings-acl)
Copied to clipboard
Bang Zhang, Ruotian Ma, Qingxuan Jiang, Peisong Wang, Jiaqi Chen, Zheng Xie, Xingyu Chen, Yue Wang, Fanghua Ye, Jian Li, Yifan Yang, Zhaopeng Tu, Xiaolong Li
| Challenge: | Large language models (LLMs) have evolved from statistical sequence predictors to sophisticated autonomous agents capable of reasoning, planning, and sustaining multi-turn conversa-tions. |
| Approach: | They propose a system that instantiates a "Sentient Agent" that simulates human-like emotional changes and inner thoughts to provide a more realistic evaluation of the model in multi-turn conversations. |
| Outcome: | The proposed framework measures the agent's higher-order social cognition in multi-turn conversations. |
Multimodal Dialogue Response Generation (2022.acl-long)
Copied to clipboard
Qingfeng Sun, Yujing Wang, Can Xu, Kai Zheng, Yaming Yang, Huang Hu, Fei Xu, Jessica Zhang, Xiubo Geng, Daxin Jiang
| Challenge: | Existing studies focus on multimodal dialogue models but neglect generation methods. |
| Approach: | They propose a multimodal dialogue response generation task which requires multimodal dialogs containing both texts and images which are difficult to obtain. |
| Outcome: | Experiments show that the proposed model can generate informative text and high-resolution image responses. |
Neural Related Work Summarization with a Joint Context-driven Attention Mechanism (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to automatic related work summarization rely on human-engineered features. |
| Approach: | They propose a neural data-driven attention mechanism to measure contextual relevance within full texts and a heterogeneous bibliography graph simultaneously. |
| Outcome: | The proposed approach achieves significant improvement over a typical seq2seq summarization baseline and five classical summarizing baselines. |
Black-Box Prompt Optimization: Aligning Large Language Models without Model Training (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models are often not well aligned with human intents, which requires additional training. |
| Approach: | They propose to use Black-Box Prompt Optimization (BPO) to perform alignments on large language models that are not well aligned with human intents. |
| Outcome: | The proposed model outperforms existing models and is model-agnostic. |
HyCoRec: Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to study the Matthew effect in Recommender Systems (RSs) however, it is amplified when the user interacts with the system over time. |
| Approach: | They propose a paradigm to alleviate the Matthew effect in conversational recommendation by learning multi-aspect preferences. |
| Outcome: | The proposed paradigm achieves state-of-the-art performance and superior of alleviating Matthew effect in conversational recommendation tasks. |
Punctuation-Steered Representation Fine-Tuning (2026.acl-short)
Copied to clipboard
| Challenge: | Existing methods for parameter-efficient fine-tuning (PeFT) are limited due to their prohibitive size and computational demands. |
| Approach: | They propose a method that fine-tunes punctuation representations to achieve performance improvements. |
| Outcome: | The proposed method improves performance by altering the representation space alone . but it results in suboptimal performance due to the effects of the method on the output . |
Varying Sentence Representations via Condition-Specified Routers (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing sentences cannot account for different aspects of semantic similarity between two sentences. |
| Approach: | They propose a transformer-style framework that generates conditioned sentences . they propose 'conditional' STS, which measures similarity between two sentences based on condition sentences - a task that requires a sentence embedding model capable of generating distinct representations for the same sentence under different conditions. |
| Outcome: | The proposed framework is superior to existing models on two condition sentences . it can generate conditioned sentences while maintaining model parameters and computational efficiency . |
LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning (2025.emnlp-main)
Copied to clipboard
Tianshi Zheng, Cheng Jiayang, Chunyang Li, Haochen Shi, Zihao Wang, Jiaxin Bai, Yangqiu Song, Ginny Wong, Simon See
| Challenge: | Modern large language models (LLMs) employ diverse logical inference mechanisms for reasoning. |
| Approach: | They analyze the comparative dynamics of inductive (System 1) versus abductive/deductive (system 2) inference in large language models by using a controlled analogical reasoning environment and a MCQ/free-text task format. |
| Outcome: | The proposed methods can significantly scale LLM reasoning. |
Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to translate sentences to other languages using heuristics are challenging. |
| Approach: | They propose a model that learns hierarchical weights for different sets of labels and applies them to other languages to translate them. |
| Outcome: | The proposed model can translate English datasets to other languages and obtain different sets of labels again using heuristics. |
CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing empathetic dialogue models only consider the affective aspect of empathy, which limits the capability of emotional response generation. |
| Approach: | They propose a model that aligns the user's cognition and affection at both the coarse-grained and fine-grounded levels and then automatically and manually evaluates the model. |
| Outcome: | The proposed model outperforms state-of-the-art models and generates more empathetic and informative responses. |
Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing systems for conversational recommender systems (CRS) have strong results in movies, but games present distinct challenges . MATCHA framework provides specialized agents for intent parsing, tool-augmented retrieval, multi-LLM ranking, and stronger safety. |
| Approach: | They propose a framework for conversational recommender systems that assigns specialized agents for intent parsing, tool-augmented retrieval, multi-LLM ranking and risk control. |
| Outcome: | MATCHA outperforms baselines on real user request dataset, improves Hit@5 by 20%, reduces popularity bias by 24%, and achieves 97.9% adversarial defense. |
OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation (2025.acl-long)
Copied to clipboard
Qinglin Zhang, Luyao Cheng, Chong Deng, Qian Chen, Wen Wang, Siqi Zheng, Jiaqing Liu, Hai Yu, Chao-Hong Tan, Zhihao Du, ShiLiang Zhang
| Challenge: | Full-duplex spoken dialogue systems allow simultaneous bidirectional communication . low latency and natural interactions in full-duplice systems remains a challenge . |
| Approach: | They propose a multi-stage post-training scheme that adapts a text large language model into a speech-text dialogue LLM. |
| Outcome: | The proposed model can model human conversation behaviors with low latency and natural interactions with low delay. |
InferenceDynamics: Adaptive LLM Routing through Structured Capability and Knowledge Profiling (2026.acl-long)
Copied to clipboard
Haochen Shi, Tianshi Zheng, Weiqi Wang, Baixuan Xu, Chunyang Li, Chunkit Chan, Tao Fan, Yangqiu Song
| Challenge: | Large Language Model (LLM) routing is a pivotal technique for navigating a diverse landscape of LLMs. |
| Approach: | They propose a flexible and scalable multi-dimensional routing framework that models the capability and knowledge of models. |
| Outcome: | The proposed framework can be used to generalize and identify top-performing models for group-level routing using modern benchmarks including MMLU-Pro, GPQA, BigGenBench, and LiveBench. |
The Linguistic Connectivities Within Large Language Models (2025.findings-acl)
Copied to clipboard
Dan Wang, Boxi Cao, Ning Bian, Xuanang Chen, Yaojie Lu, Hongyu Lin, Jia Zheng, Le Sun, Shanshan Jiang, Bin Dong, Xianpei Han
| Challenge: | Recent studies have discovered notable disparities in their performance across different languages. |
| Approach: | They conduct a systematic investigation into the behaviors of large language models across 27 different languages on 3 different scenarios and reveals a Linguistic Map correlates with the richness of available resources and linguistic family relations. |
| Outcome: | The proposed model demonstrates that there are significant disparities in performance across languages across 27 different languages on 3 different scenarios. |
Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to condensing textual information into concise and structured tables are limited in their applicability in broader contexts. |
| Approach: | They propose a benchmark dataset for generating summary tables of competitions based on real-time commentary texts that incorporates large-scale textual information into concise and structured tables. |
| Outcome: | The proposed method exhibits strong generalization abilities, surpassing previous approaches on several other text-to-table datasets. |
Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Model (LLM)-based agents extend the utility of LLMs by interacting with dynamic environments. |
| Approach: | They propose a parameter fusion framework based on directional consensus evaluation that disentangles knowledge updates through a two-stage process. |
| Outcome: | The proposed framework disentangles knowledge updates through a two-stage process with minimal computational overhead and parameter updates. |
AHVE-CNER: Aligned Hanzi Visual Encoding Enhance Chinese Named Entity Recognition with Multi-Information (2025.coling-main)
Copied to clipboard
| Challenge: | Existing glyph-based models neglect the relationship between pictorial elements and radicals for Named Entity Recognition (NER) tasks. |
| Approach: | They propose a model that integrates multi-source visual and phonetic information of Hanzi . they propose combining pictographic features with radicals to facilitate integration . |
| Outcome: | The proposed model improves performance on benchmark datasets. |
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding (2026.findings-acl)
Copied to clipboard
Songcheng Cai, Zhiheng Lyu, Yuansheng Ni, Xiangchao Chen, Baichuan Zhou, Shenzhe Zhu, Yi Lu, Haozhe Wang, Chi Ruan, Benjamin Schneider, Weixu Zhang, Xiang Li, Andy Zheng, Yuyu Zhang, Ping Nie, Wenhu Chen
| Challenge: | Existing benchmarks for agentic repository-level code understanding overlook long tail topics and rely on memorized knowledge. |
| Approach: | They propose a repository-level agentic code understanding benchmark that uses long-tail repositories with executable environments to enforce topical balance. |
| Outcome: | Empirically, a Qwen3-8B model trained with the proposed benchmark outperforms GPT-4o by 2.3 points. |
DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis (2026.acl-long)
Copied to clipboard
Lung-Hao Lee, Liang-Chih Yu, Natalia V Loukachevitch, Ilseyar Alimova, Alexander Panchenko, Tzu-Mi Lin, Zhe-Yu Xu, Jian-Yu Zhou, Guangmin Zheng, Jin Wang, Sharanya Awasthi, Jonas Becker, Jan Philip Wahle, Terry Ruas, Shamsuddeen Hassan Muhammad, Saif M. Mohammad
| Challenge: | Existing ABSA research relies on coarse-grained categorical labels, which limits its ability to capture nuanced affective states. |
| Approach: | They propose a dimensional approach that represents sentiment with continuous valence–arousal (VA) scores, enabling fine-grained analysis at both the aspect and sentiment levels. |
| Outcome: | The proposed approach represents sentiment with continuous valence–arousal (VA) scores, enabling fine-grained analysis at both the aspect and sentiment levels. |
Maximum Entropy Loss, the Silver Bullet Targeting Backdoor Attacks in Pre-trained Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing backdoor defense paradigms focus on detecting and removing poisoned samples at pre-training or inference time. |
| Approach: | They propose a new approach where the backdoor attack is directly reversed by incorporating maximum entropy loss into training to neutralize the minimal cross-entropiness loss fine-tuning on poisoned data. |
| Outcome: | The proposed model significantly lowers the attack success rate on classification tasks and reduces the risk of backdoor attacks on clean data. |
SSEGCN: Syntactic and Semantic Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis (2022.naacl-main)
Copied to clipboard
| Challenge: | Aspect-based Sentiment Analysis (ABSA) aims to predict sentiment polarity towards aspects in sentences . a novel model for ABSA is proposed, but how to harness it is still a challenge . |
| Approach: | They propose a syntactic and semantic enhanced Graph Convolutional Network (SSEGCN) model for ABSA task using aspect-aware attention mechanism and self-attention. |
| Outcome: | The proposed model outperforms state-of-the-art methods on benchmark datasets. |
Paraphrase Makes Perfect: Leveraging Expression Paraphrase to Improve Implicit Sentiment Learning (2025.coling-main)
Copied to clipboard
| Challenge: | Existing implicit sentiment learning methods focus on capturing implicit sentiment knowledge individually, without considering the potential connection between implicit and explicit sentiment. |
| Approach: | They propose an expression paraphrase strategy and a sentiment-consistent contrastive learning mechanism to learn the connections between implicit and explicit sentiment expressions and integrate them into the model. |
| Outcome: | The proposed method is effective on implicit sentiment analysis on public datasets. |
Finding Influential Instances for Distantly Supervised Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Distant supervision models suffer from high label noise and are not reliable for DS. |
| Approach: | They propose a model-agnostic instance sampling method for relation extraction (RE) by influence function, namely REIF. |
| Outcome: | The proposed method reduces the computational complexity from O(mn) to O(1), with analyzing its robustness on the selected sampling function. |
Training-free LLM Merging for Multi-task Learning (2025.acl-long)
Copied to clipboard
Zichuan Fu, Xian Wu, Yejing Wang, Wanyu Wang, Shanshan Ye, Hongzhi Yin, Yi Chang, Yefeng Zheng, Xiangyu Zhao
| Challenge: | Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing tasks. |
| Approach: | They propose a training-free method for unifying different specialized LLMs into a single model using model-wise and layer-wise pruning and scaling. |
| Outcome: | The proposed method outperforms existing merging techniques and surpasses models fine-tuned on combined datasets in most scenarios. |
Beyond the Score: Uncertainty-Calibrated LLMs for Automated Essay Assessment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Automated Essay Scoring (AES) systems attain near–human agreement on some public benchmarks, but real-world adoption is limited. |
| Approach: | They propose a distribution-free wrapper that equips any classifier with set-valued outputs enjoying formal coverage guarantees. |
| Outcome: | The proposed model achieves coverage targets while keeping prediction sets compact. |
PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents (2026.eacl-industry)
Copied to clipboard
Minjia Wang, Yunfeng Wang, Xiao Ma, Dexin Lv, Qifan Guo, Lynn Zheng, Benliang Wang, Lei Wang, Jiannan Li, Yongwei Xing, Junzhe Xu, Zheng Sun
| Challenge: | Publicly available corpora cover only slivers of human activity, such as email threads, chat logs, purchase histories, sensor traces, and provide large-scale supervision for data-hungry machine-learning pipelines. |
| Approach: | They propose a method for synthesizing realistic digital footprints using large language model agents from a structured user profile. |
| Outcome: | The proposed method generates diverse sequences of user events, producing corresponding digital artifacts such as emails, messages, calendar entries, reminders, etc. |
Generating Deep Questions with Commonsense Reasoning Ability from the Text by Disentangled Adversarial Inference (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for commonsense question generation produce shallow questions that can be answered by simple word matching. |
| Approach: | They propose a task of commonsense question generation that aims to yield deep-level questions from the text. |
| Outcome: | The proposed model can yield deep-level and to-the-point questions from the text. |
Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective (2025.findings-acl)
Copied to clipboard
Yipeng Kang, Junqi Wang, Yexin Li, Mengmeng Wang, Wenming Tu, Quansen Wang, Hengli Li, Tingjun Wu, Xue Feng, Fangwei Zhong, Zilong Zheng
| Challenge: | Current approaches to value alignment focus on a few core values, such as helpfulness, harmlessness, and honesty. |
| Approach: | They propose to use latent causal value graphs to guide two lightweight value-steering methods . role-based prompting and sparse autoencoder (SAE) steering are also used . |
| Outcome: | Experiments on Gemma-2B-IT and Llama3-8B- IT show that the proposed methods are effective and controllable. |
Controlling Styles in Neural Machine Translation with Activation Prompt (2023.findings-acl)
Copied to clipboard
| Challenge: | Earlier studies on controlling styles in neural machine translation (NMT) have focused on regulating the level of formality, but they still encounter two major challenges. |
| Approach: | They propose a method to control the style of neural machine translation by retrieving prompts from stylized monolingual corpus. |
| Outcome: | The proposed method can control the style of translation and achieve remarkable performance. |
Enhancing Transformers for Generalizable First-Order Logical Entailment (2025.acl-long)
Copied to clipboard
Tianshi Zheng, Jiazheng Wang, Zihao Wang, Jiaxin Bai, Hang Yin, Zheye Deng, Yangqiu Song, Jianxin Li
| Challenge: | Moreover, transformers have demonstrated proficiency in logical reasoning over natural language. |
| Approach: | They propose a logic-aware architecture that improves the performance in generalizable first-order logical entailment by combining distribution shifts and unseen knowledge. |
| Outcome: | The proposed architecture outperforms methods designed specifically for knowledge graph query answering on a dataset with a large dataset. |
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models (2025.findings-acl)
Copied to clipboard
Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Wan Guanglu, Xunliang Cai, Zhi Zheng, Tong Xu
| Challenge: | Existing multi-objective preference alignment methods for large language models face limitations such as auxiliary reward/reference models and computational complexity. |
| Approach: | They propose a framework that achieves dynamic balance across preference dimensions by using dimension-aware generation metrics as implicit rewards. |
| Outcome: | Empirical results show that AMoPO outperforms state-of-the-art methods by 28.5% . |
Summarize before Aggregate: A Global-to-local Heterogeneous Graph Inference Network for Conversational Emotion Recognition (2020.coling-main)
Copied to clipboard
| Challenge: | Existing studies focus on modeling emotion influences with utterance-level features, with little attention paid on phrase-level semantic connection between utterrances. |
| Approach: | They propose a two-stage Summarization and Aggregation Graph Inference Network which integrates inference for topic-related emotional phrases and local dependency reasoning over neighbouring utterances in a global-to-local fashion. |
| Outcome: | The proposed model outperforms the state-of-the-art models on three CER benchmark datasets. |
2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision (2025.findings-naacl)
Copied to clipboard
Shilong Li, Yancheng He, Hui Huang, Xingyuan Bu, Jiaheng Liu, Hangyu Guo, Weixun Wang, Jihao Gu, Wenbo Su, Bo Zheng
| Challenge: | Existing methods that optimize for scalar scores or ranking reward ignore multi-dimensional nature of human preferences. |
| Approach: | They propose to extend the preference of Direct Preference Optimization to two dimensions: segments and aspects. |
| Outcome: | The proposed framework decomposes the overall objective into multi-segment and multi-aspect objectives. |
Fine-grained Interest Matching for Neural News Recommendation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies represent each user as a single vector and then match the candidate news vector, which may lose fine-grained information for recommendation. |
| Approach: | They propose a Fine-grained interest matching method for neural news recommendation based on multi-level representations and fine-grain matching between segment pairs of each browsed news and the candidate news at each semantic level. |
| Outcome: | The proposed model can capture more fine-grained interest matching signals by performing interactions between each pair of news at multi-level semantic granularities. |
ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)
Copied to clipboard
Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo
| Challenge: | Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task. |
| Approach: | They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5. |
| Outcome: | The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers. |
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark (2025.acl-long)
Copied to clipboard
Xiang Yue, Tianyu Zheng, Yuansheng Ni, Yubo Wang, Kai Zhang, Shengbang Tong, Yuxuan Sun, Botao Yu, Ge Zhang, Huan Sun, Yu Su, Wenhu Chen, Graham Neubig
| Challenge: | Recent advances in multimodal large language models have led to progress in tackling complex reasoning tasks that combine textual and visual information. |
| Approach: | They introduce a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark. |
| Outcome: | The proposed model performs lower on MMMU-Pro than on the previous benchmark, ranging from 16.8% to 26.9%. |
Learning to Detect Noisy Labels Using Model-Based Features (2022.findings-emnlp)
Copied to clipboard
Zhihao Wang, Zongyu Lin, Junjie Wen, Xianxin Chen, Peiqi Liu, Guidong Zheng, Yujun Chen, Zhilin Yang
| Challenge: | Existing approaches to reduce label noise rely on heuristics and sample losses. |
| Approach: | They propose a method that transfers the noise distribution to a clean set and trains a model to distinguish noisy labels from clean ones using model-based features. |
| Outcome: | Empirically, the proposed approach improves over strong baselines on a wide range of tasks including text classification and speech recognition. |
Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches for optimizing human annotation efforts are limited . et al., 2015) suggest that densely annotated image captions improve vision-language alignment . |
| Approach: | They propose an AI-in-the-loop methodology to maximize the number of annotated samples and improve their comprehensiveness under fixed budget constraints. |
| Outcome: | The proposed method improves annotation speed and retrieval performance over the parallel method. |
Token Level Routing Inference System for Edge Devices (2025.acl-demo)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been gaining in performance but deployment in edge devices faces significant hurdles due to their high computational complexity. |
| Approach: | They propose a collaborative decoding system that allows small models to perform on-device inference while selectively consulting a cloud-based large model for critical token generation. |
| Outcome: | The proposed system achieves 60% performance gain on CommonsenseQA using a 0.5B model on an M1 MacBook, with under 7% of tokens generation uploaded to the large model in the cloud. |
Debt Collection Negotiations with Large Language Models: An Evaluation System and Optimizing Decision Making with Multi-Agent (2025.findings-acl)
Copied to clipboard
| Challenge: | Debt collection negotiations (DCN) are vital for managing non-performing loans (NPLs) prior systems lacking dynamic negotiation and real-time decision-making capabilities. |
| Approach: | They propose a framework for debt negotiation that incorporates planning and judging modules to improve decision rationality. |
| Outcome: | The proposed framework improves decision rationality and integrates planning and judging modules to improve decision rationalness. |
Towards More Realistic Chinese Spell Checking with New Benchmark and Specialized Expert Model (2024.lrec-main)
Copied to clipboard
Yue Wang, Zilong Zheng, Juntao Li, Zhihui Liu, Jinxiong Chang, Qishen Zhang, Zhongyi Liu, Guannan Zhang, Min Zhang
| Challenge: | Large Language Models (LLMs) have been gaining attention for their ability to perform a wide range of open-domain tasks . however, the performance of LLMs has yet to be comprehensively evaluated in realistic scenarios . |
| Approach: | They propose a task to evaluate the performance of Large Language Models (LLMs) they propose RCSC task to convert Chinese text into correct text . |
| Outcome: | The proposed task evaluates the performance of existing methods in Chinese text . the realistic Chinese spell checker can achieve state-of-the-art performance on the task . |
StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent work has demonstrated unprecedented capabilities in sophisticated linguistic comprehension and generative tasks. |
| Approach: | They propose a framework for search LLMs that trains with step-wise proximal policy optimization method to improve QA performance. |
| Outcome: | The proposed framework outperforms global-reward benchmarks on multi-hop QA with a stepwise proximal policy optimization method and richer and more detailed intermediate search rewards and token-level process supervision. |
Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)
Copied to clipboard
Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values. |
| Approach: | They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values . |
| Outcome: | The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets. |
Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have demonstrated remarkable performance on few-shot Named Entity Recognition tasks due to the high cost of obtaining high-quality labeled data. |
| Approach: | They propose to decompose the task into entity span detection and entity type classification using a type-independent entity span detector and then classify the detected spans based on their types. |
| Outcome: | The proposed method consistently yields improvements over two baseline approaches. |
FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosure (2026.acl-demo)
Copied to clipboard
Fan Zhang, Mingzi Song, Rania Elbadry, Yankai Chen, Shaobo Wang, Yixi Zhou, Xunwen Zheng, Yueru He, Yuyang Dai, Georgi Nenkov Georgiev, Ayesha Gull, Muhammad Usman Safder, Fan Wu, Liyuan Meng, Fengxian Ji, Junning Zhao, Xueqing Peng, Jimin Huang, YU Chen, Xue Liu, Preslav Nakov, Zhuohan Xie
| Challenge: | FinReporting is an agentic workflow for localized cross-jurisdiction financial reporting . existing approaches assume a single-market setting and overlook structural differences across jurisdictions . |
| Approach: | They propose a workflow that decomposes financial reporting into auditable stages . they use Large Language Models to extract and summarize corporate disclosures . |
| Outcome: | The proposed system decomposes reporting into auditable stages . it improves consistency and reliability under heterogeneous reporting regimes. |
Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference (2025.coling-main)
Copied to clipboard
Lanrui Wang, Jiangnan Li, Chenxu Yang, Zheng Lin, Hongyin Tang, Huan Liu, Yanan Cao, Jingang Wang, Weiping Wang
| Challenge: | Recent studies have focused on integrating commonsense knowledge into chatbots to enhance their ability to understand and generate dialogue responses. |
| Approach: | They propose a framework that integrates commonsense knowledge into chatbots to enable them to elicit more empathetic responses. |
| Outcome: | The proposed framework enables LLMs to uncover the implicit requirements of the conversation, aiming to elicit more empathetic responses. |
Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt Collection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models that assume users to be static, rational agents with fixed preferences fail to capture rich behavioral heterogeneity in real-world debt collection scenarios. |
| Approach: | They propose a public persona-enriched debt collection benchmark that highlights behavioral heterogeneity in negotiation. |
| Outcome: | The proposed benchmark outperforms existing models in realistic scenarios using 16 state-of-the-art LLMs. |
Instruction Tuning with Retrieval-based Examples Ranking for Aspect-based Sentiment Analysis (2024.findings-acl)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis (ABSA) identifies sentiment information related to specific aspects . previous studies have proposed using fixed examples for instruction tuning . |
| Approach: | They propose an instruction learning method with retrieval-based example ranking for ABSA tasks. |
| Outcome: | The proposed method is superior to existing models on three ABSA subtasks. |
Deep Differential Amplifier for Extractive Summarization (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to extract summary from document with a disproportionate ratio of selected and unselected sentences are far from human performance. |
| Approach: | They propose a model that rebalances sentence-level extractive summarization by amplifying the semantic difference between each sentence and all other sentences and applying the residual unit as the second item of the differential amplifier to deepen the architecture. |
| Outcome: | The proposed model performs competitively against state-of-the-art methods on two benchmark datasets. |
CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on multi-agent collaborative tasks in Minecraft is limited due to inefficiency and limited fault tolerance. |
| Approach: | They propose a framework that incorporates causality to manage dependencies among subtasks. |
| Outcome: | The proposed framework achieves state-of-the-art performance in multi-agent cooperative tasks of Minecraft. |
Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization on Multi-party Conversation (2025.acl-long)
Copied to clipboard
Luyao Cheng, Hui Wang, Chong Deng, Siqi Zheng, Yafeng Chen, Rongjie Huang, Qinglin Zhang, Qian Chen, Xihao Li, Wen Wang
| Challenge: | Mainstream speaker diarization systems rely only on acoustic information, making it challenging in complex aural environments. |
| Approach: | They propose a multimodal approach that integrates audio, visual, and semantic cues to enhance speaker diarization. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on multi-party conversations . it integrates audio-visual-semantic cues into the clustering process for acoustic speaker embeddings . |
LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding (2025.emnlp-main)
Copied to clipboard
Yuxuan Hu, Jihao Liu, Ke Wang, Jinliang Zheng, Weikang Shi, Manyuan Zhang, Qi Dou, Rui Liu, Aojun Zhou, Hongsheng Li
| Challenge: | Recent advances in Large Language Models have opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS). |
| Approach: | They propose a framework that leverages LLMs for cross-domain neural architecture optimization without extensive domain-specific tuning. |
| Outcome: | The proposed framework achieves competitive performance in both in-domain and out-of-domain tasks. |
Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal Language (2026.findings-acl)
Copied to clipboard
Peijie Wang, Ming-Liang Zhang, Jun Cao, Chao Deng, Dekang Ran, Pi Bu, Hongda Sun, Xuan Zhang, Yingyao Wang, Jun Song, Bo Zheng, Fei Yin, Cheng-Lin Liu
| Challenge: | Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across various vision reasoning tasks. |
| Approach: | They propose a unified formal language that integrates plane and solid geometry, comprehensively covering geometric structures and semantic relations. |
| Outcome: | The proposed language achieves state-of-the-art parsing performance and significantly boosts MLLMs’ capabilities for downstream geometry reasoning tasks. |
NaturalGAIA: A Verifiable Benchmark and Hierarchical Framework for Long-Horizon GUI Tasks (2026.acl-long)
Copied to clipboard
| Challenge: | Current research faces an "Evaluation-Realism Dilemma" due to unstable MLLM judges or manual verification. |
| Approach: | They propose a verifiable evaluation dataset grounded in real-world human GUI intents. |
| Outcome: | The proposed framework outperforms the state-of-the-art framework in achieving a weighted pathway success rate of 45.6% while reducing token consumption and execution time by 76%. |
Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework (2026.findings-acl)
Copied to clipboard
Jiaqi Weng, Han Zheng, Hanyu Zhang, Ej Zhou, Qinqin He, Jialing Tao, Hui Xue, Zhixuan Chu, Xiting Wang
| Challenge: | Existing studies on how SAEs derive most fine-grained latent features for safety remain unexplored. |
| Approach: | They propose a framework for interpreting SAE features in safety-critical domains . they train a suite of SAEs with human-readable explanations and systematic evaluations based on pornography, politics, violence, and terror . |
| Outcome: | The proposed framework reduces interpretation cost by 55% and improves safety-critical features. |
LoRE: Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment (2026.findings-acl)
Copied to clipboard
Chenji Lu, Zhuo Chen, Hui Zhao, Zhiyuan Zeng, Gang Zhao, Junjie Ren, null Lihaoran, Songyan Liu, Pengjie Wang, Chuan Yu, Jian Xu, Bo Zheng
| Challenge: | E-commerce search relevance is a critical component of retrieval systems. |
| Approach: | They propose a large-generative model for search relevance that trains reasoning knowledge, multi-modal understanding and rule awareness into three core competencies. |
| Outcome: | The proposed model outperforms GPT-5 in Macro-F1 and achieves 27% online gain. |
Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for novel category discovery focus on the scenario where known and novel categories are of the same granularity. |
| Approach: | They propose a novel scenario for fine-grained category discovery under coarse-grain supervision that allows for adapting models to categories of different granularity from known ones. |
| Outcome: | The proposed model can adapt models to categories of different granularity from known ones and reduce labeling cost. |
Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks (2023.emnlp-main)
Copied to clipboard
Haoqi Zheng, Qihuang Zhong, Liang Ding, Zhiliang Tian, Xin Niu, Changjian Wang, Dongsheng Li, Dacheng Tao
| Challenge: | Text classification tasks often encounter few-shot scenarios with limited labeled data, and addressing data scarcity is crucial. |
| Approach: | They propose a self-evolution learning (SE) based mixup approach for data augmentation in text classification which generates more adaptive and model-friendly pseudo samples for the model training. |
| Outcome: | The proposed approach can generate more adaptive and model-friendly pseudo samples for the model training. |
MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning (2024.acl-long)
Copied to clipboard
Chengpeng Li, Zheng Yuan, Hongyi Yuan, Guanting Dong, Keming Lu, Jiancan Wu, Chuanqi Tan, Xiang Wang, Chang Zhou
| Challenge: | In math reasoning with large language models, fine-tuning data augmentation by query evolution and diverse reasoning paths is empirically verified effective. |
| Approach: | They propose to fine-tune data augmentation by query evolution and diverse reasoning paths. |
| Outcome: | The proposed model achieves new state-of-the-art on GSM8K and MATH. |
Neighborhood Matching Network for Entity Alignment (2020.acl-main)
Copied to clipboard
| Challenge: | Structural heterogeneity between knowledge graphs is an outstanding challenge for entity alignment. |
| Approach: | They propose a framework for entity alignment that uses a neighborhood matching module to combine neighborhood differences. |
| Outcome: | The proposed framework outperforms existing methods on three datasets. |
Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that biased samples can be brittle for VQA models . however, the improvements on OOD data severely sacrifice the performance on the in-distribution (ID) data. |
| Approach: | They propose a contrastive learning approach that exploits biased samples for unbiased information that contributes to reasoning. |
| Outcome: | The proposed method achieves competitive performance on the OOD dataset while maintaining robustness on the ID dataset. |
RecMind: Large Language Model Powered Agent For Recommendation (2024.findings-naacl)
Copied to clipboard
Yancheng Wang, Ziyan Jiang, Zheng Chen, Fan Yang, Yingxue Zhou, Eunah Cho, Xing Fan, Yanbin Lu, Xiaojiang Huang, Yingzhen Yang
| Challenge: | Existing recommendations systems are limited in generalizing to new tasks due to model scale and data size constraints. |
| Approach: | They propose an LLM-powered autonomous recommender agent, RecMind, which is capable of leveraging external knowledge to provide zero-shot personalized recommendations. |
| Outcome: | The proposed model outperforms existing zero/few-shot LLM-based recommendation baseline methods in various tasks and achieves comparable performance to a fully trained recommendation model P5. |
Diversifying Dialog Generation via Adaptive Label Smoothing (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to dialog generation suffer from the over-confidence issue, which leads to poor generation diversity. |
| Approach: | They propose an Adaptive Label Smoothing approach that can adaptively estimate a target label distribution at each time step for different dialog contexts. |
| Outcome: | The proposed approach outperforms competing models on two benchmark datasets in producing diverse responses. |
CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing pruning methods rely on spatial proximity and remove relevant relations, thereby undermining reliable spatial reasoning. |
| Approach: | They propose a scene graph pruning model that integrates fuzzy semantic relevance with spatial proximity to estimate the importance of relations. |
| Outcome: | Experiments show that CAPruner outperforms proximity-based pruning with negligible cost savings. |
HyperCRS: Hypergraph-Aware Multi-Grained Preference Learning to Burst Filter Bubbles in Conversational Recommendation System (2025.findings-acl)
Copied to clipboard
Yongsen Zheng, Mingjie Qian, Guohua Wang, Yang Liu, Ziliang Chen, Mingzhi Mao, Liang Lin, Kwok-Yan Lam
| Challenge: | Existing methods to analyze filter bubbles in the static recommendation environment are unable to burst them during user interactions. |
| Approach: | They propose a paradigm to learn multi-grained user preferences during dynamic user-system interactions via natural language conversations to burst filter bubbles. |
| Outcome: | The proposed paradigm achieves state-of-the-art performance and the superior of bursting filter bubbles in the conversational recommendation system. |
A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs (2025.findings-acl)
Copied to clipboard
Yimin Deng, Yuxia Wu, Yejing Wang, Guoshuai Zhao, Li Zhu, Qidong Liu, Derong Xu, Zichuan Fu, Xian Wu, Yefeng Zheng, Xiangyu Zhao, Xueming Qian
| Challenge: | Existing methods focus on graph structure learning or semantic reasoning, lacking the capability to capture the inherent differences between historical and non-historical events. |
| Approach: | They propose a temporal knowledge graph reasoning framework that integrates both structural and semantic information to guide the reasoning process for different events. |
| Outcome: | The proposed framework integrates structural and semantic information to predict future events . it can provide evidence for many downstream tasks, including situation analysis and political decision making . |
Robust Lottery Tickets for Pre-trained Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that pre-trained language models contain smaller matching subnetworks that are not robust to adversarial examples. |
| Approach: | They propose a method to find robust tickets hidden in pre-trained language models by learning binary weight masks and an adversarial loss objective to guide the search. |
| Outcome: | The proposed method improves on previous work on adversarial robustness evaluation. |
VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction (2025.findings-emnlp)
Copied to clipboard
Jie Yang, Jiajun Chen, Zhangyue Yin, Shuo Chen, Yuxin Wang, Yiran Guo, Yuan Li, Yining Zheng, Xuanjing Huang, Xipeng Qiu
| Challenge: | Traditional Function Calling (FC) approaches operate statelessly, requiring multiple exploratory calls to build environmental awareness before execution, leading to inefficiency and limited error recovery. |
| Approach: | They propose a state-based function call approach that maintains explicit system state awareness and implements direct state transitions to achieve target conditions. |
| Outcome: | The proposed approach outperforms traditional function calling approaches, achieving superior execution accuracy and reduced latency. |
HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing (2022.findings-acl)
Copied to clipboard
| Challenge: | Recent studies focus on context-dependent text-to-SQL task but fail to exploit both . et al., 2019; xu e. al.; yu y., 2021) focus on the context-independent text to SQL task . |
| Approach: | They propose a history information enhanced text-to-SQL model to exploit context dependence information from history utterances and the last predicted SQL query. |
| Outcome: | The proposed model improves performance on two context-dependent text-to-SQL benchmarks. |
Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for designing and optimizing multi-agent systems are static and do not learn from experience. |
| Approach: | They propose a framework that enables a multi-agent system to learn to evolve . they use "textual gradients" to pinpoint failures and suggest granular modifications . |
| Outcome: | a new framework enables a multi-agent system to learn to evolve . it learns from historical optimization experiences to improve its performance . |
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Rapid advances in Large Language Models have spurred demand for processing extended context sequences . however, performance degradation due to sequence lengths out-of-distribution and excessively long inference times are limiting LLMs in long-context scenarios. |
| Approach: | They propose a training-free method for efficient and accurate long-context inference . they selectively involves a few critical KV cache tokens in attention calculation . |
| Outcome: | The proposed method speeds up attention computation and accelerates inference time while reducing selection overhead. |
MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples (2025.coling-main)
Copied to clipboard
Shuo Xie, Fangzhi Zhu, Jiahui Wang, Lulu Wen, Wei Dai, Xiaowei Chen, Junxiong Zhu, Kai Zhou, Bo Zheng
| Challenge: | Existing preference optimization methods such as DPO and KTO are inherently derived from PPO, requiring a reference model that adds GPU memory resources and relies heavily on abundant preference data. |
| Approach: | They propose an algorithm that leverages the average likelihood of model responses to fit the reward function and maximizes the utilization of preference data. |
| Outcome: | The proposed algorithm outperforms DPO, ORPO, and SimPO on MT-Bench and Arena-Hard. |
The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to learning-to-rank response selection are suboptimal due to ignorance of diversity of response quality. |
| Approach: | They propose to use off-the-shelf response retrieval models as automatic grayscale data generators to train response selection models. |
| Outcome: | The proposed approach can be automated without human effort on grayscale data. |
T2: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering (2025.emnlp-main)
Copied to clipboard
Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu
| Challenge: | Existing efficient test-time scaling methods introduce budget constraints or early stop mechanisms to avoid overthinking for straightforward questions but add human bias to the reasoning process. |
| Approach: | They propose a framework that dynamically adapts reasoning depth based on question complexity. |
| Outcome: | Experimental results show that the proposed framework achieves higher accuracy than baseline methods and reduces computational overhead by up to 25.2%. |
Uncovering Argumentative Flow: A Question-Focus Discourse Structuring Framework (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing structure modeling approaches fail to capture the author’s rhetorical intent and reasoning process. |
| Approach: | They propose a Question-Focus discourse structuring framework that explicitly models the underlying argumentative flow by anchoring each argumentative unit to a guiding question and a set of attentional foci. |
| Outcome: | The proposed framework outperforms baseline models and curated models on an argument reconstruction task in Chinese think-tank articles and claims coverage. |
LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model (2026.acl-long)
Copied to clipboard
| Challenge: | Existing parallel tokenization methods suffer from inconsistent results due to boundary artifacts that occur after merging. |
| Approach: | They propose a Lossless Parallel Tokenization framework that ensures output identical to standard sequential tokenization. |
| Outcome: | The proposed method achieves significant speedup while guaranteeing lossless tokenization. |
GRAPHIA: Harnessing Social Graph Data to Enhance LLM-Based Social Simulation (2026.acl-long)
Copied to clipboard
| Challenge: | Social graphs provide high-quality supervision signals that encode local interactions and global network structure, yet they remain underutilized for LLM training. |
| Approach: | They propose a general LLM-based social graph simulation framework that leverages graph data as supervision for LLM training. |
| Outcome: | The proposed framework improves micro-level alignment by 6.1% on three real-world networks compared to the strongest baseline. |
Toward Optimal LLM Alignments Using Two-Player Games (2025.findings-emnlp)
Copied to clipboard
Rui Zheng, Hongyi Guo, Zhihan Liu, Xiaoying Zhang, Yuanshun Yao, Xiaojun Xu, Zhaoran Wang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Yang Liu, Hang Li
| Challenge: | Alignment of large language models (LLM) is a process that ensures the model’s responses to user prompts align with human intentions and social values. |
| Approach: | They propose an alignment method based on a two-agent game consisting of an adversarial agent and a defensive agent. |
| Outcome: | The proposed method improves on a two-agent game with an adversarial agent and a defensive agent. |
Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have demonstrated remarkable performance across various reasoning tasks. |
| Approach: | They propose a task that evaluates LLMs’ capability in inferring rules from data fused with noisy examples. |
| Outcome: | The proposed method outperforms other methods with minimal performance degradation under noise and counterfactual task gaps highlight LLMs’ reliance on memorized patterns over genuine abstraction. |
How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition (2024.acl-long)
Copied to clipboard
Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou
| Challenge: | supervised fine-tuning (SFT) is a technique used to enhance multiple abilities in large language models. |
| Approach: | They propose to study the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning. |
| Outcome: | The proposed model improves math reasoning and code generation with increasing data amount . the proposed model size and SFT strategies can be used to learn multiple skills with different scaling patterns. |
Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmark (2025.emnlp-main)
Copied to clipboard
Jianyou Wang, Weili Cao, Longtian Bao, Youze Zheng, Gil Pasternak, Kaicheng Wang, Xiaoyue Wang, Ramamohan Paturi, Leon Bergen
| Challenge: | Systematic reviews should take into account the quality of available evidence, placing more weight on studies that use a valid methodology. |
| Approach: | They propose to use a risk-of-bias framework to assess the methodological strength of biomedical papers by combining expert reviewers' judgments with research paper sentences. |
| Outcome: | The proposed system measures the methodological strength of biomedical papers using the risk-of-bias framework used for systematic reviews. |
OpenResearcher: Unleashing AI for Accelerated Scientific Research (2024.emnlp-demo)
Copied to clipboard
Yuxiang Zheng, Shichao Sun, Lin Qiu, Dongyu Ru, Cheng Jiayang, Xuefeng Li, Jifan Lin, Binjie Wang, Yun Luo, Renjie Pan, Yang Xu, Qingkai Min, Zizhao Zhang, Yiwen Wang, Wenjie Li, Pengfei Liu
| Challenge: | Global scientific publications are growing annually by about 4%-5% (Pinedo et al., 2024). |
| Approach: | They introduce an AI-assisted platform that answers diverse questions from researchers using Retrieval-Augmented Generation (RAG) they develop various tools to understand queries, search from the scientific literature, filter retrieved information, provide accurate and comprehensive answers, and self-refine answers. |
| Outcome: | OpenResearcher is built on Retrieval-Augmented Generation (RAG) to integrate Large Language Models (LLMs) with up-to-date, domain-specific knowledge. |
Chain-of-Thought Reasoning in Tabular Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to extend chain-of-thought reasoning into large language models are not viable in the scenario of privatization deployment or limited resources. |
| Approach: | They propose a framework that extends chain-of-thought reasoning into tabular language models . framework coordinates two TaLMs responsible for CoT generation and answer inference . |
| Outcome: | The proposed framework outperforms the state-of-the-art ChatGPT on the TABMWP dataset by 9.55% (82.60%92.15% in accuracy) with less parameters (0.8B). |
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models (2024.acl-demos)
Copied to clipboard
Peng Wang, Ningyu Zhang, Bozhong Tian, Zekun Xi, Yunzhi Yao, Ziwen Xu, Mengru Wang, Shengyu Mao, Xiaohan Wang, Siyuan Cheng, Kangwei Liu, Yuansheng Ni, Guozhou Zheng, Huajun Chen
| Challenge: | Large Language Models (LLMs) suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. |
| Approach: | They propose an easy-to-use knowledge editing framework for Large Language Models that allows users to easily edit updated knowledge and adjust undesired behavior while minimizing the impact on unrelated inputs. |
| Outcome: | The proposed framework surpasses traditional fine-tuning in terms of reliability and generalization. |
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation (2021.acl-long)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) has shown great success in BERT compression. |
| Approach: | They propose a knowledge distillation paradigm that extracts the teacher's hidden state knowledge and then compresses it into three dimensions. |
| Outcome: | The proposed paradigm gives rise to training speedup of 2.7x 3.4x for two kinds of student models and computing devices. |
RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal NER (2020.coling-main)
Copied to clipboard
| Challenge: | Named entity recognition (MNER) for tweets is a key task of many applications. |
| Approach: | They propose a pre-trained multimodal named entity recognition model based on Relationship Inference and Visual Attention (RIVA) for tweets. |
| Outcome: | The proposed model improves on the multimodal named entity recognition (MNER) task on tweets with the aid of visual clues. |
Argus: Benchmarking and Enhancing Vision-Language Models for 3D Radiology Report Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing work on 3D radiograph report generation focuses on 2D images, but 3D medical images provide more comprehensive diagnostic information. |
| Approach: | They propose a comprehensive training recipe for building high-performing VLMs for 3DRRG using a publicly available 3D CT-report dataset. |
| Outcome: | The proposed model achieves superior performance across different model sizes and input 3D medical image resolutions. |
Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts (2025.emnlp-main)
Copied to clipboard
Yifei Yu, Qian-Wen Zhang, Lingfeng Qiao, Di Yin, Fang Li, Jie Wang, Chen Zeng Xi, Suncong Zheng, Xiaolong Liang, Xing Sun
| Challenge: | Recent models have extended Corresponding Author. context lengths to millions of tokens while maintaining reasoning and comprehension capabilities. |
| Approach: | They propose a benchmark to evaluate the ability of large language models to extract sequential information items from long contexts. |
| Outcome: | The proposed model achieves maximum accuracy of 63.50% on six well-known LLMs. |
Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure (2020.coling-main)
Copied to clipboard
| Challenge: | Multiparty dialog applications such as discourse parsing and meeting summarization are now mainstream research. |
| Approach: | They propose to annotate a machine reading comprehension dataset with discourse structure built over multiparty dialog using a modified Segmented Discourse Representation Theory (SDRT) style. |
| Outcome: | The proposed dataset contributes large-scale discourse dependency annotations in a modified Segmented Discourse Representation Theory (SDRT) style for all of its multiparty dialogs, and achieves only 67.7% F1 on Molweni’s questions, a 20+% significant drop as compared against its SQuAD 2.0 performance. |
CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown significant potential in code generation, but they also present challenges regarding the protection of Intellectual Property (IP) related to model architectures, weights, and training data. |
| Approach: | They propose a multi-bit watermarking technique that embeds additional information to preserve provenance details, such as the vendor ID of an LLM. |
| Outcome: | The proposed technique preserves provenance details while maintaining syntactical correctness of generated code. |
Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy (2021.emnlp-main)
Copied to clipboard
| Challenge: | Empirical studies on three different benchmark conversation datasets demonstrate the effectiveness of the proposed model over several strong baselines. |
| Approach: | They propose an addressee-aware module to automatically learn whether the participant keeps the historical emotional state or is affected by others in the next upcoming turn. |
| Outcome: | The proposed model can predict the participant's emotion in the next upcoming turn without knowing the participant’s response yet. |
SegTune: Structured and Fine-Grained Control for Song Generation (2026.acl-long)
Copied to clipboard
Yuejiao Wang, Zihao Ji, Pengfei Cai, Xu Li, Haorui Zheng, Zewen Song, Zhongliang Liu, Chen Zhang, Pengfei Wan
| Challenge: | Recent advances in neural song generation have enabled high-quality synthesis from lyrics and global textual prompts. |
| Approach: | They propose a framework that allows users to specify local musical descriptions aligned to song segments. |
| Outcome: | The proposed framework outperforms baselines in musicality and controllability. |
CoAD: Automatic Diagnosis through Symptom and Disease Collaborative Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Automated diagnosis (AD) is a critical application of AI in healthcare . despite its simplicity and superior performance, a decline in disease diagnosis accuracy is observed . |
| Approach: | They propose a new collaborative disease and symptom generation framework to improve automatic diagnosis. |
| Outcome: | The Transformer-based method achieves an average 2.3% improvement over previous state-of-the-art methods . it can be used to query patients about their symptoms and health concerns . |
Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings (2023.emnlp-main)
Copied to clipboard
Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Chong Deng, Hai Yu, Jiaqing Liu, Yukun Ma, Chong Zhang
| Challenge: | Prior studies diagnose the anisotropy problem in sentence embeddings from pre-trained language models without fine-tuning. |
| Approach: | They propose an unsupervised method that weights words with model-based importance estimations and computes the weighted average of word representations from pre-trained models as sentence embeddings. |
| Outcome: | Empirical evaluations show that the proposed method can alleviate the anisotropy problem and improve various pre-trained models on the STS benchmarks. |
Raw Pointer Rewriting with LLMs for Translating C to Safer Rust (2026.findings-acl)
Copied to clipboard
| Challenge: | C2Rust is a system programming language that enforces strict memory and type safety guarantees. |
| Approach: | They propose a raw pointer rewriting technique that lifts raw pointers in individual functions to appropriate Rust data structures. |
| Outcome: | The proposed technique eliminates 18.57% of local raw pointers and improves memory safety on 28 real-world C projects. |
Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing retrieval models emphasize surface-level semantic similarity, neglecting deeper solution-level logical similarities. |
| Approach: | They propose a solution-aware ranking model empowered by synthetic data for competitive programming tasks. |
| Outcome: | The proposed ranking model outperforms existing retrieval models in precision and recall metrics. |
PartialFormer: Modeling Part Instead of Whole for Machine Translation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing feed-forward neural networks have significant computational and parametric overhead. |
| Approach: | They propose a parameter-efficient Transformer architecture that utilizes multiple smaller FFNs to reduce parameters and computation while maintaining essential hidden dimensions. |
| Outcome: | The proposed architecture reduces computational and parameter overhead while maintaining essential hidden dimensions. |
Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)
Copied to clipboard
Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong
| Challenge: | Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited. |
| Approach: | They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning . |
| Outcome: | The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster. |
PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to evaluate privacy leakage in LLMs use memorized prefixes or simple instructions to extract data, which well-aligned models can easily block. |
| Approach: | They propose a framework targeting Personally Identifiable Information (PII) that uses in-context learning to build a privacy context and iteratively updates it with three gradient-based strategies to elicit target PII. |
| Outcome: | The proposed framework outperforms baseline methods and achieves state-of-the-art (SoTA) results on four white-box and two black-box LLMs. |
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
Yuan Li, Qi Luo, Xiaonan Li, Bufan Li, Qinyuan Cheng, Bo Wang, Yining Zheng, Yuxin Wang, Zhangyue Yin, Xipeng Qiu
| Challenge: | RAG systems that integrate external knowledge with Large Language Models often become bottlenecks due to their limited parameters compared to LLMs and their inability to perform step-by-step reasoning. |
| Approach: | They propose a model that integrates external knowledge with Large Language Models to enhance factual correctness and mitigate hallucination. |
| Outcome: | The proposed model outperforms baselines and can transfer well to different retrievers. |
AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark (2025.acl-long)
Copied to clipboard
| Challenge: | Evaluation benchmarks based on predefined domains and human-labeled data face limitations in addressing evaluation needs for emerging domains. |
| Approach: | They propose an automated information retrieval benchmark based on predefined domains and human-labeled data . AIR-Bench is automated and Heterogeneous with three key features . |
| Outcome: | The proposed benchmarks are based on predefined domains and human-labeled data. |
FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis (2026.findings-acl)
Copied to clipboard
Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Gang Chen
| Challenge: | Existing benchmarks for realistic financial analysis fail to capture realistic financial situations involving cross-document retrieval, multi-page evidence integration, and diverse analytical tasks. |
| Approach: | They propose a multi-modal financial RAG benchmark that evaluates large language models in realistic financial analysis settings. |
| Outcome: | The proposed framework achieves the strongest overall performance across all models. |
GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety (2026.findings-acl)
Copied to clipboard
Changxuan Fan, Xi Yang, Yueyuan Zheng, Bin Zhou, Yuanping Wang, Wenbin Hu, Huihao Jing, Ki Sen Hung, Dazhao Du, Haoran Li, Janet Hui-wen Hsiao, Yangqiu Song
| Challenge: | a survey of older adults shows that many LLMs mishandle elderly-specific contextual risks. |
| Approach: | They propose a framework to assess elderly-specific contextual risks in LLM interactions . they use a taxonomy to identify 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains . |
| Outcome: | a new framework assesses elderly-specific contextual risks in LLM interactions . it achieves 96.2% and 90.9% unsafe-prompt detection accuracy, respectively . |
Enabling Agents to Communicate Entirely in Latent Space (2026.acl-long)
Copied to clipboard
Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Yu Cheng, Bo Zheng, Wei Chen, Haochao Ying
| Challenge: | Natural language is the de facto communication medium for LLM-based agents, but it presents a fundamental constraint . natural language downsampling limits the depth and nuance of information that can be transmitted . et al.: inter-agent latent space communication is a promising paradigm for solving complex tasks . |
| Approach: | They propose a paradigm that leverages the last hidden states of an LLM as a representation of its thought for direct communication. |
| Outcome: | The proposed paradigm outperforms fine-tuned chain-of-thought prompting and single-agent baselines even across heterogeneous models. |
Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge (2024.emnlp-main)
Copied to clipboard
| Challenge: | despite advances in multimodal large language models, the challenge of interpreting long-form videos remains a challenge . despite advancements in video-language benchmarks, the inefficiency in temporal grounding and limited pre-trained context window size remains . |
| Approach: | They propose a framework that bootstraps MLLMs with advanced temporal grounding capabilities and broadens their contextual scope. |
| Outcome: | The proposed framework significantly enhances the temporal capabilities of existing MLLMs. |
IM-TQA: A Chinese Table Question Answering Dataset with Implicit and Multi-type Table Structures (2023.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks only evaluate model performance on tables with explicit table structures, which means headers are explicitly annotated and treated as model input during inference. |
| Approach: | They propose a new Table Question Answering (TQA) dataset with implicit and multi-type table structures that requires the model to understand tables without directly available header annotations. |
| Outcome: | The proposed framework outperforms baselines on a dataset with implicit and multi-type table structures and can handle multi-table tables including previously neglected complex tables. |
FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis (2025.findings-acl)
Copied to clipboard
Yilun Zheng, Sha Li, Fangkun Wu, Yang Ziyi, Lin Hongchao, Zhichao Hu, Cai Xinjun, Ziming Wang, Jinxuan Chen, Sitao Luan, Jiahao Xu, Lihui Chen
| Challenge: | Parody is an emerging phenomenon on social media, where individuals imitate a role or position opposite to their own . limited available data and deficient diversity in current datasets hinder study of parody . |
| Approach: | They build a dataset of parody users and annotated comments from both English and Chinese corpora to test parody detection and comment sentiment analysis. |
| Outcome: | The proposed datasets provide richer contextual information, which is lacking in existing datasets. |
Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory Network (2022.acl-long)
Copied to clipboard
| Challenge: | a fundamental challenge in modeling math problems is how to fuse semantics of textual description and formulas. |
| Approach: | They propose a method to continually pre-train language models for improving understanding of math problems with syntax-aware memory networks. |
| Outcome: | The proposed approach outperforms competitive baselines on four math tasks. |
FedCSR: A Federated Framework for Multi-Platform Cross-Domain Sequential Recommendation with Dual Contrastive Learning (2025.coling-main)
Copied to clipboard
Dongyi Zheng, Hongyu Zhang, Jianyang Zhai, Lin Zhong, Lingzhi Wang, Jiyuan Feng, Xiangke Liao, Yonghong Tian, Nong Xiao, Qing Liao
| Challenge: | Existing federated frameworks for cross-domain sequential recommendation rely on user alignment, which increases communication costs and privacy risks. |
| Approach: | They propose a federated cross-domain sequential recommendation framework that eliminates the need for user alignment between platforms. |
| Outcome: | The proposed framework eliminates the need for user alignment between platforms. |
Rethinking Dictionaries and Glyphs for Chinese Language Pre-training (2023.findings-acl)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models (PLMs) such as BERT and GPT have revolutionized various research fields in natural language processing (NLP) |
| Approach: | They propose a new learning paradigm that enhances the semantics understanding ability of Chinese PLMs with dictionary knowledge and structure of Chinese characters. |
| Outcome: | The proposed model improves on both modern Chinese understanding benchmark CLUE and ancient Chinese understanding. |
Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization (2025.findings-emnlp)
Copied to clipboard
Zhengzhao Lai, Youbin Zheng, Zhenyang Cai, Haonan Lyu, Jingpu Yang, Hong-Qing Liang, Yan Hu, Benyou Wang
| Challenge: | characterization imaging data is fundamental to acquiring materials information. |
| Approach: | a team of researchers develop a benchmark for materials characterization imaging data . the goal is to bridge this gap by addressing 1,500 questions that require expert-level expertise. |
| Outcome: | a new benchmark for materials characterization imaging data is presented . the benchmark reveals that MLLMs perform poorly when addressing higher-level questions . |
UCTG: A Unified Controllable Text Generation Framework for Query Auto-Completion (2025.coling-industry)
Copied to clipboard
| Challenge: | Existing approaches to control text generation (CTG) are essentially challenging to adapt to various control objectives and constraints, which results in mixed success. |
| Approach: | They propose a unified controllable text generation framework which integrates a control module, a prompt module, and a generation module. |
| Outcome: | The proposed framework significantly improves query accuracy and coherence in tasks with different objectives and constraints. |
UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation (2025.findings-emnlp)
Copied to clipboard
Tianlong Li, Wenhao Liu, Muling Wu, Shihan Dou, Zhenghua Wang, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs). |
| Approach: | They propose a method that uses an Unsupervisedly-Built Personalized Lexicon (UPL) during the decoding phase to manipulate LLM’s personality traits. |
| Outcome: | The proposed method can modulate the personality expression of large language models by dynamically altering their predicted probability of upcoming words in a pluggable fashion. |
Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs (2024.emnlp-main)
Copied to clipboard
| Challenge: | In the age of mobile internet, personal information is constantly being generated on smartphones. |
| Approach: | They propose a novel task of crafting personalized agents powered by large language models that leverage a user's smartphone memories to enhance downstream applications with LLM capabilities. |
| Outcome: | The proposed approach improves 10% over the best existing approach on a real-world dataset and improves usability. |
ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control (2025.acl-long)
Copied to clipboard
Shengpeng Ji, Qian Chen, Wen Wang, Jialong Zuo, Minghui Fang, Ziyue Jiang, Hai Huang, Zehan Wang, Xize Cheng, Siqi Zheng, Zhou Zhao
| Challenge: | Prior zero-shot TTS models only mimic the speaker’s voice without further control and adjustment capabilities while prior controllable TTS systems cannot perform speaker-specific voice generation. |
| Approach: | They propose a style control module that captures codec representations corresponding to timbre, content, and style in a discrete decoupling codec space. |
| Outcome: | The proposed system can fully clone the speaker's voice and perform speech-specific adjustment and control functions. |
Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent studies show pre-trained language models contain matching subnetworks that have similar transfer learning performance as the original PLM. |
| Approach: | They propose to prune matching subnetworks using magnitude-based pruning . they propose to optimize the subnetwork structure towards the pre-training objectives . |
| Outcome: | The proposed method is more efficient in searching subnetworks and advantageous when fine-tuning within a range of data scarcity. |
Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition (2025.acl-long)
Copied to clipboard
Kehua Feng, Keyan Ding, Tan Hongzhi, Kede Ma, Zhihua Wang, Shuangquan Guo, Cheng Yuzhou, Ge Sun, Guozhou Zheng, Qiang Zhang, Huajun Chen
| Challenge: | Existing methods for evaluation of large language models are inefficient and inefficient due to inaccuracy of standard metrics in human perception of text quality and inefficiency in sampling informative test examples. |
| Approach: | They propose a sample-efficient human evaluation method for large language models based on the principle of MAximum Discrepancy (MAD) competition. |
| Outcome: | The proposed method achieves the “golden” ranking of LLMs with a minimum set of input instructions, which in turn reveal their relative strengths and weaknesses. |
Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction (2026.findings-acl)
Copied to clipboard
Shuoxin Wang, Chang Liu, Gowen Loo, Lifan Zheng, Kaiwen Wei, Huanqian Yan, Xinyi Zeng, Jingyuan Zhang, Yu Tian
| Challenge: | Existing Large Language Model (LLM)-based mobile agents follow explicit user instructions without personalized needs. |
| Approach: | They propose a user preference learning strategy enhanced with a Personal Reward Model to improve personalization performance. |
| Outcome: | The proposed agent achieves state-of-the-art performance while maintaining competitive instruction execution performance. |
DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for reconstruction of large language models overlook diversity among experts, leading to potential redundancy. |
| Approach: | They propose a pruning-based expert reconstruction method that prunes a specific LLM and retrains it on routers, experts and normalization modules. |
| Outcome: | The proposed method outperforms pruning and MoE reconstruction methods on Llama-style models with open-source training corpora. |
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)
Copied to clipboard
Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin
| Challenge: | Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation. |
| Approach: | They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets. |
| Outcome: | The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark. |
Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (2024.findings-acl)
Copied to clipboard
Bowen Jin, Chulin Xie, Jiawei Zhang, Kashob Kumar Roy, Yu Zhang, Zheng Li, Ruirui Li, Xianfeng Tang, Suhang Wang, Yu Meng, Jiawei Han
| Challenge: | Existing studies suggest augmenting LLMs with external text corpora to alleviate hallucination problems. |
| Approach: | They propose to augment large language models with text units retrieved from external knowledge corpora to alleviate the issue. |
| Outcome: | The proposed framework outperforms baselines on GRBench with three LLMs and shows that iterative reasoning outperformed the baselines. |
ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on LLMs' factual knowledge are unreliable since the questions can vary not only in entity frequency but also in difficulty themselves. |
| Approach: | They propose a benchmark to study the role of knowledge frequency in the performance of large language models (LLMs) it aims to avoid possible semantic shortcuts which is a serious problem of current QA study. |
| Outcome: | The proposed method avoids possible semantic shortcuts and improves on existing proofs. |
COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing statically compressed pre-trained language models lack spatial and temporal efficiency due to their large size and wide width. |
| Approach: | They propose a spatially and temporally efficient model which retains the major capacity of PLMs. |
| Outcome: | The proposed model retains the major capacity of pre-trained language models at high compression and acceleration rate with 1/8 parameters and 1/19 FLOPs of BERT. |
Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering (2025.findings-acl)
Copied to clipboard
Zheng Chu, Huiming Fan, Jingchang Chen, Qianyu Wang, Mingda Yang, Jiafeng Liang, Zhongjie Wang, Hao Li, Guo Tang, Ming Liu, Bing Qin
| Challenge: | Large language models (LLMs) have demonstrated remarkable reasoning capabilities, but they still face challenges in knowledge-intensive multi-hop reasoning. |
| Approach: | They propose a method that uses self-critique feedback to guide iterative reasoning by enabling iteration and self-evaluation of its intermediate reasoning steps. |
| Outcome: | The proposed method surpasses the previous SOTA by 8.6% on three multi-hop reasoning datasets. |
IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters (2026.acl-industry)
Copied to clipboard
Hongwei Zheng, Weiqi Wu, Zhengjia Wang, Guanyu Jiang, Haoming Li, Tianyu Wu, Yongchun Zhu, Jingwu Chen, Feng Zhang
| Challenge: | Existing efforts focus on activation within ongoing dialogues, while overlooking a key real-world bottleneck. |
| Approach: | They propose a conversation starter generation system that generates personalized starters to guide users into conversation without explicit user intent. |
| Outcome: | The proposed system improves user active days by +1.84 and click-through rate by +94.25 and has been deployed in production. |
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods neglect stylistic modeling and rely on static thresholds, which greatly limits the detection performance. |
| Approach: | They propose a framework that enables stylistics-aware uncertainty quantification through conditional threshold estimation. |
| Outcome: | The proposed framework achieves an average improvement 11.34% in detection performance compared to baselines. |
Think and Recall: Layer-Level Prompting for Lifelong Model Editing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for lifelong model editing suffer from limitations in usability, such as requiring additional training corpora or lacking support for reversible and detachable edits. |
| Approach: | They propose a plug-and-play method for knowledge retrieval and storage, i.e., Layer-Level Prompting, which enables seamless and efficient lifelong model editing. |
| Outcome: | The proposed method outperforms existing methods on question answering and hallucination benchmarks across different LLMs. |
Demystify the Role of Memory in Machine Learning Engineering Agents (2026.findings-acl)
Copied to clipboard
Xinyu Zhao, Junpeng Wang, Yuzhong Chen, Menghai Pan, Chin-Chia Michael Yeh, Jiarui Sun, Yan Zheng, Mahashweta Das, Tianlong Chen
| Challenge: | Unlike short, reactive exchanges, MLE agents solve tasks through cycles of experimentation and improvement where past errors can inform future success. |
| Approach: | They propose a dynamic coding memory that captures and reuses debugging experiences and integrates it into two representative agent paradigms. |
| Outcome: | The proposed agent model captures and reuses debugging experiences and integrates it into two agent paradigms. |
Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension (2023.findings-acl)
Copied to clipboard
| Challenge: | Compared to standard RC tasks, dialogue reading comprehension (DRC) has raised challenges because of the complex speaker information and noisy dialogue context. |
| Approach: | They propose a new method for dialogue reading comprehension that extracts answers from dialogues by using key-utterances-extracting methods and a Question-Interlocutor Scope Realized Graph. |
| Outcome: | The proposed method achieves state-of-the-art performance against previous works. |
Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Abductive reasoning is the process of making educated guesses to provide explanations for observations. |
| Approach: | They propose a task of complex logical hypothesis generation to generate a complex logique hypothesis that can explain a set of observations. |
| Outcome: | The proposed model generates logical hypotheses closer to the reference hypothesis, but not better on unseen observations. |
Ranking and Sampling in Open-Domain Question Answering (D19-1)
Copied to clipboard
| Challenge: | Existing approaches focus on positive paragraphs which contain the answer during training, making it disturbed by similar but irrelevant paragraphs during testing. |
| Approach: | They propose a ranking model leveraging the paragraph-question and the paragraph relevance to compute a confidence score for each paragraph. |
| Outcome: | Experiments on three datasets show that the proposed model advances the state of the art. |
Towards Unifying Reference Expression Generation and Comprehension (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for REG and REC have distinct inputs and connections between them . a new model for REg and reprehension is needed to solve these problems . |
| Approach: | They propose a unified model for REG and REC that fuses image, region and text . they propose Vision-conditioned Masked Language Modeling and Text-Conditioned Region Prediction . |
| Outcome: | The proposed model outperforms existing models on REG and REC tasks. |
Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline (2026.acl-long)
Copied to clipboard
| Challenge: | Existing facial forgery detection methods focus on binary classification or pixel-level localization, providing little semantic insight into the nature of the manipulation. |
| Approach: | They propose a multimodal task that localizes forged regions and generates natural language explanations grounded in editing process. |
| Outcome: | The proposed task localizes forged regions and generates natural language explanations grounded in editing process. |
DCMKC: A Dual Consistency Matching Approach for Multi-hop Question Answering in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing reasoning based on chains of thought (CoTs) fails to find logical connections between reasoning steps . |
| Approach: | They propose a method to match KG reasoning chains with CoTs based on semantic similarity . they use a knowledge graph to find relevant information "within" each reasoning step . |
| Outcome: | The proposed method outperforms baselines on multi-answer questions with 5.1% improvement over baselines. |
Prompt-learning for Fine-grained Entity Typing (2022.findings-emnlp)
Copied to clipboard
Ning Ding, Yulin Chen, Xu Han, Guangwei Xu, Xiaobin Wang, Pengjun Xie, Haitao Zheng, Zhiyuan Liu, Juanzi Li, Hong-Gee Kim
| Challenge: | Extensive experiments on fine-grained entity typing under fully supervised, few-shot, and zero-shot settings show the effectiveness of prompt-learning. |
| Approach: | They propose a prompt-learning pipeline that stimulates versatile knowledge of pre-trained language models (PLMs) by constructing entity-oriented verbalizers and templates and conducting masked language modeling. |
| Outcome: | The proposed approach can be applied to fine-grained entity typing in fully supervised, few-shot, and zero-shot scenarios. |
Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling (2024.findings-acl)
Copied to clipboard
Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang
| Challenge: | Recent advances in large language models (LLMs) have led to significant success in using LLMs as agents. |
| Approach: | They propose a cognitive framework that incorporates first-order and second-order perspective transitions into LLMs to enhance their ability to identify and counteract deceptive information. |
| Outcome: | The proposed framework enhances LLMs’ ability to identify and counteract deceptive information without extra fine-tuning and data. |
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization (2022.acl-short)
Copied to clipboard
Zheng Li, Zijian Wang, Ming Tan, Ramesh Nallapati, Parminder Bhatia, Andrew Arnold, Bing Xiang, Dan Roth
| Challenge: | Empirical analyses show that pre-trained sequence-to-sequence models can achieve a 16.5x model footprint compression ratio with little performance drop relative to full-precision counterparts. |
| Approach: | They propose to distill and quantize pre-trained sequence-to-sequence models to reduce memory and latency requirements. |
| Outcome: | Empirical results show that the proposed model achieves 16.5x model footprint compression ratio with little performance drop relative to full-precision counterparts on multiple summarization and QA datasets. |
Synergizing Multimodal Temporal Knowledge Graphs and Large Language Models for Social Relation Recognition (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have limited capacity to model complex graph-structured relationships. |
| Approach: | They propose a low-coupling method synergizing multimodal temporal Knowledge Graphs and Large Language Models for social relation reasoning. |
| Outcome: | The proposed method exhibits state-of-the-art performance in social relation recognition . it bridges the gap between KGs and LLMs and will be released after acceptance . |
Advancing Parameter Efficiency in Fine-tuning via Representation Editing (2024.acl-long)
Copied to clipboard
Muling Wu, Wenhao Liu, Xiaohua Wang, Tianlong Li, Changze Lv, Zixuan Ling, Zhu JianHao, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Parameter Efficient Fine-Tuning (PEFT) has gained significant attention for its ability to achieve competitive results while updating only a small subset of trainable parameters. |
| Approach: | They propose a new approach to fine-tuning neural models that scales and biases the representation produced at each layer. |
| Outcome: | The proposed approach reduces the number of trainable parameters by a factor of 25,700 compared to full parameter fine-tuning and by . 32 compared with LoRA. |
Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety defenses typically intervene internally within the generative model, but suffer from severe concept entanglement, leading to degradation of benign generation quality. |
| Approach: | They propose a structurally isolated safety module that performs external, interpretable rectification without modifying the base model. |
| Outcome: | The proposed module performs external, interpretable rectification without modifying the base model. |
The Strength of the Weakest Supervision: Topic Classification Using Class Labels (N19-3)
Copied to clipboard
| Challenge: | a topic classifier can understand only class labels when training for tasks that require a large amount of labeled documents. |
| Approach: | They propose an algorithm that can initialize a topic classifier using only class labels . they propose a method that combines word embedding and naive Bayes classification . |
| Outcome: | The proposed approach saves significant initial labeling effort by providing a "warm start" the proposed approach can be fine-tuned with more labeled documents to reach a certain performance level. |
ACE-M3: Automatic Capability Evaluator for Multimodal Medical Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing metrics for multimodal large language models only focus on token overlap and may not align with human judgment. |
| Approach: | They propose an open-source model that assesses the question answering abilities of multimodal large language models. |
| Outcome: | Experiments show that the ACE-M3 model performs better than existing models and is more reliable than existing metrics. |
A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges (2025.findings-acl)
Copied to clipboard
Yibo Yan, Jiamin Su, Jianxiang He, Fangteng Fu, Xu Zheng, Yuanhuiyi Lyu, Kun Wang, Shen Wang, Qingsong Wen, Xuming Hu
| Challenge: | This survey provides **the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models** . integrating large language model with mathematical reasoning tasks is becoming significant as AI advances . |
| Approach: | They review over 200 studies published since 2021 and examine the state-of-the-art developments in Math-LLMs . they identify five major challenges hindering the realization of AGI in this domain . |
| Outcome: | The authors examine the state-of-the-art developments in Math-LLMs with a focus on multimodal settings. |
PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks (2022.coling-1)
Copied to clipboard
| Challenge: | Neural networks are vulnerable to adversarial examples, i.e., under a black-box scenario. |
| Approach: | They propose a word-level search algorithm that searches for subareas under dynamic search space following the subarea importance. |
| Outcome: | The proposed algorithm can achieve comparable success rates to complex search methods while saving numerous queries and time. |
Multi-modal Contrastive Representation Learning for Entity Alignment (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies focus on how to utilize information from different modalities, but it is not trivial to leverage multi-modal knowledge in entity alignment because of the modality heterogeneity. |
| Approach: | They propose a Multi-modal Contrastive Learning based Entity Alignment model which learns multiple individual representations from multiple modalities and performs contrastive learning to jointly model inter-modal and inter-modal interactions. |
| Outcome: | The proposed model outperforms state-of-the-art models on public datasets under both supervised and unsupervised conditions. |
Lightweight LLM Agent Memory with Small Language Models (2026.acl-long)
Copied to clipboard
Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang, Pengcheng Zheng, Zhicheng Wang, Ping Guo, Fan Mo, Sung-Ho Bae, Jie Zou, Jiwei Wei, Yang Yang
| Challenge: | Existing external memory systems for LLMs have low online overhead but are unstable in accumulating latency over long interactions. |
| Approach: | They propose a lightweight memory system for better agent memory driven by Small Language Models . lightmem modularizes memory retrieval, writing, and long-term consolidation . they show consistent gains across model scales and high efficiency . |
| Outcome: | The proposed system improves agent memory but has low latency and low online overhead . it separates online processing from offline consolidation to enable efficient memory invocation . the proposed system achieves an average F1 improvement of 2.5 over A-MEM on LoCoMo . |
Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark (2025.coling-main)
Copied to clipboard
Zhikun Xu, Yinghui Li, Ruixue Ding, Xinyu Wang, Boli Chen, Yong Jiang, Haitao Zheng, Wenlian Lu, Pengjun Xie, Fei Huang
| Challenge: | Recent work has noted that due to the extremely high cost of iterative updates of LLMs, they are often unable to answer dynamic questions well. |
| Approach: | They propose a Chinese Dynamic QA benchmark containing question-answer pairs related to the latest dynamic questions on the Chinese Internet. |
| Outcome: | The proposed benchmark will be one of the key data resources for improving LLMs’ Chinese question-answering ability in the future. |
Is Continuous Prompt a Combination of Discrete Prompts? Towards a Novel View for Interpreting Continuous Prompts (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on the interpretability and transferability of continuous prompts have not been conducted on the subject. |
| Approach: | They propose to interpret continuous prompts as the weighting of discrete prompts by jointly optimizing prompt fidelity and downstream fidelity. |
| Outcome: | The proposed interpretations provide effective readability and plausibility, which is helpful to understand the decision-making of continuous prompts and discover potential shortcuts. |
CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base, which often miss relevant information located further away from a global view. |
| Approach: | Hybrid-RAG combines textual documents and graph-structured relational information for RAG . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base . |
| Outcome: | Hybrid-RAG combines textual documents and graph-structured relational information . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base . |
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)
Copied to clipboard
Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Josef Dai, Boren Zheng, Tianyi Alex Qiu, Jiayi Zhou, Kaile Wang, Boxun Li, Sirui Han, Yike Guo, Yaodong Yang
| Challenge: | Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours. |
| Approach: | They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs . |
| Outcome: | The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models. |
SOAR: Supervision from Observation for Agentic Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work assigns supervision based on outcome rewards or external reward models, but ignores environment observations, a critical source of learning. |
| Approach: | They propose a supervision-based agentic reinforcement learning system that integrates environment observations as an explicit supervision signal. |
| Outcome: | The proposed model improves performance on reasoning and deep research tasks while reducing erroneous and inefficient tool usage. |
Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing data synthesis tools struggle to extract reliable fine-tuning data from heterogeneous documents. |
| Approach: | They propose a framework for synthesizing fine-tuning data from unstructured documents via an intuitive graphical user interface. |
| Outcome: | The proposed framework can extract reliable data from unstructured documents via an intuitive graphical user interface (GUI) it leverages persona-driven prompting approach to generate diverse question-answer pairs using public-available LLMs. |
MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning (2026.findings-acl)
Copied to clipboard
Yimin Deng, Zhenxi Lin, Yejing Wang, Guoshuai Zhao, Pengyue Jia, Zichuan Fu, Derong Xu, Yefeng Zheng, Xiangyu Zhao, Li Zhu, Xian Wu, Xueming Qian
| Challenge: | Existing approaches focus on diagnostic reasoning based on internal model knowledge or static knowledge bases. |
| Approach: | They propose a two-stage diagnostic reasoning framework that integrates multi-perspective evidence to generate a diagnostic prediction. |
| Outcome: | The proposed method generates suspected diagnoses and reasoning traces from web search, SOAP-formatted case, and clinical case database. |
Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent work on Chain-of-Thought prompting imposes substantial computational overhead . lack of supervision obscures the analyzability of the latent reasoning chain. |
| Approach: | They propose a framework to render latent reasoning chain into images, making latent rationale explicit and traceable. |
| Outcome: | The proposed framework achieves 3-4 token compression and substantial inference acceleration compared to explicit CoT prompting. |
MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding (2024.emnlp-main)
Copied to clipboard
Baixuan Xu, Weiqi Wang, Haochen Shi, Wenxuan Ding, Huihao Jing, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Long Chen, Yangqiu Song
| Challenge: | Existing methods for acquiring large-scale intentions generate product-centric intentions without product images and incur high costs for scalability. |
| Approach: | They propose a multimodal framework that allows Large Vision-Language Models to infer purchase intentions from multimodal product metadata and prioritize human-centric ones. |
| Outcome: | The proposed framework shows that it is robust to different prompts and superior to previous methods. |
Check It Again:Progressive Visual Question Answering via Visual Entailment (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to Visual Question Answering (VQA) only address superficial correlations between image and answer. |
| Approach: | They propose a select-and-rerank progressive framework based on Visual Entailment to address this problem. |
| Outcome: | The proposed framework improves on the Visual Question Answering (VQA) task with 7.55% accuracy. |
From Discrimination to Generation: Low-Resource Intent Detection with Language Model Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies fine-tune discriminative models on specific defined intent classes, preventing them from being directly adopted to new intent domains. |
| Approach: | They propose to use a pre-trained generative intent model to detect new intents from different domains with no parameter updates. |
| Outcome: | The proposed model outperforms baselines that need further fine-tuning or domain-specific samples. |
PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning (2026.findings-acl)
Copied to clipboard
Langming Liu, Kangtao Lv, Haibin Chen, Weidong Zhang, Yejing Wang, Shilei Liu, Xin Tong, Yujin Yuan, Yongwei Wang, Wenbo Su, Bo Zheng
| Challenge: | Large language models suffer from factual hallucinations where they generate verifiable falsehoods. |
| Approach: | They propose a framework that integrates reinforcement learning into the pretraining phase to consolidate factual knowledge. |
| Outcome: | The proposed framework significantly alleviates factual hallucinations and outperforms state-of-the-art methods. |
CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)
Copied to clipboard
Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang
| Challenge: | Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data . |
| Approach: | They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation. |
| Outcome: | The proposed framework outperforms open-source baselines and is competitive with GPT-5. |
A Dataset and Baselines for Multilingual Reply Suggestion (2021.acl-long)
Copied to clipboard
| Challenge: | Reply suggestion models help users process emails and chats faster. |
| Approach: | They present a multilingual reply suggestion dataset with ten languages . they build a generation model and a retrieval model as baselines for MRS . |
| Outcome: | The proposed model complements existing benchmarks for cross-lingual generalization . the model has different strengths in the English monolingual setting and requires different strategies to generalize across languages. |
Learning Transition Patterns by Large Language Models for Sequential Recommendation (2025.coling-main)
Copied to clipboard
Jianyang Zhai, Zi-Feng Mai, Dongyi Zheng, Chang-Dong Wang, Xiawu Zheng, Hui Li, Feidiao Yang, Yonghong Tian
| Challenge: | Extensive experiments on six real-world datasets show our approach outperforms the best baselines by 7.33% in NDCG@10, 4.65% in Recall@10 and 8.42% in MRR. |
| Approach: | They propose a framework for mapping sequential item texts to sequential item IDs that incorporates multi-query input and item linear projection to model conditional probability distribution of items. |
| Outcome: | The proposed framework outperforms baseline models on six real-world datasets by 7.33% and 4.65% respectively. |
MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have significantly enhanced automated program synthesis. |
| Approach: | They propose a model-adaptive and verification–enhanced framework for competition-level code generation that leverages adaptive assessment aligned with the model’s capabilities to select planning strategies while providing timely feedback and correction via multi-perspective verification. |
| Outcome: | The proposed framework outperforms existing state-of-the-art approaches on livecodebench, humanEval+, MBPP+, and codecontests, and achieves pass@1 results exceeding 3%–40%. |
Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Generative Reward Models have demonstrated that scaling the length of Chain-of-Thought reasoning enhances reliability of evaluation. |
| Approach: | They propose a framework that reconfigures raw rationales into structured Breadth-CoT and Depth-Co T through a modular synthesis pipeline. |
| Outcome: | The proposed framework surpasses open-source RMs by an average of 8.2%. |
From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are catalyzing a paradigm shift in scientific discovery, evolving from task-specific automation tools into increasingly autonomous agents. |
| Approach: | They introduce a foundational three-level taxonomy to delineate their escalating autonomy and evolving responsibilities within the research lifecycle. |
| Outcome: | The proposed frameworks provide a conceptual architecture and strategic foresight to navigate and shape the future of AI-driven scientific discovery. |
Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs (2025.acl-long)
Copied to clipboard
| Challenge: | Multimodal Sentiment Analysis (MSA) is a rapidly developing field that integrates multimodal information to recognize sentiments. |
| Approach: | They propose a multimodal fusion model that integrates multimodal information to recognize sentiments using multimodal transformers. |
| Outcome: | The proposed model achieves significantly higher performance than MulTs and the existing model is robust. |
Monte Carlo Tree Search Based Prompt Autogeneration for Jailbreak Attacks against LLMs (2025.coling-main)
Copied to clipboard
| Challenge: | Jailbreak attacks craft specific prompts or append adversarial suffixes to prompts, thereby inducing language models to generate harmful or unethical content and bypassing the model’s safety guardrails. |
| Approach: | They propose a Monte Carlo Tree Search (MCTS) based Prompt Auto-generation (MPA) method to generate adversarial suffixes for valid jailbreak attacks. |
| Outcome: | The proposed method outperforms existing methods on open-source and closed-source models and shows that it can generate harmful responses. |
SCA: Selective Compression Attention for Efficiently Extending the Context Window of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to compress the KV cache of large language models are expensive and limited in their context window and cost. |
| Approach: | They propose a method to expand the context window and reduce memory footprint by compressing the KV cache of large language models. |
| Outcome: | The proposed method can reduce memory footprint and expand context window of large language models without training. |
Doc-V*: Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA (2026.acl-long)
Copied to clipboard
Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai
| Challenge: | Existing OCR-free approaches to document visual question answering are brittle and passive. |
| Approach: | They propose an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation. |
| Outcome: | The proposed framework outperforms open-source and proprietary models in five benchmarks and improves out-of-domain performance by 47.9% over baseline. |
LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding (2026.acl-long)
Copied to clipboard
Zhivar Sourati, Zheng Wang, Marianne Menglin Liu, Yazhe Hu, Mengqing Guo, Sujeeth Bharadwaj, Kyu J. Han, Tao Sheng, Sujith Ravi, Morteza Dehghani, Dan Roth
| Challenge: | Conventional retrieval-augmented generation (RAG) methods encode content in isolated chunks during ingestion, losing structural and cross-page dependencies, and retrieve a fixed number of pages at inference. |
| Approach: | They propose a Layout-Aware Dynamic RAG framework that encodes content in isolated chunks during ingestion and retrieves a fixed number of pages at inference. |
| Outcome: | Experiments on MMLongBench-Doc, LongDocURL, DUDE, and MP-DoxVQA show that LAD-RAG improves retrieval, achieving over 90% perfect recall on average without any top-k tuning, and outperforming baseline retrievers by up to 20% in recall at comparable noise levels. |
VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions (2023.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for video-grounded dialogues neglect the intrinsic attributes of multimodal dialogues, such as scene and topic transitions. |
| Approach: | They propose to use a large scale video-grounded scene&topic AwaRe dialogue dataset to study video-based dialogue understanding. |
| Outcome: | The proposed dataset shows that multimodal information and segments are important in video-grounded dialogue understanding and generation. |
From Logical to Computational Sparsity: Structure-Aware Block-Sparse Attention for Long-Code Completion (2026.acl-long)
Copied to clipboard
| Challenge: | Existing sparse attention methods for long-context generation pose high latency . general sparsity methods cause excessive accuracy degradation without considering code structure . |
| Approach: | They propose a training-free **S**tructure-**a**ware **b**lock-spa**r**s**e** attention mechanism that bridges the gap between logical and computational sparsity. |
| Outcome: | The proposed method reduces TTFT by 45-55% while maintaining accuracy within 3% of dense attention. |
Mitigating Matthew Effect: Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to mitigate Matthew effect in offline recommendation systems are not effective . a number of studies have identified two root causes for the Matthew effect . |
| Approach: | They propose a framework to address the Matthew effect in conversational recommendation systems . they build hypergraphs to learn multi-level user interests to alleviate the Matthew effec . |
| Outcome: | The proposed framework achieves state-of-the-art performance on four CRS-based datasets . it improves on item-, entity-, word-oriented multiple-channel hypergraphs compared with existing methods . |
Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for enhancing recommendation quality face false negatives . only one "silly cop movie" is labeled as positive, leading to suboptimal recommendations . |
| Approach: | They propose a data augmentation framework that leverages an LLM-based semantic retriever to identify diverse and semantically relevant items and filter them by a relevance scorer to remove noisy candidates. |
| Outcome: | The proposed approach improves performance on two benchmark datasets and user simulators. |
A Framework of Reflective Agents with Adaptive Collaboration for Attributed Summary Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing prompt-based summarization approaches face limitations such as positional preference, poor citation quality and sensitivity to uninformative documents. |
| Approach: | They propose a framework of Reflective Agents with Adaptive Collaboration for attributed summarization that performs iterative summarizing via reflective agents’ collaboration. |
| Outcome: | The proposed framework outperforms baselines on the ALCE benchmark in factual correctness and citation quality. |
TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Grasping the concept of time is a fundamental facet of human cognition. |
| Approach: | They propose a hierarchical temporal reasoning benchmark that covers a broad spectrum of temporal phenomena. |
| Outcome: | The proposed benchmark shows that state-of-the-art LLMs are still far behind humans in temporal reasoning . |
PAR: Political Actor Representation Learning with Social Context and Expert Knowledge (2022.emnlp-main)
Copied to clipboard
Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Ningnan Wang, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo
| Challenge: | Existing approaches focus on textual data and voting records to induce political actors' stances. |
| Approach: | They propose a Political Actor Representation learning framework that leverages social context and expert knowledge to model ideological stances. |
| Outcome: | The proposed framework improves political text understanding and improves roll call vote prediction and political perspective detection. |
DopplerBAS: Binaural Audio Synthesis Addressing Doppler Effect (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for binaural audio synthesis are limited in phase estimation, which is crucial for spatial hearing. |
| Approach: | They propose a method to explicitly address the Doppler effect of the moving speaker . it calculates the radial relative velocity of the speaker in spherical coordinates . |
| Outcome: | The proposed method improves the representative WarpNet and BinauralGrad backbones in phase error metric and reaches a new state of the art (SOTA) it is compared with the current method which is limited in phase estimation . |
MUG: Interactive Multimodal Grounding on User Interfaces (2024.findings-eacl)
Copied to clipboard
| Challenge: | Prior studies modeled multimodal UI grounding in one round, but such an interaction is inherently iterative. |
| Approach: | They propose a task where a user and an agent collaborate on an interface screen . they use a dataset of 77,820 sequences of human user-agent interaction on mobile interfaces . |
| Outcome: | The proposed task improves the absolute task completion by 18% over the entire test set and 31% over the challenging split. |
Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have prioritized expanding the context window from which they can incorporate more information. |
| Approach: | They propose a data augmentation strategy to enable large language models to gain long-context capabilities without the need to modify existing data mixture. |
| Outcome: | The proposed model outperforms existing models on 20 billion tokens and achieves 75% and 84.5% accuracy on RULER at 128K context length. |
Enhancing Event Causality Identification with Event Causal Label and Event Pair Interaction Graph (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for event causality identification (ECI) do not consider event causal label information and interaction information between event pairs. |
| Approach: | They propose a framework to enrich the representation of event pairs by introducing the event causal label information and the interaction information between event pairs. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on two benchmark datasets. |
JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialogue Policy Learning (2024.lrec-main)
Copied to clipboard
Wai-Chung Kwan, Huimin Wang, Hongru Wang, Zezhong Wang, Bin Liang, Xian Wu, Yefeng Zheng, Kam-Fai Wong
| Challenge: | Dialogue policy learning (DPL) aims to determine an abstract representation (also known as action) to guide what the response should be. |
| Approach: | They propose a joint Transformer-based model that generates a token-grained policy that allows more dynamic dialogue action generation without the need for predefined action candidates. |
| Outcome: | The proposed model outperforms existing models showing improvements of 9% and 13% in success rate and 34% and 37% in diversity of dialogue actions across two benchmark dialogue modeling tasks. |
Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Quality Estimation (QE) is an essential role in applications of Machine Translation (MT). |
| Approach: | They propose to fuse uncertainty quantification into a pre-trained cross-lingual language model to predict the translation quality. |
| Outcome: | The proposed method achieves state-of-the-art on the datasets of WMT 2020 QE shared task. |
A Diffusion Weighted Graph Framework for New Intent Discovery (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to learn from unlabeled data generate noisy supervisory signals . current methods only rely on semantic similarities to generate supervisory signal . |
| Approach: | They propose a weighted DWGF framework to capture semantic similarities and structure relationships in data. |
| Outcome: | The proposed method outperforms state-of-the-art models on evaluation metrics across multiple benchmark datasets. |
VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck (2026.acl-long)
Copied to clipboard
| Challenge: | Existing hallucination detection methods rely on external verification tools . however, entanglement of visual-linguistic syntax and noise makes it difficult to detect hallucis . |
| Approach: | They propose a hallucination detection framework that leverages the Variational Information Bottleneck theory to detect hallucinic heads and to infer hallucication mitigation strategies. |
| Outcome: | The proposed framework outperforms baselines in hallucinations and noise detection environments. |
TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Recent work finds that realizing who holds the initiative can help select knowledge . however, there is a strong semantic transition between two rounds, probably leading to initiative misjudgment . |
| Approach: | They propose a topic-shift Aware Knowledge sElector(TAKE) model which locates relevant parts from dialogue history to improve knowledge selection. |
| Outcome: | The proposed model outperforms baseline models on the WoW. |
Noise Robust Named Entity Understanding for Voice Assistants (2021.naacl-industry)
Copied to clipboard
Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D Williams, Lin Li
| Challenge: | Named Entity Recognition and Entity Linking are challenging for voice assistants . utterances are relatively short, so there is not much context to help disambiguate . |
| Approach: | They propose a Named Entity Understanding system that combines NER and EL in a joint reranking module. |
| Outcome: | The proposed framework improves NER accuracy by up to 3.13% and EL accuracy by 3.6% in F1 score . it also leads to better accuracies in other natural language understanding tasks . |
Position: LLMs Can be Good Tutors in English Education (2025.emnlp-main)
Copied to clipboard
Jingheng Ye, Shen Wang, Deqing Zou, Yibo Yan, Kun Wang, Hai-Tao Zheng, Ruitong Liu, Zenglin Xu, Irwin King, Philip S. Yu, Qingsong Wen
| Challenge: | Recent efforts to integrate large language models into English education lack adaptability to language learning. |
| Approach: | They argue that large language models can be effective tutors in English education . they encourage interdisciplinary research to explore these roles, fostering innovation and risks . |
| Outcome: | The proposed models can play three critical roles: 1) as data enhancers, 2) as task predictors, 3) as agents, enabling personalized and inclusive education. |
Weights-Rotated Preference Optimization for Large Language Models (2025.emnlp-main)
Copied to clipboard
Chenxu Yang, Ruipeng Jia, Mingyu Zheng, Naibin Gu, Zheng Lin, Siyuan Chen, Weichong Yin, Hua Wu, Weiping Wang
| Challenge: | Existing methods to align large language models with high reward hacking are limited by the complexity of the parameter space and the complexity. |
| Approach: | They propose a weights-rotated preference optimization algorithm that constrains the output layer logits with the KL divergence inherited from DPO and fine-tunes the intermediate hidden states. |
| Outcome: | The proposed algorithm achieves a 3.27-point improvement on AlpacaEval 2 and surpasses the best baseline by 6.2 to 7.5 points on MT-Bench with merely 0.015% of the trainable parameters. |
IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce (2024.findings-emnlp)
Copied to clipboard
Wenxuan Ding, Weiqi Wang, Sze Kwok, Minghao Liu, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Junxian He, Yangqiu Song
| Challenge: | Existing approaches that distill intentions from LMs fail to generate meaningful and human-centric intentions applicable in real-world E-commerce contexts. |
| Approach: | They propose a double-task multiple-choice question answering benchmark to evaluate LMs' comprehension of purchase intentions in E-commerce. |
| Outcome: | The proposed benchmark consists of 4,360 carefully curated problems across three difficulty levels, constructed using an automated pipeline to ensure scalability on large E-commerce platforms. |
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating (2025.acl-long)
Copied to clipboard
Chao Deng, Jiale Yuan, Pi Bu, Peijie Wang, Zhong-Zhi Li, Jian Xu, Xiao-Hui Li, Yuan Gao, Jun Song, Bo Zheng, Cheng-Lin Liu
| Challenge: | Existing document understanding benchmarks only handle a small number of pages . existing models are limited to handling only a limited number of documents . |
| Approach: | They propose a long document understanding benchmark that integrates three primary tasks and 20 sub-tasks based on different primary tasks. |
| Outcome: | The proposed model outperforms existing benchmarks on open-source and closed-source models . the model outpersforms other models on more than 33,000 pages of documents . |
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development (2026.findings-acl)
Copied to clipboard
Jie Yang, Honglin Guo, Li Ji, Jiazheng Zhou, Rui Zheng, Zhikai Lei, Shuo Zhang, Zhiheng Xi, Shichun Liu, Yuxin Wang, Bo Wang, Yining Zheng, Tao Gui, Xipeng Qiu
| Challenge: | Large Language Models (LLMs) have redefined the role of AI in software engineering . current benchmarks focus on localized code generation, but neglect dynamic, full-process requirements of real-world engineering. |
| Approach: | They propose a benchmark to evaluate agentic backend coding within a realistic, executable workflow. |
| Outcome: | The ABC-Bench benchmark evaluates agentic backend coding within a realistic, executable workflow. |
LLaMA-Rider: Spurring Large Language Models to Explore the Open World (2024.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have used Large Language Models to help decision-making and planning in environments, but their capacity to acquire environmental knowledge and adapt in an open world remains uncertain. |
| Approach: | They propose an approach to spur LLMs to explore the open world, gather experiences, and learn to improve their task-solving capabilities by using a feedback-revision mechanism. |
| Outcome: | The proposed model enhances the efficiency of the LLM in exploring the open world and improves its ability to accomplish more tasks through fine-tuning with merely 1.3k instances of collected data, showing minimal training costs compared to baseline using reinforcement learning. |
Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future (2024.acl-long)
Copied to clipboard
Zheng Chu, Jingchang Chen, Qianglong Chen, Weijiang Yu, Tao He, Haotian Wang, Weihua Peng, Ming Liu, Bing Qin, Ting Liu
| Challenge: | Recent studies have revealed that chain-of-thought prompting significantly enhances LLM’s reasoning capabilities, which attracts widespread attention from both academics and industry. |
| Approach: | They propose to summarize advanced methods through a taxonomy that offers novel perspectives. |
| Outcome: | The proposed method delineates the challenges and future directions, thereby shedding light on future research. |
Helping the Weak Makes You Strong: Simple Multi-Task Learning Improves Non-Autoregressive Translators (2022.emnlp-main)
Copied to clipboard
| Challenge: | Non-autoregressive (NAR) neural machine translation models require a conditional independence assumption on target sequences, resulting in less informative learning signals. |
| Approach: | They propose a model-agnostic multi-task learning framework to provide more informative learning signals for NAR models under conventional MLE training. |
| Outcome: | The proposed framework improves accuracy of multiple NAR baselines without additional decoding overhead. |
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)
Copied to clipboard
Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si
| Challenge: | Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment. |
| Approach: | They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives. |
| Outcome: | The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering. |
Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) evolve into agentic systems capable of autonomous tool invocation and complex reasoning. |
| Approach: | They propose a trajectory-level preference benchmark to evaluate judges' ability to distinguish preferred versus distractor agent trajectories in tool-integrated environments. |
| Outcome: | The proposed benchmark evaluates how well judges distinguish preferred versus distractor agent trajectories in complex tool-using scenarios. |
A Survey on Cross-Lingual Summarization (2022.tacl-1)
Copied to clipboard
| Challenge: | Cross-lingual summarization is a task of generating a summary in one language for a given document in a different language. |
| Approach: | They present a systematic review of the literature on cross-lingual summarization . they summarize previous efforts and compare them with each other . |
| Outcome: | The proposed approach is compared with previous approaches and summarizes them to provide a deeper analysis. |
Target Really Matters: Target-aware Contrastive Learning and Consistency Regularization for Few-shot Stance Detection (2022.coling-1)
Copied to clipboard
| Challenge: | stance detection is a task to identify attitudes from opinions towards certain targets, but it is expensive and time-consuming . stance detector is based on labeled data, but unlabeled data can be collected easier . |
| Approach: | They propose a semi-supervised framework for few-shot stance detection that uses unlabeled data to learn more distinguishable representations for different targets. |
| Outcome: | The proposed framework achieves state-of-the-art performance on multiple benchmark datasets. |
Taming Language Models for Text-attributed Graph Learning with Decoupled Aggregation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to learning text-attributed graphs neglect interaction between textual and structural information. |
| Approach: | They propose a framework that integrates textual and structural information into TAG learning . they propose combining semantic aggregation and structural aggregations to improve learning a . |
| Outcome: | The proposed framework outperforms state-of-the-art learning methods while requiring less resources. |
Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for sarcasm detection ignore the incongruity character in sarcasm, which is often manifested between modalities or within modalités. |
| Approach: | They propose to capture inter-modality incongruity in a text-based model by using a self-attention mechanism and a co-attention model to model the contradiction within the text. |
| Outcome: | The proposed model achieves state-of-the-art on a public multi-modal sarcasm detection dataset. |
Massive End-to-end Speech Recognition Models with Time Reduction (2024.naacl-long)
Copied to clipboard
Weiran Wang, Rohit Prabhavalkar, Haozhe Shan, Zhong Meng, Dongseong Hwang, Qiujia Li, Khe Chai Sim, Bo Li, James Qin, Xingyu Cai, Adam Stooke, Chengjian Zheng, Yanzhang He, Tara Sainath, Pedro Moreno Mengibar
| Challenge: | Using the neural architecture of Google’s universal speech model, we reduce the frame rate and speed up training and inference. |
| Approach: | They propose to use the neural architecture of Google’s universal speech model with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference. |
| Outcome: | The proposed methods work with both connectionist temporal classification (CTC) and RNN-Transducer (RNN-T) and over two domains. |
StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)
Copied to clipboard
Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective. |
| Approach: | They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality. |
| Outcome: | The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality. |
Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models (2025.acl-long)
Copied to clipboard
Yancheng He, Shilong Li, Jiaheng Liu, Yingshui Tan, Weixun Wang, Hui Huang, Xingyuan Bu, Hangyu Guo, Chengwei Hu, Boren Zheng, Zhuoran Lin, Dekai Sun, Zhicheng Zheng, Wenbo Su, Bo Zheng
| Challenge: | Current frontier models sometimes generate false outputs or answers that are not substantiated by evidence. |
| Approach: | They propose Chinese SimpleQA, a Chinese benchmark to evaluate LLMs' factuality . they focus on Chinese language over 6 major topics with 99 diverse subtopics . |
| Outcome: | The Chinese SimpleQA benchmark evaluates the factuality ability of LLMs . the questions and answers are short and easy-to-evaluate . |
LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency (2022.coling-1)
Copied to clipboard
| Challenge: | Existing parameter-efficient methods focus on reducing trainable parameters but neglect the inference speed, which limits the ability to deploy PLMs. |
| Approach: | They propose to use a hypernetwork-assisted inter-layer connector to enhance inference efficiency by tuning parameters inside a linear connector between two Transformer layers. |
| Outcome: | The proposed model reduces model parameters to 11.75% while preserving performance degradation to less than 5%. |
Towards Faithful Multi-step Reasoning through Fine-Grained Causal-aware Attribution Reasoning Distillation (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances have witnessed large language models (LLMs) achieving significant milestones across various domains of natural language processing. |
| Approach: | They introduce fine-grained attribution reasoning distillation (FARD) which incorporates grounded citations to consolidate the relationships between reasoning steps. |
| Outcome: | The proposed method outperforms CoT distillation methods on mathematical and general reasoning benchmarks. |
LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)
Copied to clipboard
Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen
| Challenge: | a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented. |
| Approach: | They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs). |
| Outcome: | The proposed library is based on extensive experiments in a variety of evaluation settings. |
VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing quantization methods for large language models suffer performance degradation at ultra-low bit-widths due to key cache outliers. |
| Approach: | They propose a vector quantization method that suppresses outliers in the key cache and reduces memory access overhead. |
| Outcome: | The proposed method outperforms baseline quantization methods across long-context understanding and mathematical reasoning tasks while minimizing memory access overhead. |
E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for embedding mathematical expressions are limited by the size and diversity of training data. |
| Approach: | They propose an e-graph-based dataset generation scheme that synthesizes large and diverse datasets. |
| Outcome: | The proposed method outperforms state-of-the-art large language models on several tasks. |
Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to improve NAT model's performance but do not fully utilize it. |
| Approach: | They propose a non-autoregressive translation method which can obtain high-quality translations while maintaining the inference speed of NAT models. |
| Outcome: | The proposed method outperforms the autoregressive translation model on three translation tasks with 7.6 speedup. |
Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have advanced mathematical reasoning, but they still struggle with out-of-distribution (OOD) issues. |
| Approach: | They propose a framework to evaluate the logical validity of reasoning steps . they retrieves semantically similar questions and steps for PRM as a warmup . |
| Outcome: | The proposed framework outperforms baseline models on multiple real-world datasets. |
A Gradient Control Method for Backdoor Attacks on Parameter-Efficient Tuning (2023.acl-long)
Copied to clipboard
| Challenge: | Parameter-Efficient Tuning (PET) fine-tunes pre-trained language models for downstream tasks, but a large reduction in the number of attackable parameters will greatly affect the effectiveness of backdoor attacks, resulting in backdoor forgetting. |
| Approach: | They propose a gradient control method to consolidate the attack effect by freezing most parameters of the pre-trained model and fine-tuning only a small number of parameters. |
| Outcome: | The proposed method improves sentiment classification and spam detection, and can be applied to different tasks. |
Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models (2025.acl-long)
Copied to clipboard
| Challenge: | Parameter-efficient fine-tuning (PEFT) is a common method for fine- tuning large language models . however, once updated, PEFT modules suffer performance degradation on newer versions . |
| Approach: | They propose a method that enhances the PEFT module by focusing on the task-specific pattern while reducing its dependence on certain knowledge in the base model. |
| Outcome: | Experiments show that PEFT modules can maintain performance on updated models without re-tuning . the proposed approach can be used in real-world applications with large model sizes . |
Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling (2026.findings-acl)
Copied to clipboard
Zhenghua Wang, Yiran Ding, Changze Lv, Yixin Wu, Tianlong Li, Zhibo Xu, Muling Wu, Tianyuan Shi, Shizheng Li, Qi Qian, Xuanjing Huang, Xiaoqing Zheng
| Challenge: | Existing methods to address the "lost-in-the-middle" problem suffer from high latency or suboptimal hand-crafted scaling strategies. |
| Approach: | They propose a layer-specific positional embedding scaling method that assigns distinct scaling factors to each layer. |
| Outcome: | Experiments show that the proposed method mitigates positional attention bias and delivers consistent improvements across multiple long-context benchmarks. |
Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective (2025.coling-main)
Copied to clipboard
Tianlong Li, Zhenghua Wang, Wenhao Liu, Muling Wu, Shihan Dou, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) however, limited research into the underlying mechanisms that make LLMs vulnerable to such attacks has been conducted. |
| Approach: | They propose that LLMs' self-safeguarding capability is linked to specific activity patterns within their representation space. |
| Outcome: | The proposed models can be detected with a few pairs of contrastive queries, and the robustness can be manipulated by weakening or strengthening these patterns. |
Jointly Learning Entity and Relation Representations for Entity Alignment (D19-1)
Copied to clipboard
| Challenge: | Entity alignment is a viable method for integrating heterogeneous knowledge among different knowledge graphs (KGs). |
| Approach: | They propose a Graph Convolutional Network-based framework for learning relation representations by embedding relation seeds into entities and incorporating relation approximation into entities to iteratively improve alignment. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on three real-world cross-lingual datasets. |
SKGSum: Structured Knowledge-Guided Document Summarization (2024.findings-acl)
Copied to clipboard
Qiqi Wang, Ruofan Wang, Kaiqi Zhao, Robert Amor, Benjamin Liu, Jiamou Liu, Xianda Zheng, Zijian Huang
| Challenge: | Existing summarization methods ignore the importance of summary structure, resulting in summaries that emphasize the most prominent information while omitting essential details from other sections. |
| Approach: | They propose a method that uses automatically extracted summary points to generate summaries. |
| Outcome: | The proposed methods improve quality and BERTScore of summaries and broaden the types of documents that can be effectively summarized. |
Consistency Regularization for Cross-Lingual Fine-Tuning (2021.acl-long)
Copied to clipboard
Bo Zheng, Li Dong, Shaohan Huang, Wenhui Wang, Zewen Chi, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei
| Challenge: | Experimental results show that consistency regularization improves cross-lingual fine-tuning . pre-trained cross-linguistic models can transfer task-specific supervision from one language to the other . |
| Approach: | They propose to improve cross-lingual fine-tuning with consistency regularization . they use example consistency regularized to penalize prediction sensitivity to four types of data augmentations . |
| Outcome: | The proposed method improves cross-lingual fine-tuning across tasks . it can be generalized to other target languages without additional training . |
Towards Scalable Lightweight GUI Agents via Multi-role Orchestration (2026.findings-acl)
Copied to clipboard
Ziwei Wang, Junjie Zheng, Leyang Yang, Sheng Zhou, Xiaoxuan Tang, Fang Zhouhua, Zhiwei Liu, Dajun Chen, Yong Li, Jiajun Bu
| Challenge: | Advanced GUI agents suffer from prohibitive deployment costs on resource-constrained devices. |
| Approach: | They propose a lightweight GUI agent with GUI-specific knowledge and task scalability . LAMO-3B supports monolithic execution and MAS-style orchestration . |
| Outcome: | The proposed GUI agent LAMO-3B supports monolithic execution and MAS-style orchestration. |
OSCR-Attack: One-Shot Character Level Attacks through Self-Optimizing Continuous Relaxation (2026.findings-acl)
Copied to clipboard
Lingyi Kong, Zhuo Liu, Zhanghao Hu, Qilong Qiu, Yutao Yang, Jingjing Xue, Zheng Wang, Lin Gui, Feiping Nie
| Challenge: | Character-level adversarial attacks preserve semantics but are costly and inefficient . generative LLMs are gaining popularity due to their uncertainty and vulnerability to textual adversarials . |
| Approach: | They propose an end-to-end framework that transforms discrete choices into continuous representations and a conflict resolution strategy that maps them back into discrete insertion operations. |
| Outcome: | The proposed framework improves ASR by 21.45% points and accelerates the attack by 3.66 times compared to baselines. |
Slot Dependency Modeling for Zero-Shot Cross-Domain Dialogue State Tracking (2022.coling-1)
Copied to clipboard
| Challenge: | Existing zero-shot learning methods ignore slot dependencies in a multidomain dialogue . experimental results show the effectiveness of our proposed method over existing state-of-art generation methods . |
| Approach: | They propose to use slot prompts combination, slot values demonstration and slot constraint object to model slot-slot dependency, slot-value dependency and slot-context dependency respectively. |
| Outcome: | The proposed method outperforms state-of-the-art methods under zero-shot/few-shot settings. |
Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for converting large language models into powerful text encoders require extensive training on large datasets. |
| Approach: | They propose a training-free approach that enables bidirectional attention and suppresses the attention sink phenomenon, resulting in superior performance. |
| Outcome: | The proposed approach enables bidirectional attention and suppresses the attention sink phenomenon, resulting in superior performance. |
Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing vision-language models overemphasize linguistic priors, leading to modality bias. |
| Approach: | They propose a vision-language aggregation framework that mitigates modality bias in TAL by preserving vision as the dominant signal while adaptively exploiting language only when beneficial. |
| Outcome: | Experiments on THUMOS14 show that the proposed model outperforms state-of-the-art models by up to 3.2% mAP. |
Hallucination Detection for Generative Large Language Models by Bayesian Sequential Estimation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detecting hallucinations require large numbers of observations to be retrieved, increasing response times. |
| Approach: | They propose a framework that leverages Bayesian sequential analysis to optimize the trade-off between costs and benefits during the hallucination detection process. |
| Outcome: | The proposed framework surpasses existing methods in efficiency and precision of hallucination detection. |
Clear Up Confusion: Iterative Differential Generation for Fine-grained Intent Detection with Contrastive Feedback (2025.coling-main)
Copied to clipboard
| Challenge: | Recent studies on fine-grained intent detection have focused on collecting large-scale and high-quality samples via crowdsourcing resulting in data scarcity. |
| Approach: | They propose an iterative differential generation framework with contrastive feedback to generate high-quality pseudo samples and accurately capture the crucial nuances in target class distribution. |
| Outcome: | The proposed framework generates high-quality pseudo samples and captures crucial nuances in target class distribution. |
SCOTT: Self-Consistent Chain-of-Thought Distillation (2023.acl-long)
Copied to clipboard
| Challenge: | Large language models (LMs) generate free-text rationales for their predictions via chain-of-thought prompting, but there is little guarantee that the generated rationale is consistent with LM’s predictions or faithfully justify the decisions. |
| Approach: | They propose a faithful knowledge distillation method to learn a small, self-consistent CoT model from a larger teacher model by contrastive decoding. |
| Outcome: | The proposed method yields comparable performance but is less faithful than baselines. |
ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to building cross-lingual summarization systems on dialogue documents are limited. |
| Approach: | They propose a benchmark dataset for building cross-lingual summarization systems on dialogue documents. |
| Outcome: | The proposed model outperforms pipeline models on ClidSum and mDialBART. |
KEPL: Knowledge Enhanced Prompt Learning for Chinese Hypernym-Hyponym Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on hypernym-hyponym (“is-a”) relations is mostly in the English language. |
| Approach: | They propose a Knowledge Enhanced Prompt Learning method for Chinese hypernym-hyponym relation extraction using Hearst-like patterns as the prior knowledge. |
| Outcome: | The proposed method is able to extract hypernym-hyponym relations from Chinese unstructured texts using Hearst-like patterns and embed patterns and text simultaneously. |
LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025.emnlp-main)
Copied to clipboard
Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, Junbo Zhao
| Challenge: | Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL). |
| Approach: | They propose a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. |
| Outcome: | The proposed framework can boost LLMs’ reasoning ability by integrating external knowledge sources through retrieval-augmented generation (RAG) The proposed model can mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. |
ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent studies have proposed tool learning, which augments LLMs with external tools. |
| Approach: | They propose an adaptive and hierarchy-aware reranking method to refine retrieval results by truncating the retrieval result related to seen and unseen tools at different positions. |
| Outcome: | The proposed method improves retrieval results, leading to better execution results generated by the LLM. |
Using Context-to-Vector with Graph Retrofitting to Improve Word Embeddings (2022.acl-long)
Copied to clipboard
| Challenge: | Contextualized embeddings are expensive and resource-demanding, hence environmentally unfriendly. |
| Approach: | They propose a method to convert contextualized embeddings from pre-trained models into static embeddables using synonym knowledge and weighted vector distribution. |
| Outcome: | The proposed method outperforms baseline embeddings by a large margin through extrinsic and intrinsic tasks. |
ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design (2026.findings-acl)
Copied to clipboard
Yutang Ge, Guojiang Zhao, Sihang Li, Zheng Cheng, Zifeng Zhao, Hanchen Xia, Guolin Ke, Linfeng Zhang, Zhifeng Gao, Yu Guang Wang
| Challenge: | Recent deep generative models have already shown encouraging * Equal contribution. |
| Approach: | They propose to use generic instruction-tuned LLMs as direct text-to-sequence generators to achieve this goal. |
| Outcome: | Recent studies show that reflection improves sequence quality and alignment while maintaining competitive foldability. |
An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint (2025.emnlp-main)
Copied to clipboard
Yi Sun, Han Wang, Jiaqiang Li, Jiacheng Liu, Xiangyu Li, Hao Wen, Yizhen Yuan, Huiwen Zheng, Yan Liang, Yuanchun Li, Yunxin Liu
| Challenge: | Large Language Models (LLMs) are a powerful tool for test-time scaling, but they are often used under time constraints. |
| Approach: | They propose to use LLMs to make models think before answering questions . they also use self-correction and best-of-N decoding to encourage deeper thinking . |
| Outcome: | The proposed models are able to achieve higher inference accuracy with extra inference computation under time constraints. |
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning (2024.naacl-long)
Copied to clipboard
| Challenge: | Prompt tuning on a few data samples presents security issues, e.g., Trojan attacks. |
| Approach: | They propose a method to transfer established data poisoning attacks directly to few-shot prompt tuning, a technique to address the poisoned imbalance issue. |
| Outcome: | The proposed method achieves an ASR of over 99% while maintaining negligible decreases in CDA. |
M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for retrieving relevant memories from an external database are coarse-grained and can cause noise and focus on crucial memories. |
| Approach: | They propose a multiple partition paradigm for RAG where each database partition serves as a basic unit for execution. |
| Outcome: | The proposed framework outperforms baseline methods on three language generation tasks on seven datasets. |
VLEU: a Method for Automatic Evaluation for Generalizability of Text-to-Image Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing metrics, such as CLIP, measure the semantic alignment between single prompts and their corresponding images, but they fail to evaluate a model’s generalizability across a broad spectrum of textual inputs. |
| Approach: | They propose a metric that leverages the power of Large Language Models to sample from the visual text domain and assess its generalizability. |
| Outcome: | The proposed metric evaluates the generalizability of T2I models and provides valuable insights during the finetuning process. |
Mitigating Hallucinations in VLMs: Enhancing Visual Attention via Head-Wise Perturbation (2026.findings-acl)
Copied to clipboard
| Challenge: | Vision–Language Models (VLMs) have demonstrated strong capabilities in tasks that require joint understanding of text and images. |
| Approach: | They propose a strategy that incorporates head-wise attention perturbation via continuous multiplicative noise coupled with a visual-guided loss focused on vision-sensitive text tokens to promote a more balanced attention distribution. |
| Outcome: | The proposed approach outperforms baseline models on three benchmarks and consistently outperformed the baseline model. |
BeamLoRA: Beam-Constraint Low-Rank Adaptation (2025.acl-long)
Copied to clipboard
Naibin Gu, Zhenyu Zhang, Xiyu Liu, Peng Fu, Zheng Lin, Shuohuan Wang, Yu Sun, Hua Wu, Weiping Wang, Haifeng Wang
| Challenge: | Low-Rank Adaptation (LoRA) is one of the most efficient parameter-efficient fine-tuning methods. |
| Approach: | They propose to conceptualize each LoRA module as a beam where each rank corresponds to a potential sub-solution. |
| Outcome: | The proposed method improves performance on three base models and 12 datasets. |
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis (2025.findings-emnlp)
Copied to clipboard
Shuang Sun, Huatong Song, Yuhao Wang, Ruiyang Ren, Jinhao Jiang, Junjie Zhang, Fei Bai, Jia Deng, Xin Zhao, Zheng Liu, Lei Fang, Zhongyuan Wang, Ji-Rong Wen
| Challenge: | Existing approaches to deep search training lack high-quality training trajectories, prohibitive computational costs and lack of high-fidelity training data. |
| Approach: | They propose a framework that synthesizes high-quality training data by simulating real user interactions in live web search environments. |
| Outcome: | The proposed framework synthesizes high-quality training data by simulating user interactions in live web search environments. |
COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)
Copied to clipboard
Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang
| Challenge: | Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns. |
| Approach: | They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users. |
| Outcome: | The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks. |
GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents (2026.acl-long)
Copied to clipboard
Yunzhe Wang, Runhui Xu, Kexin Zheng, Tianyi Zhang, Jayavibhav Niranjan Kogundi, Soham Hans, Volkan Ustun
| Challenge: | Multimodal Large Language Models are emerging as a backbone for autonomous agents in 3D environments. |
| Approach: | They propose a framework for evaluating agentic-centric perception and reasoning through video understanding. |
| Outcome: | The proposed framework evaluates agentic-centric perception and reasoning through video understanding. |
EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models (2025.emnlp-demos)
Copied to clipboard
Ziwen Xu, Shuxun Wang, Kewei Xu, Haoming Xu, Mengru Wang, Xinle Deng, Yunzhi Yao, Guozhou Zheng, Huajun Chen, Ningyu Zhang
| Challenge: | Large Language Models (LLMs) have demonstrated extraordinary capabilities, however, they may still generate unreliable or unsafe outputs. |
| Approach: | They propose a framework that allows plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. |
| Outcome: | The framework is designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. |
M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)
Copied to clipboard
Jiaheng Liu, Ken Deng, Congnan Liu, Jian Yang, Shukai Liu, He Zhu, Peng Zhao, Linzheng Chai, Yanan Wu, JinKe JinKe, Ge Zhang, Zekun Moore Wang, Guoan Zhang, Yingshui Tan, Bangyu Xiang, Zhaoxiang Zhang, Wenbo Su, Bo Zheng
| Challenge: | Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities . |
| Approach: | They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models. |
| Outcome: | The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree. |
Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing research on multi-modal Named Entity Recognition (MNER) does not integrate all multi-modal representations to provide rich contextual information to improve NER. |
| Approach: | They propose an iterative reasoning framework that integrates all the diverse multi-modal representations following the strategy of "decompose, prioritize, and eliminate" . they propose to use hierarchically connected fusion layers to prioritize transitions from "easy-to-hard" and "coarse-to fine" |
| Outcome: | The proposed framework integrates all the diverse multi-modal representations following the strategy of "decompose, prioritize, and eliminate". |
AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models are increasingly used to automate data analysis, but data science tasks often admit multiple statistically valid solutions. |
| Approach: | They propose a framework to evaluate LLM-generated code and assess its reproducibility . they introduce two reproducibility-enhancing prompting strategies and benchmark them against standard prompting . |
| Outcome: | The proposed framework improves reproducibility of large language models . it provides a foundation for transparent, reliable, and efficient human–AI collaboration in data science. |
Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for converting visual tokens into tokens are limited by their high volume . et al., 2023; Zheng e.t., 2023): a revolution in video understanding. |
| Approach: | They propose a language-aware dynamic token compression system that converts video clips into soft caption tokens as visual representations. |
| Outcome: | The proposed method reduces FLOPs by 49% while maintaining competitive performance. |
Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation (2020.acl-main)
Copied to clipboard
| Challenge: | Fully supervised neural approaches have achieved significant progress in the task of Chinese word segmentation (CWS) however, they suffer from the cross-domain issue when they come to processing of out-of-domain data. |
| Approach: | They propose to use Chinese word as a target domain for distant annotation and adversarial training to reduce noise and maximize utilization of the source domain information. |
| Outcome: | The proposed method outperforms existing state-of-the-art methods on real-world datasets and significantly outperformed previous state- of-the art methods. |
CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models (2025.naacl-long)
Copied to clipboard
Ying Nie, Binwei Yan, Tianyu Guo, Hao Liu, Haoyu Wang, Wei He, Binfan Zheng, Weihao Wang, Qiang Li, Weijian Sun, Yunhe Wang, Dacheng Tao
| Challenge: | Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging task like finance, has not been fully explored. |
| Approach: | They propose a benchmark to assess the financial knowledge of large language models (LLMs) in China. |
| Outcome: | The proposed benchmark is the most comprehensive evaluation benchmark to date for LLMs in finance. |
My Words Imply Your Opinion: Reader Agent-Based Propagation Enhancement for Personalized Implicit Emotion Analysis (2025.acl-long)
Copied to clipboard
| Challenge: | Current studies personalize emotion analysis by focusing on the author but neglect the impact of the intended reader on implicit emotional feedback. |
| Approach: | They propose a model which incorporates reader feedback into implicit emotion analysis (IEA) they use large language models to create reader agents to simulate reader feedback . |
| Outcome: | The proposed model outperforms state-of-the-art models in a text-centric environment. |
Social-aware Sparse Attention Network for Session-based Social Recommendation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for predicting the next item for an anonymous session do not capture user preferences and noisy irrelevant interactions. |
| Approach: | They propose to use social networks and historical sessions to provide personalized recommendations for the current session. |
| Outcome: | The proposed model outperforms existing models on two benchmark datasets. |
LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendation (2025.findings-emnlp)
Copied to clipboard
Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, Hongwei Li
| Challenge: | Traditional contrastive learning methods treat negative feedback as equally hard or easy, ignoring informative semantic difficulty during training. |
| Approach: | They propose a framework leveraging Large Language Models to Activate interactions in Graph Contrastive Learning for Recommendation. |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks on multiple benchmarks. |
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks (2026.acl-long)
Copied to clipboard
Wenqi Zhang, Mengna Wang, Gangao Liu, Huixin Xu, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Jiajun Liu, Weiming Lu, Peng Li, Yueting Zhuang
| Challenge: | Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks, but their effectiveness in embodied domains remains largely unexplored. |
| Approach: | They propose a reasoning model for interactive embodied tasks that synthesizes 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes. |
| Outcome: | The proposed model outperforms existing visual reasoning models by +9%, 24%, and +13% on long-horizon tasks. |
BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering (2024.acl-long)
Copied to clipboard
Zheng Chu, Jingchang Chen, Qianglong Chen, Haotian Wang, Kun Zhu, Xiyuan Du, Weijiang Yu, Ming Liu, Bing Qin
| Challenge: | Large language models (LLMs) have demonstrated strong reasoning capabilities, but they still suffer from factual errors when tackling knowledge-intensive tasks. |
| Approach: | They propose a reasoning framework for knowledge-intensive multi-hop QA that prioritizes promising answers at each hop of question. |
| Outcome: | The proposed framework outperforms SOTA methods on four open-domain multi-hop reasoning datasets by 8.5%. |
Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization (2023.findings-acl)
Copied to clipboard
| Challenge: | Current speaker diarization systems consider only acoustic information, resulting in performance degradation when encountering adverse acustic environment. |
| Approach: | They propose methods to extract speaker-related information from conversational semantics in multi-party meetings. |
| Outcome: | The proposed method improves on AISHELL-4 and AliMeeting datasets on speakers diarization and speaker-turn detection. |
SessionIntentBench: A Multi-task Inter-session Intention-shift Modeling Benchmark for E-commerce Customer Behavior Understanding (2026.findings-acl)
Copied to clipboard
Yuqi Yang, Weiqi Wang, Baixuan Xu, Wei Fan, Qing Zong, Chunkit Chan, Zheye Deng, Xin Liu, Yifan Gao, Changlong Yu, Chen Luo, Yang Li, Zheng Li, Qingyu Yin, Bing Yin, Yangqiu Song
| Challenge: | Existing models fail to capture and model customer intention effectively because of insufficient information exploitation and only apparent information like descriptions and titles are used. |
| Approach: | They propose to exploit existing session data to capture and model intention in E-commerce product purchase sessions using a multimodal benchmark. |
| Outcome: | The proposed framework can bridge the gap between intention understanding in simplified research cases like co-buy intention and more complex yet practical scenarios like session history. |
FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery (2023.findings-acl)
Copied to clipboard
Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Song, Zheng Li, Yifan Gao, Tianyu Cao, Bing Yin
| Challenge: | Existing intention-based studies on recommendation tasks are limited and use models to implicitly model the intention memberships. |
| Approach: | They propose a framework that leverages the generation power of large language models and human-in-the-loop annotation to semi-automatically construct the intention knowledge graph. |
| Outcome: | The proposed framework can model e-commerce knowledge and have many potential applications. |
Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency (2025.acl-long)
Copied to clipboard
Jiafeng Liang, Shixin Jiang, Xuan Dong, Ning Wang, Zheng Chu, Hui Su, Jinlan Fu, Ming Liu, See-Kiong Ng, Bing Qin
| Challenge: | Large Multimodal Models (LMMs) have demonstrated impressive performance on general video comprehension benchmarks, but their robustness needs to be thoroughly investigated for broader applications. |
| Approach: | They propose a temporal robustness benchmark which introduces temporal inconsistency perturbations separately at the visual and textual modalities to assess the robustness of models. |
| Outcome: | The proposed method improves the model’s robustness and reliability in temporal analysis. |
Rethinking Word-level Adversarial Attack: The Trade-off between Efficiency, Effectiveness, and Imperceptibility (2024.lrec-main)
Copied to clipboard
| Challenge: | Neural language models have demonstrated impressive performance but remain vulnerable to word-level adversarial attacks. |
| Approach: | They propose two standardized search spaces to address the problem of word-level adversarial attacks. |
| Outcome: | The proposed search spaces improve performance and trade-offs in different scenarios. |
OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)
Copied to clipboard
Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou
| Challenge: | Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs. |
| Approach: | They propose a framework that integrates dialogue, reasoning, and personalized recommendation. |
| Outcome: | Experiments across public benchmarks show state-of-the-art performance. |
VC4VG: Optimizing Video Captions for Text-to-Video Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in text-to-video generation highlight the critical role of high-quality video-text pairs in training models capable of producing coherent and instruction-aligned videos. |
| Approach: | They propose a caption optimization framework tailored to the needs of T2V models. |
| Outcome: | The proposed framework improves video caption quality and video generation performance. |
NavA3: Understanding Any Instruction, Navigating Anywhere, Finding Anything (2026.acl-long)
Copied to clipboard
Lingfeng Zhang, Xiaoshuai Hao, Yingbo Tang, Haoxiang Fu, Xinyu Zheng, Pengwei Wang, Zhongyuan Wang, Wenbo Ding, Shanghang Zhang
| Challenge: | Existing embodied navigation methods struggle with such tasks due to their limitations in comprehending high-level human instructions and localizing objects with an open vocabulary. |
| Approach: | They propose a hierarchical framework for long-horizon navigation that integrates human instructions with 3D scene views. |
| Outcome: | The proposed model achieves SOTA results and can complete long-horizon navigation tasks across different robot embodiments in real-world environments. |
Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation (2023.emnlp-main)
Copied to clipboard
Chenxu Yang, Zheng Lin, Lanrui Wang, Chong Tian, Liang Pang, Jiangnan Li, Qirong Ho, Yanan Cao, Weiping Wang
| Challenge: | Existing knowledge-grounded dialogue generation models struggle with dull and repetitive outputs, a problem commonly termed as text degeneration. |
| Approach: | They propose a framework that allows the model to "cheat" the objective by duplicating knowledge segments in a superficial pattern matching based on overlap. |
| Outcome: | The proposed framework can be applied to a WoW dataset and shows that it works across models and decoding strategies. |
CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation (2025.emnlp-main)
Copied to clipboard
Ziyue Liu, Ruijie Zhang, Zhengyang Wang, Mingsong Yan, Zi Yang, Paul D. Hovland, Bogdan Nicolae, Franck Cappello, Sui Tang, Zheng Zhang
| Challenge: | Large foundation models have become huge, but they consume computational resources in pretraining. |
| Approach: | They propose to replace full-size layers with compute-efficient auto-encoders that enforce low-rank activations throughout training. |
| Outcome: | The proposed method reduces the computing cost by 2pmbtimes and improves training throughput by 1.86pmtime. |
Investigating Human and LLMs’ Decisions in Unverifiable Environments: A Case Study with GitHub Activity Overview (2026.findings-acl)
Copied to clipboard
| Challenge: | examining the behaviors of Large Language Models as artificial social actors is underexplored, especially in unverifiable scenarios where conventional benchmarking has little to help improve their abilities. |
| Approach: | They propose a method to collect, compare, and reason about human and LLMs' decisions in an unverifiable scenario and use it to examine their behaviors. |
| Outcome: | The proposed method compared human and LLM decisions in an unverifiable scenario on GitHub and found that proprietary LLMs behave more like humans than open-source LLM systems. |
SoulChat: Improving LLMs’ Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are used in psychological counseling to provide universal advice. |
| Approach: | They constructed a multi-turn empathetic conversation dataset with 2 million samples . they found that the model's empathy ability is enhanced when finetuning . |
| Outcome: | Experiments show that large language models can be finetuned to provide empathy . but, when applied to mental health or emotional support conversation, there are three main issues . |
Measure Children’s Mindreading Ability with Machine Reading (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing scoring models do not take the features of the stories and video clips into account when scoring, which will reduce the accuracy of the models. |
| Approach: | They propose to leverage the features extracted from stories and videos related to the questions being asked during the children’s mindreading evaluation. |
| Outcome: | The proposed framework agrees well with human experts on scores produced by the models. |
ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs (2026.acl-long)
Copied to clipboard
Hongxin Ding, Baixiang Huang, Yue Fang, Weibin Liao, Xinke Jiang, Jinyang Zhang, Yinghao Zhu, Zheng Li, Liantao Ma, Junfeng Zhao, Yasha Wang
| Challenge: | Existing medical Large Language Models (LLMs) follow a reactive paradigm, risking diagnostic errors by answering before seeking sufficient details. |
| Approach: | They propose a reinforcement learning framework that transitions LLMs toward a proactive paradigm, enabling them to ask clinically valuable questions before decision-making. |
| Outcome: | Experiments on partial-information medical benchmarks show that ProMed outperforms state-of-the-art methods by 6.29% on average and delivers a 54.45% gain over the reactive paradigm. |
Verifiable Format Control for Large Language Model Generations (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods focus on benchmarking general instruction following while overlooking how to improve specific format following ability for small LLMs. |
| Approach: | They propose to synthesize massive datasets to improve LLMs' format following abilities by using a verifiable format following feature. |
| Outcome: | The proposed method improves the format following ability of small LLMs with about 7B parameters. |
Safely Learning with Private Data: A Federated Learning Framework for Large Language Model (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing large language models (LLMs) use large amounts of public data and massive parameters, but private data is often stored in isolated data silos. |
| Approach: | They propose a Federated Learning framework for large language models which offloads most training parameters to the server while training embedding and output layers locally. |
| Outcome: | The proposed framework achieves comparable metrics to centralized chatGLM model on NLU and generation tasks. |
Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA (2022.findings-emnlp)
Copied to clipboard
Qingyi Si, Fandong Meng, Mingyu Zheng, Zheng Lin, Yuanxin Liu, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou
| Challenge: | Visual Question Answering (VQA) models are prone to learn the shortcut solution formed by dataset biases rather than the intended solution. |
| Approach: | They propose a dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets. |
| Outcome: | The proposed dataset considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets. |
SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities in machine translation, but most MT-specific LLMs rely heavily on external supervision during training. |
| Approach: | They propose a reinforcement learning framework for machine translation that is reference-free and relies solely on self-judging rewards. |
| Outcome: | The proposed framework outperforms existing LLMs and larger general LLM models on English Chinese translation benchmarks and performs competitively with leading closed-source systems. |
What Factors Influence LLMs’ Judgments? A Case Study on Question Answering (2024.lrec-main)
Copied to clipboard
Lei Chen, Bobo Li, Li Zheng, Haining Wang, Zixiang Meng, Runfeng Shi, Hao Fei, Jun Zhou, Fei Li, Chong Teng, Donghong Ji
| Challenge: | Existing studies indicate that Large Language Models perform at a level comparable to humans with advantages of speed and cost-effectiveness in different fields. |
| Approach: | They propose to introduce four unexplored factors and a new dimension of question difficulty to provide a more comprehensive understanding of LLMs’ judgments across varying question intricacies. |
| Outcome: | The proposed dimensions of question difficulty and answer quantity provide valuable insights into optimizing LLMs’ performance as judges. |
Fusion or Defusion? Flexible Vision-and-Language Pre-Training (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to vision-and-language pretraining (VLP) lack effectiveness and efficiency in downstream multimodal tasks. |
| Approach: | They propose a flexible vision-and-language pre-training model by incorporating cross-modal fusions into a dual-encoder architecture and a cross-module knowledge transfer strategy to guide the training process. |
| Outcome: | The proposed model is well-equipped with effectiveness and efficiency compared with other strong VLP models. |
ProgCo: Program Helps Self-Correction of Large Language Models (2025.acl-short)
Copied to clipboard
| Challenge: | Existing LLMs fail to self-correct and generate correct feedback, leading to misleading refinement and failure of self-refinement. |
| Approach: | They propose a program-driven self-correction approach that uses program-based verification to self-refine initial responses without external feedback. |
| Outcome: | The proposed model achieves self-correction and can be further enhanced when combined with real program tools. |
Improving Adversarial Text Generation by Modeling the Distant Future (2020.acl-main)
Copied to clipboard
Ruiyi Zhang, Changyou Chen, Zhe Gan, Wenlin Wang, Dinghan Shen, Guoyin Wang, Zheng Wen, Lawrence Carin
| Challenge: | Recent work has shown excellent performance on text generation tasks by combining reinforcement learning (RL) and generative models. |
| Approach: | They propose a model-based imitation-learning approach to improve text generation performance by focusing on a long horizon. |
| Outcome: | The proposed model improves on a number of text-generation tasks and provides intermediate rewards for generator optimization. |
A Predicate-Function-Argument Annotation of Natural Language for Open-Domain Information eXpression (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing OIE (Open Information Extraction) algorithms are redundant and not reusable. |
| Approach: | They propose a pipeline where an Open-domain Information eXpression task provides a platform for all OIE strategies. |
| Outcome: | The proposed pipeline provides a platform for all OIE strategies. |
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)
Copied to clipboard
Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang
| Challenge: | Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction. |
| Approach: | They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack. |
| Outcome: | The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses. |
The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Games (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches focus on information processing and strategy selection, overlooking the significance of persuasive communication in social deduction games. |
| Approach: | They propose a reinforcement learning framework that trains agents to optimize influential utterances for persuasive impact by formalizing turn-based dialogue as a Stackelberg competition . |
| Outcome: | The proposed framework outperforms baselines across four social deduction benchmarks and shows that it is effective in persuasive communication. |
Prompt Combines Paraphrase: Teaching Pre-trained Models to Understand Rare Biomedical Words (2022.coling-1)
Copied to clipboard
Haochun Wang, Chi Liu, Nuwa Xi, Sendong Zhao, Meizhi Ju, Shiwei Zhang, Ziheng Zhang, Yefeng Zheng, Bing Qin, Ting Liu
| Challenge: | Pre-trained models perform poorly with limited data and rare biomedical words. |
| Approach: | They propose to use prompt to fine-tune pre-trained models for biomedical domain tuning with a simple approach. |
| Outcome: | The proposed method achieves up to 6% improvement in biomedical natural language inference task without any extra parameters or training steps using few-shot vanilla prompt settings. |
AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use (2026.acl-industry)
Copied to clipboard
| Challenge: | Modern industrial applications increasingly demand language models capable of multi-step reasoning and tool use in real-world settings. |
| Approach: | They propose a model family that trains via multi-round reinforcement learning on synthetic data and open-source data. |
| Outcome: | The proposed model train on synthetic and open-source data achieves strong performance on multiple agentic benchmarks and in an industrial agent system. |
Improving Continual Pre-training Through Seamless Data Packing (2025.findings-acl)
Copied to clipboard
| Challenge: | Empirical evaluations across various model architectures and corpus domains demonstrate the effectiveness of our method, outperforming baselines in 99% of all settings. |
| Approach: | They propose a method that uses a sliding window technique to pack data before continual pre-training to preserve contextual information and enhance model performance. |
| Outcome: | Empirical evaluations across various model architectures and corpus domains demonstrate the effectiveness of the proposed method outperforming baselines in 99% of settings. |
Combo of Thinking and Observing for Outside-Knowledge VQA (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to visual question answering use external knowledge to acquire and use knowledge beyond images. |
| Approach: | They propose to constrain the cross-modality space into the same space of natural-language space . they propose a multimodal encoder, textual encoder and answer decoder to introduce more types of knowledge . |
| Outcome: | The proposed framework outperforms the state-of-the-art by 6.17% accuracy on a cross-modal space and natural-language space. |
Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning? (2025.acl-long)
Copied to clipboard
Yancheng He, Shilong Li, Jiaheng Liu, Weixun Wang, Xingyuan Bu, Ge Zhang, Z.y. Peng, Zhaoxiang Zhang, Zhicheng Zheng, Wenbo Su, Bo Zheng
| Challenge: | Recent advances in o1-like models have generated long Chain-of-Thought reasoning steps to improve the reasoning abilities of existing Large Language Models (LLMs). |
| Approach: | They propose a DeltaBench to analyze the quality and effectiveness of o1-like models and measure their ability to detect errors in long COT reasoning. |
| Outcome: | The proposed model can detect errors in long COT reasoning. |
Seek-and-Solve: Benchmarking MLLMs for Visual Clue-Driven Reasoning in Daily Scenarios (2026.findings-acl)
Copied to clipboard
Xiaomin Li, Tala Wang, Zichen Zhong, Ying Zhang, Zirui Zheng, Takashi Isobe, Dezhuang Li, Huchuan Lu, You He, Xu Jia
| Challenge: | Existing benchmarks focus on evaluating MLLMs’ pre-existing knowledge or perceptual understanding, often neglecting the critical capability of reasoning. |
| Approach: | They propose a benchmark designed for visual clue-driven reasoning in daily scenarios that combines rigorous grounding in authentic daily activities and challenging query design that necessitates more than surface-level perception. |
| Outcome: | The proposed benchmark identifies visual clues and their ability to provide robust reasoning in daily scenarios. |
Compressing and Debiasing Vision-Language Pre-Trained Models for Visual Question Answering (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on VQA models have found that they suffer from dataset biases and inefficient memory footprints. |
| Approach: | They investigate whether a VLP can be compressed and debiased simultaneously by searching sparse and robust subnetworks. |
| Outcome: | The proposed compression and debiasing pipelines outperform the debiased full VLPs on VQA tasks. |
SCOUT: Selective Coupling via Optimal Unbalanced Transport for Interpretable Text Classification (2026.acl-long)
Copied to clipboard
| Challenge: | Standard interpretable models often rely on scalar similarities that obscure the true evidentiary basis of a prediction. |
| Approach: | They propose a new paradigm that grounds prototype reasoning in the selective correspondence of discriminative fragments. |
| Outcome: | The proposed model outperforms rationale extraction and post-hoc attribution methods on seven benchmarks. |
MTGER: Multi-view Temporal Graph Enhanced Temporal Reasoning over Time-Involved Document (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work models time implicitly, making it difficult to handle complex relationships . a novel temporal reasoning framework explicitly models the temporal relationships among facts by multi-view temporal graphs . |
| Approach: | They propose a multi-view temporal graph-based temporal reasoning framework that explicitly models the temporal relationships among facts by multi-visit temporal charts. |
| Outcome: | The proposed framework gives more consistent answers under question perturbations. |
AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing (2023.findings-acl)
Copied to clipboard
Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, Abbas Ghaddar
| Challenge: | Developing monolingual large Pre-trained Language Models (PLMs) is shown to be very successful in handling different tasks in Natural Language Processing (NLP). |
| Approach: | They present AraMUS, the largest Arabic PLM with 11B parameters trained on 529GB of high-quality Arabic textual data. |
| Outcome: | The proposed model achieves state-of-the-art performance on a diverse set of Arabic classification and generative tasks. |
Promoting Data and Model Privacy in Federated Learning through Quantized LoRA (2024.findings-emnlp)
Copied to clipboard
Zhu JianHao, Changze Lv, Xiaohua Wang, Muling Wu, Wenhao Liu, Tianlong Li, Zixuan Ling, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Existing federated learning frameworks require substantial data and computational resources to develop large language models. |
| Approach: | They propose a method that distributes a quantized version of the model’s parameters during training and combine it with a popular fine-tuning method to significantly reduce communication costs. |
| Outcome: | The proposed method enables accurate estimations for parameter updates while preventing clients from accessing a model whose performance is comparable to the centrally hosted one. |
ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models (2022.naacl-main)
Copied to clipboard
Junyi Li, Tianyi Tang, Zheng Gong, Lixin Yang, Zhuohao Yu, Zhipeng Chen, Jingyuan Wang, Xin Zhao, Ji-Rong Wen
| Challenge: | Recent years have featured a trend towards Transformer based pretrained language models (PLMs) in natural language processing systems. |
| Approach: | They propose to use four evaluation dimensions to evaluate ten widely-used PLMs . they find that pretrained language models are good at different ability tests . |
| Outcome: | The results show that pretrained language models are good at different ability tests and have excellent transferability between tasks. |
CoDA: Restoring Contextual Dominance via Copy-Encouraged Attention Intervention for Mitigating RAG Hallucinations (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-augmented generation reduces hallucination by grounding outputs in external evidence. |
| Approach: | They propose a lightweight inference-time attention intervention that amplifies evidence-aligned value states to enhance contextual faithfulness and reduce hallucination. |
| Outcome: | The proposed model reduces hallucination by grounding model outputs in external evidence. |
MaRF: Leveraging Representation-Level Fusion of Formula Semantics for Mathematical Information Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Mathematical information retrieval (MIR) relies on combining textual content with mathematical expressions. |
| Approach: | They propose a dual-encoder representation-level fusion framework for MIR that integrates formula semantics into context-aware dense retrieval. |
| Outcome: | The proposed framework outperforms baselines on the ARQMath-3 benchmark. |
DisCo: Distilled Student Models Co-training for Semi-supervised Text Mining (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing text mining models are fine-tuned by fine-timing a large pre-trained language model (PLM) in downstream tasks. |
| Approach: | They propose a semi-supervised learning framework for fine-tuning a cohort of small student models generated from a large pre-trained language model using knowledge distillation. |
| Outcome: | The proposed framework outperforms baseline models on semi-supervised text classification and extractive summarization tasks while maintaining comparable performance. |
LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering (2025.acl-short)
Copied to clipboard
Zhifan Ye, Zheng Wang, Kejing Xia, Jihoon Hong, Leshu Li, Lexington Whalen, Cheng Wan, Yonggan Fu, Yingyan Celine Lin, Souvik Kundu
| Challenge: | Recent work attributes performance degradation to an exponential decay in hidden-state memory. |
| Approach: | They propose a token filtering strategy that is training-free and attention-guided . they propose 'LAMB' to preserve critical tokens during inference . |
| Outcome: | The proposed token filtering improves long-context performance by 30.35% over state-of-the-art methods on benchmarks. |
Enhancing Semantics in Multimodal Chain of Thought via Soft Negative Sampling (2024.lrec-main)
Copied to clipboard
| Challenge: | Chain of thought (CoT) is used for complex reasoning problems, but hallucinations are a problem in multimodal CoT. |
| Approach: | They propose a method to generate soft negative samples with different semantics to mitigate hallucinations in multimodal CoT. |
| Outcome: | The proposed method mitigates hallucinations in multimodal CoT by using soft negative sampling. |
CLEVA: Chinese Language Models EVAluation Platform (2023.emnlp-demo)
Copied to clipboard
Yanyang Li, Jianqiao Zhao, Duo Zheng, Zi-Yuan Hu, Zhi Chen, Xiaohui Su, Yongfeng Huang, Shijia Huang, Dahua Lin, Michael Lyu, Liwei Wang
| Challenge: | Large language models (LLMs) have revolutionized natural language processing. |
| Approach: | They propose a Chinese-based platform that assesses Chinese LLMs using a standardized workflow and a unique sampling strategy. |
| Outcome: | CLEVA evaluates Chinese LLMs on a standardized workflow and a competitive leaderboard with minimal coding. |
Example Quality Matters: Multi-Aspects Example Augmentation for Private Library Programming (2026.acl-long)
Copied to clipboard
Yuhao Li, Haifeng Sun, Xuesong Zhang, Shu Yao, Haoyu Zheng, Yvchuan Wang, Huazheng Wang, Zirui Zhuang, Qi Qi, Jianxin Liao, Jingyu Wang
| Challenge: | Existing approaches to code generation fail to consider the quality of retrieved examples. |
| Approach: | They propose a retrieval-augmented generation method that combines existing API examples to improve complexity and readability. |
| Outcome: | The proposed method achieves up to 22% accuracy improvement over baseline methods. |
Model Extrapolation Expedites Alignment (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve LLM alignment training require expensive computational resources. |
| Approach: | They propose a model extrapolation method to expedite LLMs’ alignment with human preferences by amplifying parameter changes based on a first-order approximation without any additional training overhead. |
| Outcome: | The proposed method outperforms a fully-trained model on leading benchmarks and significantly outperformed open-source models. |
CBP-Tuning: Efficient Local Customization for Black-box Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Customized black-box prompt tuning is a new approach to customize large language models . however, as models grow, the resources required for training and deployment become increasingly expensive . |
| Approach: | They propose a framework that facilitates efficient local customization while preserving bidirectional privacy. |
| Outcome: | The proposed framework facilitates efficient local customization while preserving bidirectional privacy. |
Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs (2025.findings-emnlp)
Copied to clipboard
Yu Yan, Sheng Sun, Zhe Wang, Yijun Lin, Zenghao Duan, Zhifei Zheng, Min Liu, Zhiyi Yin, Jianping Zhang
| Challenge: | Large Language Models have been developed to deal with real-world crimes, but it remains unclear whether they internalize authentic knowledge or are forced to simulate toxic language patterns. |
| Approach: | They construct knowledge-intensive Q&A to investigate misuse threats of Large Language Models in terms of dangerous knowledge possession, harmful task planning utility, and harmfulness judgment robustness. |
| Outcome: | The findings raise concerns that jailbreak success is often attributable to a hallucination loop between jailbroken LLM and judger LLM . |
M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have shown their potential to deliver human-like judgments. |
| Approach: | They propose a systematic LLM-based multi-agent framework for advanced LLM as-a-judge MT evaluation that integrates dimension-specific results into a final evaluation judgment. |
| Outcome: | The proposed framework outperforms existing LLM-as-a-judge methods and competes with state-of-the-art automatic metrics even when powered by a suboptimal model like GPT-4o mini. |
Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training (2026.acl-long)
Copied to clipboard
Jihao Gu, Qihang Ai, Yingyao Wang, Pi Bu, Jingxuan Xing, Yue Cao, Zekun Zhu, Wei Jiang, Ziming Wang, Yingxiu Zhao, Ming-Liang Zhang, Jun Song, Yuning Jiang, Bo Zheng
| Challenge: | Existing approaches to training agents for visual-language models trap them in local optima, hindering exploration and error correction with the environment. |
| Approach: | They propose a hierarchical training recipe that bridges atomic action execution and strategic task completion. |
| Outcome: | The proposed training recipe bridges atomic action execution and strategic task completion. |
Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have explored compression and accumulation methods to compress contexts, but these methods lose useful context information during the compression process, leading to performance degradation. |
| Approach: | They propose a method that allows LLMs to take a deep breath and insert a special token at the end of each chunk. |
| Outcome: | Experiments on language modeling and out-of-domain tasks validate the superiority of the proposed method. |
R2H: Building Multimodal Navigation Helpers that Respond to Help Requests (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing dialog-based embodied datasets are not sufficient to develop intelligent navigation-helper agents capable of navigating users in unfamiliar areas. |
| Approach: | They introduce a novel benchmark, Respond to Help Requests, to promote the development of multi-modal navigation helpers capable of responding to requests for help . they also propose two approaches to construct the navigation-helper agent, including fine-tuning a task-oriented multi-mod response generation model that can see and respond, named SeeRee, and employing . a multi-module large language model in a zero-shot manner. |
| Outcome: | The proposed model outperforms the baseline model and the proposed model on two tasks based on human evaluations and automatic benchmarking. |
Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human–Agent Interaction (2026.acl-long)
Copied to clipboard
Zisu Huang, Muzhao Tian, Xiaohua Wang, Jingwen Xu, Zhengkang Guo, Qi Qian, Kaitao Song, Jiakang Yuan, Changze Lv, Xiaoqing Zheng
| Challenge: | Existing systems that use memory as an "all-or-nothing" approach to memory usage are often static and rely on experience-following tendencies. |
| Approach: | They propose a framework that allows users to dynamically regulate memory reliance by adding context into the model's prompt. |
| Outcome: | The proposed model outperforms prompting and memory masking strategies in multiple scenarios. |
The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking (2022.findings-acl)
Copied to clipboard
Yinghui Li, Qingyu Zhou, Yangning Li, Zhongli Li, Ruiyang Liu, Rongyi Sun, Zizhen Wang, Chao Li, Yunbo Cao, Hai-Tao Zheng
| Challenge: | Chinese Spell Checking (CSC) aims to detect and correct spelling errors, which are caused by the phonological or visual similarity. |
| Approach: | They propose an Error-driven COntrastive Probability Optimization framework to refine the knowledge representations of pre-trained language models to avoid predicting common characters. |
| Outcome: | Extensive experiments and detailed analyses on SIGHAN datasets demonstrate that ECOPO is simple yet effective. |
MKeCL: Medical Knowledge-Enhanced Contrastive Learning for Few-shot Disease Diagnosis (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to disease classification are limited in real-world clinics due to insufficient data and inflexibility. |
| Approach: | They propose a medical knowledge-Enhanced Contrastive Learning approach to disease diagnosis . they incorporate medical knowledge graphs and medical licensing exams in modeling . |
| Outcome: | The proposed model outperforms existing models on real clinical EMRs on a single patient. |