Papers by Lu Chen
TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method (2022.emnlp-main)
Copied to clipboard
Zeqian Ju, Peiling Lu, Xu Tan, Rui Wang, Chen Zhang, Songruoyao Wu, Kejun Zhang, Xiang-Yang Li, Tao Qin, Tie-Yan Liu
| Challenge: | a new lyric-to-melody generation system bridges the gap between lyrics and melodies . previous generation systems lack paired data and lack of control on generated melodie. |
| Approach: | They develop a lyric-to-melody generation system with music template to bridge the gap between lyrics and melodies. |
| Outcome: | The proposed system bridges the gap between lyrics and melodies by using music template. |
Lifelong Learning of Topics and Domain-Specific Word Embeddings (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing lifelong topic models focus on indomain text streams in which each chunk only contains documents from a single domain. |
| Approach: | They develop a lifelong collaborative model that uses non-negative matrix factorization to learn topics and domain-specific word embeddings. |
| Outcome: | The proposed model can learn topics and domain-specific word embeddings from a lifelong collaborative model. |
Are U a Joke Master? Pun Generation via Multi-Stage Curriculum Learning towards a Humor LLM (2024.findings-acl)
Copied to clipboard
Yang Chen, Chong Yang, Tu Hu, Xinhao Chen, Man Lan, Li Cai, Xinlin Zhuang, Xuan Lin, Xin Lu, Aimin Zhou
| Challenge: | Existing research has demonstrated that the ability of large language models (LLMs) to generate humorous sentences is limited to producing 25 unique jokes. |
| Approach: | They propose a multi-stage curriculum preference learning framework to optimize both pun structure preferences and humor preferences by a Chinese Pun dataset. |
| Outcome: | The proposed method significantly outperforms baseline models on Chinese and English benchmark datasets. |
RRHF-V: Ranking Responses to Mitigate Hallucinations in Multimodal Large Language Models with Human Feedback (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to mitigate hallucinations generate erroneous or fabricated information. |
| Approach: | They propose a rank-response-based model that annotates pair-reponses and trains alignment algorithms to improve the correspondence between images and text. |
| Outcome: | The proposed model outperforms the DPO method and outperfies existing methods on two MLLMs of different sizes and four widely used benchmarks. |
META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI (2022.emnlp-main)
Copied to clipboard
| Challenge: | Current task-oriented dialogue systems focus on multi-turn text/speech interaction, then call back-end APIs to perform task. |
| Approach: | They propose a GUI-based task-oriented dialogue system that can perform GUI operations on real APPs without invoking TOD-specific backend APIs. |
| Outcome: | The proposed GUI-based task-oriented dialogue system can perform GUI operations on real APPs and execute tasks without invoking TOD-specific backend APIs. |
ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search (2025.acl-long)
Copied to clipboard
Yize Zhang, Tianshu Wang, Sirui Chen, Kun Wang, Xingyu Zeng, Hongyu Lin, Xianpei Han, Le Sun, Chaochao Lu
| Challenge: | Large language models (LLMs) have impressive capabilities but their application in open-ended, knowledge-intensive, complex reasoning scenarios is limited. |
| Approach: | They propose a framework that integrates risk assessment of intermediate reasoning states with dynamic retrieval-augmented generation within a Monte Carlo tree search paradigm. |
| Outcome: | The proposed framework outperforms the state-of-the-art KAR methods by up to 23.10% and the latest RAG-equipped large reasoning models by upto 25.37%. |
D2-RAG: Dual-Decision Retrieval-Augmented Generation via Multi-Dimensional Uncertainty and Utility-Aware Decoding (2026.findings-acl)
Copied to clipboard
Jinshuo Zhang, Xiaoding Zhou, Weiyu Zhang, Guoqiang Chen, Ying Lian, Xiaoyang Meng, Yonghe Chen, Hongjiao Guan, Jiasheng Si, Wenpeng Lu
| Challenge: | Retrieval-Augmented Generation (RAG) mitigates hallucinations in large language models by incorporating external knowledge. |
| Approach: | They propose a dual-decision retrieval-augmented generation that integrates multi-dimensional uncertainty estimation to decide whether to retrieve and employs adaptive contrastive decoding to handle retrieved contexts of varying quality. |
| Outcome: | The proposed model outperforms baselines on four medical question-answering datasets while suppressing interference from noisy contexts. |
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. |
Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Latent Synthesis is an efficient textual data utilization framework for end-to-end speech processing models . labeled speech data are scarcer and more expensive for collection compared to textual ones . |
| Approach: | They propose a textual data utilization framework for E2E speech processing models . they train a latent synthesizer to convert textual information into an intermediate latent representation . |
| Outcome: | The proposed framework improves on low-resource speech recognition and spoken language understanding tasks. |
RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation (2026.acl-long)
Copied to clipboard
Bingxian Wu, Yu Zhang, Zonghao Guo, Tang Liu, Chen Qian, Yuxiang Lu, Xingbo Du, Yanghao Li, Yidan Zhang, Chi Chen, Ling Yao, Chenghu Zhou, Maosong Sun
| Challenge: | Existing RS agents built on general-purpose LLMs are domain-agnostic, resulting in brittle and error-prone workflows. |
| Approach: | They propose a knowledge-enhanced memory evolution mechanism that bootstraps RS agents with pre-distilled domain knowledge and iteratively integrates online experience for robust multi-step tool execution. |
| Outcome: | Experiments show that the new model improves tool-use performance and accuracy . iteratively, iteration of the model integrates online experience for robust multi-step tool execution . |
SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation benchmarks for Large Language Models focus on objective tasks like mathematics and coding in English, which do not reflect the practical use cases of on-device LLMs in real-world mobile scenarios. |
| Approach: | They propose a benchmark to evaluate the capabilities of on-device Large Language Models in Chinese mobile contexts. |
| Outcome: | The proposed framework evaluates on-device LLMs and MLLMs in Chinese . it provides a standardized framework for evaluating LLM performance on real smartphones . |
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)
Copied to clipboard
Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin
| Challenge: | a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities . |
| Approach: | They present a comparative analysis to identify and distinguish LLM activities from human activities. |
| Outcome: | The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities. |
Symbol tuning improves in-context learning in language models (2023.emnlp-main)
Copied to clipboard
Jerry Wei, Le Hou, Andrew Lampinen, Xiangning Chen, Da Huang, Yi Tay, Xinyun Chen, Yifeng Lu, Denny Zhou, Tengyu Ma, Quoc Le
| Challenge: | Language models are sensitive to the way that prompts are given, indicating that they are not reasoning in a robust manner. |
| Approach: | They propose to fine tune language models on in-context input-label pairs where natural language labels are replaced with arbitrary symbols. |
| Outcome: | The proposed model is much stronger at reasoning tasks and more robust to underspecified prompts than the standard model. |
Learning In-context Learning for Named Entity Recognition (2023.acl-long)
Copied to clipboard
Jiawei Chen, Yaojie Lu, Hongyu Lin, Jie Lou, Wei Jia, Dai Dai, Hua Wu, Boxi Cao, Xianpei Han, Le Sun
| Challenge: | Existing methods to recognize entities in text are limited by the diversity of entity types and the lack of high-quality annotations. |
| Approach: | They propose an in-context learning-based NER approach that can inject in-const NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. |
| Outcome: | The proposed method outperforms the PLMs+fine-tuning counterparts on 4 few-shot NER datasets and significantly outperformed the Plms+initialized extractors. |
Mitigating Uncertainty in Document Classification (N19-1)
Copied to clipboard
| Challenge: | Existing models for uncertainty measurement are time-consuming and unable to handle large-scale data sets. |
| Approach: | They propose a new dropout-entropy method for uncertainty measurement and a metric learning method on feature representations to boost the performance of dropout based uncertainty methods. |
| Outcome: | The proposed method improves accuracy from 0.78 to 0.92 when 30% of the most uncertain predictions were handed over to human experts in “20NewsGroup” data. |
Consecutive Batch Model Editing with HooK Layers (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models that retrain are time- and resource-consuming, but they lack the memory to support sequential and batch editing. |
| Approach: | They propose a model editing method that supports sequential and batch editing . they use a small amount of memory to store several hook layers that remain unchanged over time . |
| Outcome: | The proposed method is memory-friendly and can store hook layers that remain unchanged over time. |
SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator (2026.acl-long)
Copied to clipboard
Xueyang Zhou, Weidong Wang, Lin Lu, Jiawen Shi, Guiyao Tie, Xu Yongtian, Lixing Chen, Pan Zhou, Neil Zhenqiang Gong, Lichao Sun
| Challenge: | SafeAgent improves agent safety through fully automated synthetic data generation. |
| Approach: | They propose a framework that improves agent safety through fully automated synthetic data generation. |
| Outcome: | The proposed framework outperforms closed-source models on two safety benchmarks and one real-world task. |
PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration (2025.acl-long)
Copied to clipboard
| Challenge: | Existing privacy protection methods for large language models suffer from performance degradation or large inference time overhead. |
| Approach: | They propose a plug-and-play method to protect the privacy of user inputs during LLM inference . they use offline restoration vectors to train restoration vector for each privacy span type . |
| Outcome: | The proposed method can prevent the linear growth of the privacy budget. |
TrInk: Ink Generation with Transformer Network (2025.emnlp-main)
Copied to clipboard
Zezhong Jin, Shubhang Desai, Xu Chen, Biyi Fang, Zhuoyi Huang, Zhe Li, Chong-Xin Gan, Xiao Tu, Man-Wai Mak, Yan Lu, Shujie Liu
| Challenge: | Existing methods for handwriting generation capture global dependencies and can generate high-quality handwritten samples. |
| Approach: | They propose a Transformer-based model for ink generation, TrInk, which captures global dependencies. |
| Outcome: | The proposed model reduces character error rate and word error rate by 35.56% on the IAM-OnDB dataset compared to previous models. |
CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent studies have demonstrated that Large Language Models (LLMs) have impressive capabilities in a variety of domains and tasks. |
| Approach: | They propose a method which prompts LLMs to generate SQL queries based on the previously generated SQL query with an edition chain. |
| Outcome: | The proposed method outperforms different in-context learning baselines and achieves state-of-the-art performance on two benchmarks SParC and CoSQL using LLMs. |
HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on hallucination focus on text or vision, while few audio-oriented studies are limited in scale, modality coverage, and diagnostic depth. |
| Approach: | They propose a large-scale benchmark for evaluating hallucinations across speech, sound, and music. |
| Outcome: | The proposed model improves hallucination rate, yes/no bias, error-type analysis, and refusal rate. |
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)
Copied to clipboard
Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified. |
| Approach: | They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 . |
| Outcome: | Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 . |
ChatMap: Mining Human Thought Processes for Customer Service Chatbots via Multi-Agent Collaboration (2025.findings-acl)
Copied to clipboard
Xinyi Jiang, Tianyi Hu, Yuheng Qin, Guoming Wang, Zhou Huan, Kehan Chen, Gang Huang, Rongxing Lu, Siliang Tang
| Challenge: | Existing methods for enhancing dialogue performance rely on summarizing behavior . e-commerce chatbots need to align their dialogue strategies with human behavior to achieve coherent, human-like conversations with customers. |
| Approach: | They propose a method to extract core patterns from dialogue data and integrate them into models by mining service thought processes using a multi-agent aPproach. |
| Outcome: | The proposed method outperforms manual methods and outperfies baselines on Taobao in China. |
REInstruct: Building Instruction Data from Unlabeled Corpus (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for annotating instruction data are expensive and difficult to scale. |
| Approach: | They propose a method to automatically build instruction data from an unlabeled corpus without heavy reliance on proprietary LLMs and human annotation. |
| Outcome: | The proposed method outperforms existing methods on AlpacaEval leaderboard and other open-source methods. |
MemSearcher: Iterative Memory Integration for Search Agent via End-to-End Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Qianhao Yuan, Jie Lou, Zichao Li, Jiawei Chen, Yaojie Lu, Hongyu Lin, Le Sun, Debing Zhang, Xianpei Han
| Challenge: | Recent LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs and increasing compute cost and memory overhead. |
| Approach: | They propose an agent framework that maintains a compact memory during multi-turn interactions. |
| Outcome: | The proposed framework outperforms strong history-concatenation (ReAct-style) baselines on a range of public datasets while maintaining nearly constant token counts across multi-turn interactions. |
mCLIP: Multilingual CLIP via Cross-lingual Transfer (2023.acl-long)
Copied to clipboard
Guanhua Chen, Lu Hou, Yun Chen, Wenliang Dai, Lifeng Shang, Xin Jiang, Qun Liu, Jia Pan, Wenping Wang
| Challenge: | Existing multilingual vision-language pretrained models are biased towards English due to the lack of sufficient non-English image-text pairs. |
| Approach: | They propose to train a retrieval-efficient dual-stream multilingual VLP model by aligning CLIP model and a multilingual text encoder through a novel Triangle Cross-modal Knowledge Distillation method. |
| Outcome: | Empirical results show that mCLIP achieves new state-of-the-art performance for both zero-shot and finetuned multilingual image-text retrieval tasks. |
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing (2020.acl-main)
Copied to clipboard
| Challenge: | Existing semantic parsing frameworks rely on nontrivial human labor to generate canonical utterances. |
| Approach: | They propose a framework that uses an unsupervised paraphrase model to parse canonical utterances. |
| Outcome: | The proposed framework is effective and compatible with supervised training. |
SDiaReward: Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness (2026.acl-long)
Copied to clipboard
Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan, Xueyi Pu, Yifu Chen, Chenyuhao Wen, Tianle Liang, Zhou Zhao
| Challenge: | SDiaReward is an end-to-end spoken dialogue system that integrates paralinguistic nuances and spontaneous nature of human conversation. |
| Approach: | They propose an end-to-end multi-turn reward model trained on SDiaReward-Dataset . it is a collection of episode-level preference pairs targeting modality and colloquiality gaps . |
| Outcome: | The proposed model outperforms general-purpose audio LLMs in episode-level evaluation. |
Mixture of Soft Prompts for Controllable Data Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) generate fluent text when the target output follows natural language patterns. |
| Approach: | They propose a method that uses large language models to generate fluent text from a limited ontology rather than direct prediction by using soft prompts. |
| Outcome: | The proposed method produces diverse and natural text while preserving label semantics. |
Hierarchical Topic Modeling via Contrastive Learning and Hyperbolic Embedding (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing hierarchical topic models are based on Euclidean space, which cannot retain the hierarchically semantic information in the corpus, leading to irrational structure of the generated topics. |
| Approach: | They propose a novel hierarchical topic model that uses contrastive learning to capture information from documents. |
| Outcome: | The proposed model performs on topic coherence and topic diversity, and on the rationality of the topic hierarchy. |
SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning (2025.acl-industry)
Copied to clipboard
Zhengyuan Liu, Geyu Lin, Hui Li Tan, Huayun Zhang, Yanfeng Lu, Xiaoxue Gao, Stella Xin Yin, Sun He, Hock Huan Goh, Lung Hsiang Wong, Nancy F. Chen
| Challenge: | Empirical studies show that SingaKids provides effective dialogic teaching, benefiting learners at different performance levels. |
| Approach: | They propose a dialogic tutor designed to facilitate language learning through picture description tasks. |
| Outcome: | Empirical studies show that SingaKids provides effective dialogic teaching, benefiting learners at different performance levels. |
Multilingual Brain Surgeon: Large Language Models Can Be Compressed Leaving No Language behind (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for MC focus on quantization and network pruning. |
| Approach: | They propose a calibration method that samples calibration data from various languages proportionally to the language distribution of the model training datasets. |
| Outcome: | The proposed method improves the performance of existing English-centric compression methods on the BLOOM multilingual LLM. |
Jailbreak Open-Sourced Large Language Models via Enforced Decoding (2024.acl-long)
Copied to clipboard
Hangfan Zhang, Zhimeng Guo, Huaisheng Zhu, Bochuan Cao, Lu Lin, Jinyuan Jia, Jinghui Chen, Dinghao Wu
| Challenge: | Existing studies show that Large Language Models can be misused to generate undesired content. |
| Approach: | They propose to use large language models to manipulate the generation process to generate undesired content without heavy computations or prompt designs. |
| Outcome: | The proposed method shows that open-sourced large language models could be misused to generate undesired content without heavy computations or prompt designs. |
LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent large-scale video-language pre-trained models have shown appealing performance on downstream tasks. |
| Approach: | They propose a video-text model that adapts a pre-trained image-language model into a text-based model without heavy pre-training. |
| Outcome: | The proposed model outperforms existing models on video-text retrieval and video question answering tasks without heavy pre-training. |
The Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning (2026.acl-long)
Copied to clipboard
Renmiao Chen, Yida Lu, Shiyao Cui, Xuan Ouyang, Victor Shea-Jay Huang, Shumin Zhang, Chengwei Pan, Han Qiu, Minlie Huang
| Challenge: | Recent advances in multimodal reasoning may pose new safety risks . evaluators neglect reasoningbased safety, where harm emerges only through MLLMs . |
| Approach: | They introduce a benchmark for multi-image reasoning safety that includes 2,676 instances . they find that models with more advanced multi- image reasoning are more vulnerable . |
| Outcome: | The proposed benchmark consists of 2,676 instances covering 9 multi-image relations . the results show that models with more advanced multi- image reasoning are more vulnerable . |
Exploring Schema Generalizability of Text-to-SQL (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing text-to-SQL models are limited in their generalizability, despite their performance being over-estimated. |
| Approach: | They propose a framework to generate novel text-to-SQL data via automatic and synchronous (DS, SQL) pair altering. |
| Outcome: | The proposed framework generates text-to-SQL data via automatic and synchronous (DS, SQL) pair altering. |
Can Post-Training Transform LLMs into Causal Reasoners? (2026.findings-acl)
Copied to clipboard
| Challenge: | Causal inference is a core component of human cognition and requires decision-makers to distinguish between causation and association. |
| Approach: | They propose a dataset comprising seven core causal tasks for training and five diverse test sets and evaluate five different post-training approaches. |
| Outcome: | The proposed model achieves 93.5% accuracy on the CaLM benchmark, compared to 55.4% by OpenAI o3. |
SynET: Synonym Expansion using Transitivity (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to find synonyms from text corpora are distributed and pattern based, but they suffer from low precision and low recall. |
| Approach: | They propose a task of synonym expansion using transitivity and propose auxiliary task to reduce the impact of noisy sentences. |
| Outcome: | The proposed approach reduces the impact of noisy sentences and reduces noise in a real-world dataset. |
When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have achieved impressive performance across NLP tasks. |
| Approach: | They propose to use long-context SFT to improve short-contemporary performance . they also decouple and analyze two key components, Multi-Head Attention and Feed-Forward Network . |
| Outcome: | The proposed model improves short-context performance, contrary to pretraining. |
CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset (2023.findings-acl)
Copied to clipboard
| Challenge: | a cross-domain text-to-SQL task aims to parse user questions into SQL on complete unseen databases . a single-domain task evaluates the performance on identical databases based on the same domain . |
| Approach: | They propose a cross-domain text-to-SQL task that parses user questions into SQL on unseen databases. |
| Outcome: | The proposed system can parse user questions into SQL on complete unseen databases. |
Uncertainty-Aware Cross-Lingual Transfer with Pseudo Partial Labels (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to train pre-trained language models for zero-shot cross-lingual tasks are noisy and lack confidence. |
| Approach: | They propose an uncertainty-aware cross-lingual transfer framework with pseudo-partial-label to maximize the utilization of unlabeled data by reducing noise. |
| Outcome: | The proposed framework outperforms baselines on named entity recognition and natural language inference tasks on 40 languages. |
TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fewshot text classification depend on inter-class variance . Existing approaches suffer from MLADA, which performs poorly on tasks with high inter- class variance whereas it fails to distinguish samples from tasks with low inter-group variance. |
| Approach: | They propose a task-adaptive reference transformation network to transform class prototypes to per-class fixed reference points in task-adapted metric spaces. |
| Outcome: | The proposed method surpasses state-of-the-art methods in 1-shot and 5-shot classifications on the 20 Newsgroups dataset. |
SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)
Copied to clipboard
Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen
| Challenge: | Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios. |
| Approach: | They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance. |
| Outcome: | The proposed framework improves model capabilities across all domains and scales. |
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. |
DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation (2026.findings-acl)
Copied to clipboard
Hao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
| Challenge: | Existing presentation agents rely on predefined workflows and fixed templates to generate presentations. |
| Approach: | They propose an agentic framework that adapts to diverse user intents and iterative refinement based on observation. |
| Outcome: | The proposed framework can be used to generate presentations with environmental observations. |
Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on retrieval-augmented generation (RAG) rarely address the issue of predictive uncertainty, i.e., how likely it is that a RAG model’s prediction is incorrect. |
| Approach: | They propose a framework that induces RAG models to alter latent factors and analyzes the effect on their answers. |
| Outcome: | The proposed framework identifies two critical factors affecting RAG models' confidence in their answers and analyzes the effect on their answers. |
Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Previous Sign Language Translation methods have relied on gloss annotations to improve performance, but labeling high-quality glosses is labor-intensive and inefficient. |
| Approach: | They propose to integrate Large Language Model (LLM) into SLT by factorizing learning into two stages to improve the learning curve. |
| Outcome: | The proposed approach improves on three SLT datasets conducted under the gloss-free setting. |
SeqVAT: Virtual Adversarial Training for Semi-Supervised Sequence Labeling (2020.acl-main)
Copied to clipboard
| Challenge: | Empirical studies show that virtual adversarial training (VAT) significantly improves the sequence labeling performance over baselines under supervised and semi-supervised settings. |
| Approach: | They propose a method which naturally applies VAT to sequence labeling models with conditional random field (CRF) Empirical studies show that SeqVAT significantly improves the sequence labelling performance over baselines under supervised settings, and outperforms state-of-the-art approaches under semi-supervised settings. |
| Outcome: | Empirical results show that the proposed method outperforms state-of-the-art approaches under semi-supervised settings. |
CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | CKnowEdit is the first-ever knowledge editing dataset designed to correct linguistic, factual, and logical errors in Large Language Models. |
| Approach: | They propose a Chinese knowledge editing dataset to correct linguistic, factual, and logical errors in Large Language Models. |
| Outcome: | The proposed dataset highlights the challenges that LLMs face in mastering Chinese . CKnowEdit can correct linguistic, factual, and logical errors in Chinese, the authors show . |
ALCAP: Alignment-Augmented Music Captioner (2023.emnlp-main)
Copied to clipboard
| Challenge: | Traditional approaches to music captioning ignore the intricate interplay between the two . however, a comprehensive understanding of music necessitates the integration of both these elements. |
| Approach: | They propose a method to learn multimodal alignment between audio and lyrics through contrastive learning. |
| Outcome: | The proposed method achieves new state-of-the-art on two music captioning datasets. |
PreCo: A Large-scale Dataset in Preschool Vocabulary for Coreference Resolution (D18-1)
Copied to clipboard
| Challenge: | Existing methods for coreference resolution are based on word2vec-like representations of entities. |
| Approach: | They propose a large-scale English dataset for coreference resolution . they use 38K documents and 12.5M words from English-speaking preschoolers . |
| Outcome: | The proposed dataset is more efficient with higher training-test overlap than OntoNotes . the study also shows that mention detection and clustering are more efficient on PreCo . |
LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to encode text-to-SQL data are node-centric and ignore semantics embedded in the topological structure of edges. |
| Approach: | They propose a Line Graph Enhanced Text-to-SQL model to mine relational features without constructing meta-paths. |
| Outcome: | The proposed model achieves state-of-the-art on the cross-domain text-to-SQL benchmark Spider at the time of writing. |
Attention-Enhancing Backdoor Attacks Against BERT-based Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing textual backdoor attacks focus on generating stealthy triggers or modifying model weights. |
| Approach: | They propose a Trojan Attention Loss (TAL) which enhances the Trojan behavior by directly manipulating attention patterns. |
| Outcome: | The proposed method improves the effectiveness of the backdoor attacks on different backbone models and tasks. |
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. |
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. |
Few-shot Named Entity Recognition via Superposition Concept Discrimination (2024.lrec-main)
Copied to clipboard
| Challenge: | Few-shot named entity recognition (NER) aims to identify entities of target types with limited number of illustrative instances. |
| Approach: | They propose a superposition concept discriminator which solves the intrinsic generalization problem by an active learning paradigm. |
| Outcome: | The proposed model significantly improves few-shot named entity recognition (FS-NER) with minimal additional efforts. |
Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have facilitated the development of Multimodal LLMs. |
| Approach: | They propose a causal framework to interpret unimodal biases in visual question answering problems and a framework to integrate information from different modalities and mitigate biase. |
| Outcome: | The proposed framework analyzes visual question answering (VQA) problems to assess their impact on predictions. |
FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference (2025.emnlp-main)
Copied to clipboard
| Challenge: | Low-rank compression can reduce memory usage and computational demand, but results are poor during decoding. |
| Approach: | They propose a fine-grained low-rank compression algorithm that determines optimal rank allocation for each layer and incorporates progressive low-ranked decoding to maintain text generation quality. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on summarization tasks and on understanding tasks. |
CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models (2026.acl-long)
Copied to clipboard
Haibo Tong, Zeyang Yue, Feifei Zhao, Erliang Lin, Lu Jia, Ruolin Chen, Yinqian Sun, Qian Zhang, Yi Zeng
| Challenge: | Existing benchmarks for Large Language Models (LLMs) are limited to false belief tasks, highlighting bottlenecks in specific dimensions. |
| Approach: | They propose a benchmark to evaluate Large Language Models' Theory of Mind capabilities . they evaluate 8000 bilingual instances across 46 paradigms and validated by 49 human annotators . |
| Outcome: | The proposed benchmark reveals performance heterogeneities and bottlenecks in 22 representative models. |
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders (2025.emnlp-main)
Copied to clipboard
Weiqiao Shan, Yuang Li, Yuhao Zhang, Yingfeng Luo, Chen Xu, Xiaofeng Zhao, Long Meng, Yunfei Lu, Min Zhang, Hao Yang, Tong Xiao, JingBo Zhu
| Challenge: | Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects. |
| Approach: | They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt. |
| Outcome: | The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks. |
A Systematic Survey of Automatic Prompt Optimization Techniques (2025.emnlp-main)
Copied to clipboard
Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, Haozhu Wang, Han Ding, Yuzhe Lu, Zhichao Xu, Yun Zhou, Balasubramaniam Srinivasan, Qiaojing Yan, Yueyan Chen, Haibo Ding, Panpan Xu, Lin Lee Cheong
| Challenge: | Recent advances in prompt engineering have created impediments for end users to adopt . however, prompt engineering remains an impedance due to rapid advances in models, tasks, and associated best practices. |
| Approach: | They propose to define APO as a 5-part unifying framework and categorize all relevant works based on their salient features. |
| Outcome: | The proposed framework aims to improve the performance of large language models on various tasks. |
CELLO: Causal Evaluation of Large Vision-Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large vision-language models have improved causal reasoning abilities . however, current models struggle with tasks like causal reasoning . |
| Approach: | They propose a fine-grained and unified definition of causality involving interactions between humans and objects. |
| Outcome: | The proposed model surpasses traditional commonsense causality by including explicit causal graphs . it also shows that current LVLMs can benefit from a causally inspired prompting strategy . |
PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing paper search systems lack detailed information to support finer-grained queries. |
| Approach: | They propose a paper-based index that transforms abstract-based corpus index into hierarchical index tree and offline can support paper search queries. |
| Outcome: | The proposed system achieves the SOTA performance and excels in fine-grained scenarios. |
Breaking the Noise Barrier: LLM-Guided Semantic Filtering and Enhancement for Multi-Modal Entity Alignment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multi-modal entity alignment (MMEA) aims to identify equivalent entities between two multimodal knowledge graphs. |
| Approach: | They propose a novel LLMguided MMEA framework that prioritizes noise reduction before fusion. |
| Outcome: | The proposed framework prioritizes noise reduction before fusion and improves semantics on the noisy FB YG dataset. |
i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data (2024.findings-naacl)
Copied to clipboard
Ziyi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Xuemei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang
| Challenge: | i-Code V2 is one of the first models capable of generating natural language from any combination of Vision, Language, and Speech data. |
| Approach: | They propose to create a model that can generate natural language from any combination of Vision, Language, and Speech data. |
| Outcome: | i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks. |
TheoremQA: A Theorem-driven Question Answering Dataset (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent LLMs like GPT-4 and PaLM-2 have made tremendous progress in solving fundamental math problems like GSM8K by achieving over 90% accuracy. |
| Approach: | They propose to use theorem-driven question-answering dataset to evaluate AI models' ability to apply theoretic concepts to solving challenging science problems. |
| Outcome: | TheoremQA is curated by domain experts and contains 800 high-quality questions covering 350 theoremics from Math, Physics, EE&CS, and Finance. |
JointCoder: Exploring Automated ICD Coding on Real-World Chinese EHRs with a Multi-Agent Framework (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing automated ICD coding systems face several fundamental challenges due to the limited availability of publicly available Chinese ICD datasets. |
| Approach: | They propose to use a Chinese ICD coding dataset and a multi-agent framework to reformulate ICD as a joint disease-procedure coding task. |
| Outcome: | The proposed system outperforms state-of-the-art methods on real-world Chinese ICD coding datasets and 1.7B-parameter models. |
Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network (P18-1)
Copied to clipboard
| Challenge: | Existing models for matching dialogue responses rely on semantic and functional dependencies . a recent study only uses the last utterance in context for matching a reply . |
| Approach: | They propose a model that matches a response with its multi-turn context using attention. |
| Outcome: | The proposed model outperforms the state-of-the-art models on two large-scale multi-turn response selection tasks. |
Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards (P19-1)
Copied to clipboard
| Challenge: | Existing generative models generate too few keyphrases, but they often generate too many . et al. (2017) propose a reinforcement learning approach for keyphrase generation . |
| Approach: | They propose a reinforcement learning approach that encourages a model to generate sufficient keyphrases with an adaptive reward function. |
| Outcome: | The proposed method improves state-of-the-art generative models with conventional and new evaluation methods on real-world datasets. |
Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment (2021.acl-long)
Copied to clipboard
| Challenge: | Existing deep learning models for automatic readability assessment discard linguistic features traditionally used for the task. |
| Approach: | They propose to incorporate linguistic features into machine learning models by learning syntactic dense embeddings based on linguistic feature extraction. |
| Outcome: | Experiments with six data sets of two proficiency levels show that the proposed model can perform better than existing models. |
An Iterative Emotion Interaction Network for Emotion Recognition in Conversations (2020.coling-main)
Copied to clipboard
| Challenge: | Emotion recognition in conversations (ERC) is a task that aims to recognize the emotion of each utterance in conversations. |
| Approach: | They propose an iterative emotion interaction network which uses iterativly predicted emotion labels instead of gold emotion labels to explicitly model the emotion interaction. |
| Outcome: | The proposed method retains state-of-the-art performance on two datasets and achieves high accuracy. |
A Table-to-Text Framework with Heterogeneous Multidominance Attention and Self-Evaluated Multi-Pass Deliberation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Table-to-text works have been widely applied in different domains, such as weather forecast and financial report generation. |
| Approach: | They propose a table-to-text approach on top of Self-evaluated multi-pass Generation and Heterogenous Multidominance Attention to explore the hierarchical structure. |
| Outcome: | The proposed method outperforms several SOTA methods quantitatively and qualitatively on three public datasets. |
Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration (2026.eacl-long)
Copied to clipboard
Guozhao Mo, Yanjiang Liu, Yafei Shi, Jiawei Chen, Yang Li, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Bo Zheng, Xianpei Han
| Challenge: | Existing methods for dynamic web navigation rely on greedy strategies or value estimation, struggle to achieve effective backtracking and are heavily dependent on proprietary models. |
| Approach: | They propose a cognitive multi-agent collaboration framework that enhances cyberspace exploration capability through In-Context Exploration. |
| Outcome: | The proposed framework surpasses the proprietary model Claude-3.5 Sonnet on the WebArena benchmark. |
StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children’s Story-Based Learning (2024.emnlp-main)
Copied to clipboard
Jiaju Chen, Yuxuan Lu, Shao Zhang, Bingsheng Yao, Yuanzhe Dong, Ying Xu, Yunyao Li, Qianwen Wang, Dakuo Wang, Yuling Sun
| Challenge: | Existing story reading systems fail to capture the nuances of how education experts think when conducting interactive story reading activities. |
| Approach: | They propose to use existing question-answering (QA) datasets to capture experts' annotations and thinking process to construct a story-based annotation framework. |
| Outcome: | The proposed framework captures experts’ annotations and thinking process and can be used to generate 5, 868 expert-annotated QA pairs with real-world knowledge. |
TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing models for structural reading comprehension (SRC) only focus on comprehension of plain text, tables, tables or knowledge bases. |
| Approach: | They propose a topological information enhanced model which transforms a token-level task into a tag-level one by introducing a two-stage process. |
| Outcome: | The proposed model outperforms baselines and achieves state-of-the-art performance on the web-based SRC benchmark WebSRC at the time of writing. |
Through the Valley: Path to Effective Long CoT Training for Small Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Long chain-of-thought (CoT) supervision is effective for large language models . but small models trained on limited long CoT data experience performance degradation . |
| Approach: | They identify a phenomenon called Long CoT Degradation in small language models . long CoT data can be used to generate long chain-of-thought (CoT) responses . |
| Outcome: | The results show that models trained on 8k long CoT examples lose up to 75% of their original performance before fine-tuning. |
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. |
Sparsity-Accelerated Training for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated proficiency across various NLP tasks but often require additional training, such as continual pre-training and supervised fine-tuning. |
| Approach: | They propose to leverage sparsity in pre-trained LLMs to accelerate training by disregarding computations for unimportant neurons. |
| Outcome: | The proposed framework achieves comparable or superior performance to standard training while significantly accelerating the process. |
ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing semantic parsing models struggle to adapt to unseen database schemas . a new architecture, ShadowGNN, processes schemas at abstract and semantic levels . |
| Approach: | They propose a new architecture which processes schemas at abstract and semantic levels. |
| Outcome: | The proposed architecture outperforms state-of-the-art models on a text-to-sql benchmark . it uses domain-independent representations to extract logical linking between question and schema . |
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)
Copied to clipboard
Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun
| Challenge: | Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs. |
| Approach: | They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction. |
| Outcome: | The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI. |
Measuring Pointwise 𝒱-Usable Information In-Context-ly (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In-context learning (ICL) is a new learning paradigm that has gained popularity along with the development of large language models. |
| Approach: | They propose to adapt a recently proposed hardness metric, pointwise V-usable information (PVI), to an in-context version. |
| Outcome: | The proposed hardness metric is compared with the original model and is more efficient because it requires only a few exemplars and does not require fine-tuning. |
Document Segmentation Matters for Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
Zhitong Wang, Cheng Gao, Chaojun Xiao, Yufei Huang, Shuzheng Si, Kangyang Luo, Yuzhuo Bai, Wenhao Li, Tangjian Duan, Chuancheng Lv, Guoshan Lu, Gang Chen, Fanchao Qi, Maosong Sun
| Challenge: | Existing rule-based chunking methods lead to suboptimal splits, where overly large chunks introduce irrelevant information and small chunks lack semantic coherence. |
| Approach: | They propose a method that leverages document summaries as pseudo-instructions to guide chunking by computing semantic similarity between sentences and the summary. |
| Outcome: | Experiments on multiple open-domain question-answering benchmarks show that PIC significantly improves retrieval accuracy (Hits@k) and end-to-end QA performance (Exact Match) without any additional training. |
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. |
ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch (2025.emnlp-main)
Copied to clipboard
Jiawei Chen, Xinyan Guan, Qianhao Yuan, Mo Guozhao, Weixiang Zhou, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Xianpei Han
| Challenge: | Existing instruction data synthesis methods focus on single-turn instructions and neglect cross-turn coherence, resulting in context drift and reduced task completion rates. |
| Approach: | They propose a framework that constrains multi-turn instruction synthesis by explicitly modeling human conversational intent. |
| Outcome: | The proposed framework outperforms existing models trained on single-turn and multi-turn instruction datasets. |
JoPA: Explaining Large Language Model’s Generation via Joint Prompt Attribution (2025.acl-long)
Copied to clipboard
| Challenge: | Existing attempts to explain the entire language generation often treat input prompt texts independently, ignoring their combinatorial effects on the follow-up generation. |
| Approach: | They propose a framework for explaining how a few prompt texts collaboratively influences the LLM's complete generation. |
| Outcome: | The proposed explanations demonstrate faithfulness and efficiency of the proposed framework. |
Enhance Robustness of Sequence Labelling with Masked Adversarial Training (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Adversarial training (AT) has shown strong regularization effects on deep learning algorithms by introducing small input perturbations to improve model robustness. |
| Approach: | They propose to use adversarial training to improve robustness from contextual information in sequence labelling tasks by masking or replacing some words in the sentence. |
| Outcome: | The proposed method shows significant improvements on accuracy and robustness of sequence labelling on CoNLL 2000 and 2003 benchmarks. |
RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository (2026.acl-long)
Copied to clipboard
Zhiyuan Peng, Xin Yin, Pu Zhao, Fangkai Yang, Lu Wang, Ran Jia, Xu Chen, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing benchmarks focus on isolated function/class-level generation, neglecting complete microservice repository generation. |
| Approach: | They propose a multilingual benchmark for repository-level end-to-end web microservice generation that reflects real-world development workflows. |
| Outcome: | The benchmark compared 106 repositories across 18 domains and 11 frameworks and 1,258 API endpoints and 2,335 test cases. |
Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | a new text classification framework for large language models addresses the problem of boundary ambiguity and inherent biases in LLMs. |
| Approach: | They propose a two-stage classification framework for large language models to mitigate bottlenecks . their approach uses pairwise comparisons to efficiently narrow down options . |
| Outcome: | The proposed framework reduces the number of options and improves on four datasets. |
SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated strong performance across various NLP tasks, but their effectiveness in ECI remains limited due to biases in causal reasoning. |
| Approach: | They propose a structural example retrieval framework that leverages LLMs’ few-shot learning capabilities to help LLM models in ECI. |
| Outcome: | The proposed framework leverages LLMs’ few-shot learning capabilities to guide LLM models in causal reasoning, mitigating bias and improving accuracy. |
Reasoning Makes Good Annotators : An Automatic Task-specific Rules Distilling Framework for Low-resource Relation Extraction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to extract knowledge from unlabeled data generate noise labels. |
| Approach: | They propose an automatic task-specific rules distilling framework to generate a logic rule from unlabeled data. |
| Outcome: | The proposed framework could power the labeling ability by discovering reliable model-labeled data. |
Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering (2026.acl-long)
Copied to clipboard
Qiming Li, Xiaocheng Feng, Yixuan Ma, Ruihan Chen, Zihe Tong, Zekai Ye, Xiachong Feng, Libo Qin, Haoyu Ren, Kun Chen, Yunfei Lu, Dandan Tu, Bing Qin
| Challenge: | Existing approaches to enhance multilingual reasoning capabilities rely on costly multilingual training or employ prompting with external translation tools. |
| Approach: | They propose a training-free inference-time method to enhance multilingual reasoning capabilities via Representation Engineering without additional training data or tools. |
| Outcome: | The proposed method outperforms existing methods on four reasoning benchmarks in English and Thai and Swahili. |
A Large Scale Speech Sentiment Corpus (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing corpus for sentiment analysis uses text inputs, but voice inputs are becoming more important as smart assistants and mobile voice control become more prevalent. |
| Approach: | They propose to extend the Switchboard-1 Telephone Speech Corpus by adding sentiment labels from 3 different human annotators for every transcript segment. |
| Outcome: | The proposed corpus contains 49500 labeled speech segments covering 140 hours of audio. |
OctoTools: A Multi-Agent Framework with Extensible Tools for Complex Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing prompting methods for large language models (LLMs) are restricted to specialized domains, limited tool types, or require additional training data. |
| Approach: | They propose a training-free, user-friendly, and easily extensible multi-agent framework designed to tackle complex reasoning across diverse domains. |
| Outcome: | The proposed framework outperforms AutoGen, GPT-Functions, and LangChain by up to 10.6% when given the same set of tools. |
GhostBERT: Generate More Features with Cheap Operations for BERT (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that some parameters in pre-trained language models can be pruned away without severe accuracy degradation. |
| Approach: | They propose a method which generates more features with very cheap operations from the remaining features and can be applied to unpruned BERT models to enhance their performance. |
| Outcome: | Empirical results on the GLUE benchmark on three backbone models (i.e., BERT, RoBERTa and ELECTRA) verify the efficacy of the proposed method. |
GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing (2026.acl-long)
Copied to clipboard
Ming Wang, Shuang Wu, Bixuan Wang, Lu Lin, Yuxin Chen, Xiaocui Yang, Daling Wang, Shi Feng, Yifei Zhang, Yufan Sun
| Challenge: | Large language models (LLMs) inherit contamination from training corpora, directional bias under social-desirability framing, and limited responsiveness to context beyond the item text. |
| Approach: | They propose a paradigm that reformulates TAT, Rorschach, and SCT with newly generated stimuli and organises assessment as a three-stage pipeline. |
| Outcome: | The proposed paradigm reformulates TAT, Rorschach, and SCT with newly generated stimuli and organises assessment as a three-stage pipeline. |
Alignment for Efficient Tool Calling of Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in tool learning have enabled large language models to integrate external tools, enhancing their task performance by expanding their knowledge boundaries. |
| Approach: | They propose a framework that combines probabilistic knowledge boundary estimation with dynamic decision-making to allow LLMs to better assess when to invoke tools based on their confidence. |
| Outcome: | The proposed framework shows significant improvements in tool efficiency by reducing unnecessary tool usage. |
Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) and AI systems have led to a paradigm shift in the design and optimization of complex workflows. |
| Approach: | They propose a systematic review of recent progress in optimizing compound AI systems . they formalize the notion of compound AI system optimization and classify existing methods along several key dimensions . |
| Outcome: | The proposed methods outperform existing methods in the field of compound AI and highlight open research challenges and future directions. |
SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training (2025.findings-acl)
Copied to clipboard
Wenxi Chen, Ziyang Ma, Ruiqi Yan, Yuzhe Liang, Xiquan Li, Ruiyang Xu, Zhikang Niu, Yanqiao Zhu, Yifan Yang, Zhanxun Liu, Kai Yu, Yuxuan Hu, Jinyu Li, Yan Lu, Shujie Liu, Xie Chen
| Challenge: | a new spoken dialogue system with single-stage training is demonstrating its low latency and high quality . SLAM-Omni achieves zero-shot timbre control by modeling spoken language with semantic tokens . |
| Approach: | They propose a timbre-controllable, end-to-end voice interaction system with single-stage training. |
| Outcome: | The proposed system outperforms previous models on 4 GPUs with limited data. |
LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios (2025.naacl-long)
Copied to clipboard
Pei Chen, Hongye Jin, Cheng-Che Lee, Rulin Shao, Jingfeng Yang, Mingyu Zhao, Zhaoyu Zhang, Qin Lu, Kaiwen Men, Ning Xie, Huasheng Li, Bing Yin, Han Li, Lingyun Wang
| Challenge: | LongLeader aims to assess different LLMs' long-context comprehension abilities . long-constext comprehension is a key bottleneck for many use cases . |
| Approach: | They propose a leaderboard to assess different LLMs' long-context comprehension abilities . they offer open-source access to the benchmarks and maintain a dedicated website . |
| Outcome: | The proposed model assesses different LLMs on selected benchmarks and provides open-source access to the benchmarks. |
Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing Parameter-Efficient Fine-Tuning (PEFT) strategies that focus on specialized experts are not effective for Mixture-of-Experts (MoE). |
| Approach: | They propose to integrate a dynamic routing mechanism among specialized experts in Mixture-of-Experts (MoE) . |
| Outcome: | Extensive experiments on commonsense and math reasoning tasks validate the performance and efficiency of the proposed routed approach. |
Event Extraction as Multi-turn Question Answering (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Current approaches to event extraction fail to model rich interactions among event types and arguments of different roles. |
| Approach: | They propose a new paradigm that formulates event extraction as multi-turn question answering . they propose to use reading comprehension problems to extract triggers and arguments . |
| Outcome: | The proposed approach outperforms current state-of-the-art on argument extraction tasks . it makes full use of dependency among arguments and event types, and generalizes well . |
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent advances in large language models have raised concerns about their susceptibility to jailbreaking attacks, which leads to harmful content inadvertently. |
| Approach: | They propose to exploit the safety alignment patterns of LLMs by simultaneous obfuscation in queries and responses to break down adversarial intent of query. |
| Outcome: | The proposed attack breaks down adversarial intent of query and encourages benign content regarding the games to precede anticipated harmful content in the response. |
Read As Human: Compressing Context via Parallelizable Close Reading and Skimming (2026.acl-long)
Copied to clipboard
Jiwei Tang, Shilei Liu, Zhicheng Zhang, Qingsong Lv, Runsong Zhao, Tingwei Lu, Langming Liu, Haibin Chen, Yujin Yuan, Hai-Tao Zheng, Wenbo Su, Bo Zheng
| Challenge: | Existing task-aware methods require loading the entire input sequence at once for compression, which suffer from computational inefficiency. |
| Approach: | They propose a framework that adopts an adaptive hybrid reading strategy to reduce computational inefficiency and redundant information in long-context scenarios. |
| Outcome: | Experiments show that RAM outperforms baselines on multiple question answering and summarization benchmarks while delivering up to a 12x speedup on long inputs. |
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 . |
Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)
Copied to clipboard
Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong
| Challenge: | Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries. |
| Approach: | They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored . |
| Outcome: | The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods. |
Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach (2022.emnlp-main)
Copied to clipboard
| Challenge: | Currently, the generalization issues hinder the applicability of neural table-to-text models due to the limited source tables. |
| Approach: | They propose a table-structureaware text generation model with pretrained language model and propose TASD to bridge the gap between the structured table and text input. |
| Outcome: | The proposed model bridges the gap between the structured table and text input and generates accurate and fluent descriptive texts on two public datasets. |
FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping (2024.emnlp-main)
Copied to clipboard
| Challenge: | Autoregressive Large Language Models (LLMs) are omnipresent but typically come with a substantial model size. |
| Approach: | They propose a novel fine-grained skip strategy for autoregressive large language models . they observe the saturation of computationally expensive feed-forward blocks of LLMs . |
| Outcome: | The proposed method can skip 25-30% of FFN blocks with marginal change in performance on knowledge-intensive generation tasks. |
OmniCode: A Benchmark for Evaluating Software Development Agents (2026.findings-acl)
Copied to clipboard
Atharv Sonwane, Eng-Shen Tu, Wei-Chung Lu, Claas Beger, Carter Larsen, Debjit Dhar, Simon Alford, Rachel Chen, Ronit Pattanayak, Tuan Anh Dang, Guohao Chen, Gloria Geng, Kevin Ellis, Saikat Dutta
| Challenge: | popular coding benchmarks focus on narrowly scoped tasks such as competition programming and patch generation. |
| Approach: | They propose a software engineering benchmark that aims to provide a broader set of tasks beyond code or patch generation. |
| Outcome: | The proposed framework performs well on bug fixing for Python, test generation, code review fixing, and style fixing with popular agent frameworks such as SWE-Agent. |
Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks (2020.acl-main)
Copied to clipboard
| Challenge: | Existing graph-to-sequence approaches use graph neural networks as encoders, but they lack the structure information needed to translate AMR into the graph-based data. |
| Approach: | They propose a graph-to-sequence task which aims to recover natural language from Abstract Meaning Representations (AMR) they adopt graph attention networks with higher-order neighborhood information to explore the edge relations in AMR graphs. |
| Outcome: | The proposed framework achieves state-of-the-art performance on English AMR benchmark datasets and is able to translate the AMR semantics into the natural language. |
System Prompt Hijacking via Permutation Triggers in LLM Supply Chains (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are rapidly transforming the landscape of artificial intelligence due to the substantial resources required for training. |
| Approach: | They propose a post-deployment attack that bypasses system prompts to compromise models . they introduce Precise Activation Guarding and Unit Deviation Sampling to protect against attack . |
| Outcome: | The proposed attack bypasses system prompts, enabling unrestricted model outputs and safety violations. |
Across Programming Language Silos: A Study on Cross-Lingual Retrieval-Augmented Code Generation (2026.findings-acl)
Copied to clipboard
Qiming Zhu, Jialun Cao, Xuanang Chen, Weili Zhang, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Shing-Chi Cheung
| Challenge: | Current research on large language models with retrieval-augmented code generation (RACG) has focused on single-language settings, leaving their cross-lingual effectiveness underexplored. |
| Approach: | They construct a dataset covering 13 PLs with nearly 14K instances to study cross-lingual code knowledge transfer in RACG. |
| Outcome: | The proposed model shows unequal cross-lingual knowledge transfer even with direct injection and shows limited reliance on natural language information embedded in code when equipped with a code-specific retriever. |
AdapterShare: Task Correlation Modeling with Adapter Differentiation (2022.emnlp-main)
Copied to clipboard
| Challenge: | AdapterShare is an adapter differentiation method to explicitly model the task correlation among multiple tasks. |
| Approach: | They propose an adapter differentiation method to explicitly model the task correlation among multiple tasks. |
| Outcome: | The proposed method achieves 1.90 points improvement on five dialogue understanding tasks and 2.33 points gain on NLU tasks. |
Multi-hop Evidence Retrieval for Cross-document Relation Extraction (2023.findings-acl)
Copied to clipboard
| Challenge: | Relation Extraction (RE) is a task that seeks to identify the relation of entities described according to some context. |
| Approach: | They propose a multi-hop evidence retrieval method based on evidence path mining and ranking to support cross-document relation extraction. |
| Outcome: | The proposed method acquires cross-document evidence and boosts performance in both closed and open environments. |
VQAGuider: Guiding Multimodal Large Language Models to Answer Complex Video Questions (2025.acl-long)
Copied to clipboard
| Challenge: | Multimodal large language models (MLLMs) can grasp the intention of a question and decomposing it to a series of visual recognition sub-tasks to find out the answer with the help of an agent. |
| Approach: | They propose a framework for multimodal large language models to grasp the intention of a question and decompose it into a series of visual recognition sub-tasks to find out the answer. |
| Outcome: | The proposed framework improves the accuracy of complex video-related questions by 29.6% and 17.2% on CVQA and the existing VQA datasets. |
RORA: Robust Free-Text Rationale Evaluation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing metrics rely on degree to which rationale supports a label, but they fail to evaluate rationales that inadvertently leak the label. |
| Approach: | They propose a RObust free-text RAtionale evaluation against label leakage that quantifies the new information supplied by a rationale to justify the label. |
| Outcome: | The proposed evaluation outperforms existing methods in evaluating human-written, synthetic, or model-generated rationales, particularly demonstrating robustness against label leakage. |
Code Execution with Pre-trained Language Models (2023.findings-acl)
Copied to clipboard
Chenxiao Liu, Shuai Lu, Weizhu Chen, Daxin Jiang, Alexey Svyatkovskiy, Shengyu Fu, Neel Sundaresan, Nan Duan
| Challenge: | Pre-trained code intelligence models ignore the execution trace and only rely on source code and syntactic structures to understand code execution. |
| Approach: | They develop a mutation-based data augmentation technique to create a Python dataset and task for code execution that challenges existing models. |
| Outcome: | The proposed model outperforms existing models on code execution and shows its potential for zero-shot code-to-code search and text-to code generation. |
Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents (2026.acl-long)
Copied to clipboard
Ziyi Wang, Yuxuan Lu, Yimeng Zhang, Pei Chen, Ziwei Dong, Jing Huang, Jiri Gesi, Xianfeng Tang, Chen Luo, Qun Liu, Yisi Sang, Hanqing Lu, Manling Li, Jin Lai, Dakuo Wang
| Challenge: | Tool-calling agents are increasingly deployed in real-world customer-facing workflows . but most studies on tool-callers focus on idealized settings with general, fixed, and well-specified tasks. |
| Approach: | They propose a tool-calling agent-based data pipeline that converts trajectories into user-facing tasks with controlled intent adaptations. |
| Outcome: | The proposed pipeline can be used to study tool use under three scenarios. |
LatticeGen: Hiding Generated Text in a Lattice for Privacy-Aware Large Language Model Generation on Cloud (2024.findings-naacl)
Copied to clipboard
Mengke Zhang, Tianxing He, Tianle Wang, Lu Mi, Niloofar Mireshghallah, Binyi Chen, Hao Wang, Yulia Tsvetkov
| Challenge: | Currently, the server controls the generated text, but users can't keep it private . prompted generation is a common interaction paradigm for large language models on cloud . |
| Approach: | They propose a protocol where the server handles most of the computation while the client controls the sampling operation. |
| Outcome: | The proposed protocol protects both prompt and generation under strong attacks. |
CLaSp: In-Context Layer Skip for Self-Speculative Decoding (2025.acl-long)
Copied to clipboard
Longze Chen, Renke Shan, Huiming Wang, Lu Wang, Ziqiang Liu, Run Luo, Jiawei Wang, Hamid Alinejad-Rokny, Min Yang
| Challenge: | Existing methods for drafting Large Language Models require additional modules to be trained, which can be challenging to implement and ensure compatibility across various LLMs. |
| Approach: | They propose an in-context layer-skipping strategy for self-speculative decoding that uses a plug-and-play mechanism to skip intermediate layers of the verify model to construct a compressed draft model. |
| Outcome: | The proposed method achieves a speedup of 1.3 1.7 on LLaMA3 series models without altering the original distribution of the generated text. |
ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have focused on the development of semantic parsers within the framework of cross-domain analysis. |
| Approach: | They propose a method to generate auto-CoT exemplars using ACT-SQL and extend it to multi-turn text-to-Sql tasks. |
| Outcome: | The proposed method achieves SOTA performance on the Spider dev set among existing in-context learning approaches. |
Industry Scale Semi-Supervised Learning for Natural Language Understanding (2021.naacl-industry)
Copied to clipboard
| Challenge: | Obtaining human annotation is expensive and time-consuming process. |
| Approach: | They propose a semi-supervised learning pipeline which leverages millions of unlabeled examples to improve natural language understanding tasks. |
| Outcome: | The proposed pipeline can be used to improve natural language understanding tasks. |
SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)
Copied to clipboard
Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen
| Challenge: | Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities. |
| Approach: | They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance. |
| Outcome: | The proposed method achieves a superior balance between downstream learning and general capability retention. |
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking (2025.acl-long)
Copied to clipboard
Zhuoqun Li, Haiyang Yu, Xuanang Chen, Hongyu Lin, Yaojie Lu, Fei Huang, Xianpei Han, Yongbin Li, Le Sun
| Challenge: | Existing studies in retrieval-augmented generation (RAG) do not sufficiently address the design of complex engineering solutions. |
| Approach: | They propose a retrieval-augmented generation system that leverages tree-based exploration and bi-point thinking mechanism to generate reliable solutions. |
| Outcome: | Experiments show that the proposed system achieves state-of-the-art (SOTA) performance on the SolutionBench, highlighting its potential to enhance the automation and reliability of complex engineering solution design in real-world applications. |
When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Key-Value (KV) caching is widely used in large language models to enable long-context inference efficiently, yet its security implications remain underexplored. |
| Approach: | They propose a history-aware, per-head feedback merging strategy that prevents safety degradation while maintaining efficiency. |
| Outcome: | The proposed strategy prevents safety degradation while maintaining efficiency. |
PychoAgent: Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events (2025.emnlp-main)
Copied to clipboard
Mengzhu Liu, Zhengqiu Zhu, Chuan Ai, Chen Gao, Xinghong Li, Lingnan He, Kaisheng Lai, Yingfeng Chen, Xin Lu, Yong Li, Quanjun Yin
| Challenge: | Social media's rich information content and spatiotemporal granularity provide unique opportunities for emotion prediction and management. |
| Approach: | They propose a Psychology-driven generative Agent framework for explainable panic prediction based on emotion arousal theory. |
| Outcome: | The proposed framework improves panic emotion prediction performance by 13% to 21% compared to baseline models. |
Aligning Retrieval with Reader Needs: Reader-Centered Passage Selection for Open-Domain Question Answering (2025.coling-main)
Copied to clipboard
Chunlei Xin, Shuheng Zhou, Xuanang Chen, Yaojie Lu, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun
| Challenge: | Existing retrieval methods aim to gather relevant passages but fail to prioritize consistent and useful information for the reader. |
| Approach: | They propose a novel method which re-ranks passages based on the reader's prediction probability distribution and clusters passage according to the predicted answers. |
| Outcome: | The proposed method improves the quality of evidence passages under zero-shot scenarios. |
Multi-task Learning for Paraphrase Generation With Keyword and Part-of-Speech Reconstruction (2022.findings-acl)
Copied to clipboard
| Challenge: | PGKPR is a deep learning approach to generate paraphrases using key semantics of the source sentence. |
| Approach: | They propose a model with keyword and part-of-speech reconstruction for paraphrase generation using deep learning. |
| Outcome: | The proposed model outperforms comparative models on two commonly-used datasets. |
CLEAR: Can Language Models Really Understand Causal Graphs? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing language models lack a conceptual framework for understanding causal graphs, but there is still potential for improvement. |
| Approach: | They develop a framework to define causal graph understanding by assessing language models’ behaviors through four practical criteria derived from diverse disciplines. |
| Outcome: | The proposed framework defines three complexity levels and encompasses 20 causal graph-based tasks across 20 different levels. |
EasyEA: Large Language Model is All You Need in Entity Alignment Between Knowledge Graphs (2025.findings-acl)
Copied to clipboard
| Challenge: | Entity alignment (EA) aims to identify entities in different knowledge graphs (KGs) that represent the same real-world object. |
| Approach: | They propose an end-to-end EA framework based on large language models that requires no training to implement. |
| Outcome: | The proposed framework significantly reduces the reliance on seed entity pairs while achieving state-of-the-art (SOTA) performance on diverse datasets. |
Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering (2024.findings-acl)
Copied to clipboard
| Challenge: | Domain-specific question answering (QA) requires a comprehensive understanding of a specific domain to answer specialized questions. |
| Approach: | They propose a new alignment objective to align the LLM preference with different human preferences uniformly to optimize LLM performance in real-world, domain-specific QA settings. |
| Outcome: | The proposed pipeline is superior for real-scenario domain-specific question answering with LLMs. |
BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization (P19-1)
Copied to clipboard
| Challenge: | Existing text summarization datasets are compiled from news articles, where summary-worthy content often appears in the beginning of input articles. |
| Approach: | They present a novel dataset, BIGPATENT, consisting of 1.3 million records of U.S. patent documents along with human written abstractive summaries. |
| Outcome: | The proposed dataset is compared with existing summarization datasets and demonstrates that salient content is evenly distributed in the input. |
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. |
LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following (2023.emnlp-main)
Copied to clipboard
| Challenge: | Embodied Instruction Following has shown an impressive success rate when the environment has been seen in training, but when deployed in an unseen environment, it tends to struggle when deployed with an unsightly environment. |
| Approach: | They propose to explicitly align the agent’s hidden states with the instructions via contrastive learning to bridge the semantic gap between high-level language instructions and the agent's low-level action space. |
| Outcome: | The proposed meta-actions achieve a 4.5% success rate in unseen environments compared to a strong multi-modal Transformer baseline . |
Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to track dialogue state are limited due to data sparsity and long dialogues. |
| Approach: | They propose to use the previous dialogue state and current dialogue utterance as input for DST. |
| Outcome: | The proposed approach outperforms existing methods and improves existing ones. |
NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question Answering (2025.acl-long)
Copied to clipboard
Ruisheng Cao, Hanchong Zhang, Tiancheng Huang, Zhangyi Kang, Yuxin Zhang, Liangtai Sun, Hanqi Li, Yuxun Miao, Shuai Fan, Lu Chen, Kai Yu
| Challenge: | Existing approaches to retrieval augmented generation neglect PDF structure and layout . individual PDFs often exceed prompt limits and user queries may span multiple documents. |
| Approach: | They propose a hybrid neural symbolic retrieval framework which combines both paradigms in an interactive process. |
| Outcome: | The proposed framework organizes semi-structured PDF content into relational database and vectorstore . it defeats both RAG and structured baselines on three PDF-based QA datasets . |
EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence (2026.acl-long)
Copied to clipboard
| Challenge: | Ultrasound is the preferred early cancer screening modality due to non-ionizing radiation, cost-effectiveness, and real-time imaging. |
| Approach: | They propose to use ultrasound-tailored vision-language models with a mixture-of-experts architecture to train ultrasound-specific knowledge across seven anatomical systems. |
| Outcome: | The proposed model outperforms Qwen2-VL by 7.58 BLEU-1 and 3.45 ROUGE-1 points in report generation. |
OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue (2023.tacl-1)
Copied to clipboard
| Challenge: | Existing task-oriented dialogue systems lack ontology-aware pretraining methods for task-orientated dialogue. |
| Approach: | They propose an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD) . they propose to pretrain on large-scale contextual text data to bridge the gap between the pretraining method and downstream tasks. |
| Outcome: | The proposed model achieves an exciting boost and obtains competitive performance even without any TOD data on CamRest676 and MultiWOZ benchmarks. |
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design (2026.findings-acl)
Copied to clipboard
Xu Guo, Qiming Ge, Jian Tong, Kedi Chen, Jin Zhang, Xiaogui Yang, Xuan Gao, Haijun Lv, Zhihui Lu, Yicheng Zou, Qipeng Guo
| Challenge: | Existing approaches to RLVR use multiple-choice questions as verifiable rewards . however, not all tasks provide reliable verification . |
| Approach: | They propose a framework that actively constructs high-quality distractors to block elimination shortcuts and promote deep reasoning. |
| Outcome: | The proposed method significantly improves reasoning capabilities of Large Language Models. |
UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on geometry problem solving treats calculation and proving as two specific tasks hindering a deep model to unify reasoning ability on multiple math tasks. |
| Approach: | They propose a large-scale Unified Geometry problem benchmark to unify geometry on multiple math tasks. |
| Outcome: | The proposed framework outperforms the existing model with 5.6% and 3.2% accuracies on calculation and proving problems. |
Real-time Ad Retrieval via LLM-generative Commercial Intention for Sponsored Search Advertising (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for retrieving documents and ads use one-to-few mappings and time-consuming content extraction. |
| Approach: | They propose a framework that leverages LLM-generated commercial intents as an intermediate semantic representation to directly retrieve ads for queries in real-time. |
| Outcome: | The proposed framework has been implemented in a real-world online system, handling daily search volumes in billions. |
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge (2025.emnlp-main)
Copied to clipboard
Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, Kai Shu, Lu Cheng, Huan Liu
| Challenge: | Recent advances in Large Language Models (LLMs) inspire the "LLM-as-a-judge" paradigm . traditional methods of assessment and evaluation fail in dynamic and open-ended scenarios . |
| Approach: | They propose a paradigm where LLMs are leveraged to perform scoring, ranking, or selection for machine learning evaluation scenarios. |
| Outcome: | The proposed model-based judgment and evaluation paradigms are based on large language models and are compared to the current model-driven evaluation paradigm. |
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. |
Nonlinear Structural Equation Model Guided Gaussian Mixture Hierarchical Topic Modeling (2023.acl-long)
Copied to clipboard
| Challenge: | Existing topic models assume that topics are independent and that they are not a tree structure, which complicates the analysis. |
| Approach: | They propose a neural topic model with a Gaussian mixture prior distribution to improve the model’s ability to adapt to sparse data. |
| Outcome: | The proposed model outperforms baseline models on sparse data on a set of widely used datasets and generates more coherent topics and rational topic structures. |
MultiConIR: Towards Multi-Condition Information Retrieval (2025.findings-emnlp)
Copied to clipboard
Xuan Lu, Sifan Liu, Bochao Yin, Yongqi Li, Xinghao Chen, Hui Su, Yaohui Jin, Wenjun Zeng, Xiaoyu Shen
| Challenge: | MultiConIR is a benchmark designed to evaluate retrieval and reranking models under nuanced multi-condition query scenarios. |
| Approach: | They propose a benchmark to evaluate retrieval and reranking models under nuanced multi-condition query scenarios. |
| Outcome: | The proposed benchmark evaluates retrieval and reranking models under nuanced multi-condition query scenarios across five domains. |
Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Chain-of-Thought (CoT) is a key technique for enhancing the performance of Large Language Models. |
| Approach: | They propose a framework that optimizes outputs by utilizing wrong information and multi-perspective verification. |
| Outcome: | The proposed framework surpasses all baselines on 8 datasets and 5 LLMs. |
CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments (2026.acl-long)
Copied to clipboard
Haotian Xu, Yue Hu, Zhengqiu Zhu, Chen Gao, Ziyou Wang, Junreng Rao, Wenhao Lu, Weishi Li, Quanjun Yin, Yong Li
| Challenge: | Existing benchmarks focus on indoor or street settings, overlooking challenges of open-ended urban spaces. |
| Approach: | They propose a benchmark to probe cross-view spatial reasoning capabilities of current VLMs in urban settings. |
| Outcome: | The citycube benchmark examines the performance of current vision-language models in urban environments. |
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. |
TempCompass: Do Video LLMs Really Understand Videos? (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks on video large language models lack a comprehensive feedback on temporal perception ability . current models cannot distinguish between different temporal aspects and are limited in task formats . |
| Approach: | They propose a benchmark to evaluate temporal perception ability of video large language models . they construct conflicting videos that share the same static content but differ in a specific temporal aspect . |
| Outcome: | The proposed benchmarks show that video large language models exhibit poor temporal perception ability. |
Multimodal Procedural Planning via Dual Text-Image Prompting (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Embodied agents have demonstrated performance in following instructions informed by texts and images . however, the potential of models providing useful guidelines for humans to complete tasks remains underexplored . |
| Approach: | They propose a multimodal procedural planning task that generates paired text-image plans . this task provides more complementary and informative guidance than unimodal plans a . authors propose modality prompting methods that leverage zero-shot reasoning ability . |
| Outcome: | The proposed method improves the interaction in dual modalities and provides more information than unimodal plans. |
READoc: A Unified Benchmark for Realistic Document Structured Extraction (2025.findings-acl)
Copied to clipboard
Zichao Li, Aizier Abulaiti, Yaojie Lu, Xuanang Chen, Jia Zheng, Hongyu Lin, Xianpei Han, Shanshan Jiang, Bin Dong, Le Sun
| Challenge: | Document Structured Extraction (DSE) is a field of document structure analysis that aims to extract structured content from raw documents. |
| Approach: | They propose a benchmark to evaluate document structured extraction systems by converting unstructured PDFs into semantically rich Markdown. |
| Outcome: | The proposed benchmark is based on 3,576 diverse and real-world documents from arXiv, GitHub, and Zenodo. |
LearnAct: Few-Shot Mobile GUI Agent with a Unified Demonstration Benchmark (2026.findings-acl)
Copied to clipboard
Guangyi Liu, Pengxiang Zhao, Liang Liu, Zhiming Chen, Yuxiang Chai, Yaozhen Liang, WenHao Wang, Siheng Chen, Zhengxi Lu, Shuai Ren, Hao Wang, Shibo He, Yong Liu, Wenchao Meng
| Challenge: | Mobile GUI agents show promise in automating tasks but face significant generalization challenges in long-tail scenarios. |
| Approach: | They propose a benchmark framework for mobile GUI agents that measures the performance of GUI agents by analyzing their performance. |
| Outcome: | The LearnGUI benchmark outperforms existing methods in offline and online evaluations and demonstrates consistent gains across model architectures. |
YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)
Copied to clipboard
Hu Yiwen, Huatong Song, Jie Chen, Jia Deng, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Yang Lu, Xu Miao, Xin Zhao, Ji-Rong Wen
| Challenge: | prevailing pre-training approaches for large language models involve several complexities. |
| Approach: | They propose a low-cost training recipe and a robust optimization approach to mitigate training instability . they also propose synthesis, curriculum, and data selection pipelines to integrate data . |
| Outcome: | The proposed model achieves top-tier performance among models with similar parameter scale . it is comparable to industry-leading models that require significantly more data . |
DeMAC: Enhancing Multi-Agent Coordination with Dynamic DAG and Manager-Player Feedback (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-agent systems (MAS) powered by large language models struggle to adapt to evolving task dependencies and to handle uncertainties. |
| Approach: | They propose a Dynamic Environment-Aware Manager-Player Agents Coordination framework that enhances multi-agent coordination through long-term strategic planning. |
| Outcome: | The proposed framework outperforms traditional reinforcement learning and human-agent collaboration in the Overcooked simulation. |
Neural Graph Matching Networks for Chinese Short Text Matching (2020.acl-main)
Copied to clipboard
| Challenge: | Chinese word segmentation can be erroneous, ambiguous or inconsistent, causing performance problems. |
| Approach: | They propose a sentence matching framework that uses paired word lattices as input instead of a character sequence. |
| Outcome: | The proposed framework outperforms the state-of-the-art short text matching models on two Chinese datasets. |
Structured Dialogue Policy with Graph Neural Networks (C18-1)
Copied to clipboard
| Challenge: | Recent advances focus on improving DRL-based dialogue policy optimization. |
| Approach: | They propose to design a graph neural network structure that is better suited for dialogue management. |
| Outcome: | The proposed approach outperforms state-of-the-art approaches in 18 tasks of the PyDial benchmark. |
Harnessing LLMs for Temporal Data - A Study on Explainable Financial Time Series Forecasting (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Recent advances in machine learning and artificial intelligence have opened up numerous opportunities and challenges in financial time series forecasting. |
| Approach: | They propose to use Large Language Models for explainable financial time series forecasting to leverage cross-sequence information and extract insights from text and price time series. |
| Outcome: | The proposed model outperforms ARMA-GARCH and gradient-boosting tree models while underperforming on other models. |
Unexpected Phenomenon: LLMs’ Spurious Associations in Information Extraction (2024.findings-acl)
Copied to clipboard
Weiyan Zhang, Wanpeng Lu, Jiacheng Wang, Yating Wang, Lihan Chen, Haiyun Jiang, Jingping Liu, Tong Ruan
| Challenge: | Information extraction (IE) tasks require a limited number of example instructions to achieve effective performance. |
| Approach: | They propose two strategies to find spurious associations in large language models (LLMs) they use forward label extension and backward label validation to leverage extended labels to improve model performance. |
| Outcome: | The proposed methods improve performance on Chinese and English datasets and 9.55%, 11.42%, and 21.27% in F1 scores on SciERC, ACE05, and DuEE datasets. |
Crossroads of Optimization under Uncertainty: How to Choose the Optimal Model (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to Optimization under Uncertainty (OuU) have inherent limitations and advantages. |
| Approach: | They propose a framework that automates the modeling and solving of six types of uncertainty models and generates mapping pairs to explore the potential relationship between optimization problems and optimal models. |
| Outcome: | The proposed framework achieves superior performance even on specific model types, with correlation analysis showing that data scale and specific scenario significantly influence model selection. |
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. |
Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to extract event records from text decompose complex structure prediction task into multiple subtasks. |
| Approach: | They propose a sequence-to-structure generation paradigm that can extract events from text . they propose unified event extraction, constrained decoding algorithm and curriculum learning algorithm . |
| Outcome: | The proposed method can achieve competitive performance using record-level annotations in both supervised learning and transfer learning settings. |
AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation (2024.findings-emnlp)
Copied to clipboard
Jia Fu, Xiaoting Qin, Fangkai Yang, Lu Wang, Jue Zhang, Qingwei Lin, Yubo Chen, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
| Challenge: | Recent advances in Large Language Models have transformed ML/AI development . a reevaluation of AutoML principles for Retrieval-Augmented Generation (RAG) systems is needed. |
| Approach: | They propose a framework for hyper-parameter tuning and a hierarchical MAB method for efficient exploration of large search spaces. |
| Outcome: | The proposed framework outperforms baseline methods in more challenging optimization scenarios. |
ReGLA: Refining Gated Linear Attention (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) are known for their computational and storage requirements due to the quadratic computation complexity of softmax attention. |
| Approach: | They propose to reduce the quadratic computation complexity of softmax attention by using feature maps, normalization and the gating mechanism to improve performance. |
| Outcome: | The proposed model outperforms existing gated linear attention models in extensive tasks including training from scratch and post-linearization with continual pre-training. |
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent work on Text-to-SQL for multi-turn dialogue has attracted great interest . current approaches mostly employ end-to end models and face data sparsity problems . |
| Approach: | They propose a decoupled multi-turn text-to-SQL framework where dialogue context is explicitly solved by an utterance rewrite model and a single-turn Text-toSQl parser are proposed. |
| Outcome: | The proposed method outperforms existing models on SParC and CoSQL datasets without annotated in-domain data. |
A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for document image translation rely on the vanilla encoder-decoder paradigm . a novel dynamic aggregation mechanism is designed to enhance the text semantics in query features toward translation. |
| Approach: | They propose a Query-Response DIT framework that reformulates the DIT task into a parallel response/translation process of multiple queries. |
| Outcome: | The proposed framework improves translation quality on four translation directions on three benchmarks. |
DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)
Copied to clipboard
Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability. |
| Approach: | They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence. |
| Outcome: | The proposed model outperforms baselines on three real-world datasets. |
MoDification: Mixture of Depths Made Easy (2025.naacl-long)
Copied to clipboard
Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song
| Challenge: | Long-context efficiency is a trending topic in large language model (LLM) serving. |
| Approach: | They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory. |
| Outcome: | The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications. |
Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Text summarization is a key natural language generation task, but the high cost of inaccurate summaries raises concerns about the reliability of uncertainty estimation on text summarisation (UE-TS) evaluation methods. |
| Approach: | They propose a UE-TS benchmark that evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets. |
| Outcome: | The proposed benchmark evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets, with human-annotation analysis incorporated where applicable. |
AgentRM: Enhancing Agent Generalization with Reward Modeling (2025.acl-long)
Copied to clipboard
Yu Xia, Jingru Fan, Weize Chen, Siyu Yan, Xin Cong, Zhong Zhang, Yaxi Lu, Yankai Lin, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing LLM-based agents have strong performance on held-in tasks, but their generalizability to unseen tasks remains poor. |
| Approach: | They propose a reward-based generalizable reward model to guide the policy model for effective test-time search. |
| Outcome: | The proposed agentRM outperforms existing agents on held-in tasks by 8.8 points on average. |
HiChunk: Evaluating and Enhancing Retrieval Augmented Generation with Hierarchical Chunking (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation benchmarks for document chunking are inadequate due to evidence sparsity . evaluators are unable to evaluate different chunking methods due to the evidence sparing . |
| Approach: | They propose a QA benchmark for document chunking and a hierarchical document structuring framework for it. |
| Outcome: | The proposed framework improves document chunking quality within reasonable time consumption. |
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. |
MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models generate erroneous information and evaluations fail to assess factual correctness of models. |
| Approach: | They propose to use MoleculeQA to evaluate molecular factual correctness in large language models by organizing molecules into a taxonomy and building QA pairs through human and LLM efforts. |
| Outcome: | The proposed model improves the factual correctness of generated information and enables the development of new models. |
DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction (P19-1)
Copied to clipboard
| Challenge: | Existing methods for labeling relational facts require significant expert labor to write relation-specific patterns, which makes them too sophisticated to generalize quickly. |
| Approach: | They propose a neural pattern diagnosis framework that can summarize and refine relation-specific patterns with human experts in the loop. |
| Outcome: | The proposed framework can summarize and refine high-quality relational patterns from noise data with human experts in the loop. |
Is C4 Dataset Optimal for Pruning? An Investigation of Calibration Data for LLM Pruning (2024.emnlp-main)
Copied to clipboard
Abhinav Bandari, Lu Yin, Cheng-Yu Hsieh, Ajay Jaiswal, Tianlong Chen, Li Shen, Ranjay Krishna, Shiwei Liu
| Challenge: | Existing approaches to prune LLMs rely on the C4 dataset as calibration data . arithmetic datasets perform better than pre-training datasets for pruning, whereas chain-of-thought is only useful on certain tasks. |
| Approach: | They evaluate the selection of calibration data for LLM pruning across a wide range of datasets . they find that C4 is not the optimal calibration data, and that CoT is only useful on certain tasks. |
| Outcome: | The chosen calibration data significantly impacts the performance of pruned LLMs, the authors found . their results shed light on the importance of carefully selecting calibration data for LLM pruning . |
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. |
Summarization as Indirect Supervision for Relation Extraction (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Relation extraction (RE) models rely on training data with expensive annotations . et al., 2018; Zhao e.t al, 2018) . |
| Approach: | They propose a method that converts RE into a summarization formulation by using constraint decoding techniques. |
| Outcome: | The proposed method improves relation extraction models with high-resource and high-contrast inferences. |
Debiasing In-Context Learning by Instructing LLMs How to Follow Demonstrations (2024.findings-acl)
Copied to clipboard
Lvxue Li, Jiaqi Chen, Xinyu Lu, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun
| Challenge: | In-context learning (ICL) has gained considerable attention due to its data efficiency and task adaptability. |
| Approach: | They propose to de-biase demonstration bias in in-context learning by focusing on semantic ambiguity induced by demonstrations and reducing the semantic hazard. |
| Outcome: | The proposed methods significantly improve performance on six datasets. |
Large Language Models Meet NL2Code: A Survey (2023.acl-long)
Copied to clipboard
Daoguang Zan, Bei Chen, Fengji Zhang, Dianjie Lu, Bingchao Wu, Bei Guan, Wang Yongji, Jian-Guang Lou
| Challenge: | generating code from a natural language description is a pressing and significant challenge in code intelligence. |
| Approach: | They propose to survey 27 existing large language models for NL2Code and compare them to humanEval benchmarks. |
| Outcome: | The proposed model is compared with existing models on the HumanEval benchmark. |
SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks. |
| Approach: | They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically. |
| Outcome: | The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios. |
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)
Copied to clipboard
Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie
| Challenge: | Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models. |
| Approach: | They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts. |
| Outcome: | The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings . |
Reflective RAG: Self-Evaluation Driven Strategy Optimization in Agentic Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent agentic RAG systems lack the capacity to evaluate the utility of retrieved information, leading to brittle reasoning and suboptimal decision-making. |
| Approach: | They propose a framework that integrates self-evaluation to dynamically optimize retrieval and generation strategy. |
| Outcome: | The proposed framework outperforms strong agentic baselines on five knowledge-intensive QA benchmarks and improves training stability and generalization to multi-hop reasoning tasks. |
Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)
Copied to clipboard
Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang
| Challenge: | Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking. |
| Approach: | They propose an iterative adversarial training method that incorporates three key innovations to address these challenges. |
| Outcome: | Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%. |
Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made significant advancements but can be misused to generate harmful content. |
| Approach: | They propose a Robustly Aligned LLM to defend against alignment-breaking attacks by retraining existing LLMs and using adversarial or handcrafted jailbreaking prompts. |
| Outcome: | The proposed model reduces attack success rates from nearly 100% to around 10% or less. |
SAM3-I: Segment Anything with Instructions (2026.acl-long)
Copied to clipboard
Jingjing Li, Yue Feng, Yuchen Guo, Jincai Huang, Wei Ji, Qi Bi, Yongri Piao, Miao Zhang, Xiaoqi Zhao, Qiang Chen, Shihao Zou, Huchuan Lu, Li Cheng
| Challenge: | Existing methods for concept-level grounding and instruction-level reasoning use coarse representations and iterative mask filtering. |
| Approach: | They propose an instruction-following extension of the Segment Anything Model 3 family that unifies concept-level grounding and instruction-level reasoning within a single segmentation framework. |
| Outcome: | Experiments show that SAM3-I achieves appealing performance across referring and reasoning-based segmentation while maintaining its strong concept recall ability. |
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (2025.findings-acl)
Copied to clipboard
Xin Men, Mingyu Xu, Qingyu Zhang, Qianhao Yuan, Bingning Wang, Hongyu Lin, Yaojie Lu, Xianpei Han, Weipeng Chen
| Challenge: | Recent studies have identified significant redundancy in large language models . quantization and pruning are two methods that reduce computational resources . |
| Approach: | They propose simple pruning methods that prune redundant layers based on their BI scores. |
| Outcome: | The proposed pruning methods demonstrate superior performance over previous pruning methods. |
Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training (2020.coling-main)
Copied to clipboard
| Challenge: | Unsupervised neural machine translation (UNMT) has attracted great interest in the machine translation community. |
| Approach: | They propose to explicitly take noisy data into consideration to improve the robustness of UNMT based systems. |
| Outcome: | The proposed methods significantly improved the robustness of the conventional UNMT systems in noisy scenarios. |
Task-Agnostic Detector for Insertion-Based Backdoor Attacks (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for textual backdoor detection are task-specific and less effective beyond sentence classification. |
| Approach: | They propose a task-agnostic method for backdoor detection that leverages final layer logits and an efficient pooling technique. |
| Outcome: | TABDet can jointly learn from diverse task-specific models, demonstrating superior detection efficacy over traditional methods. |
Miracle: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Personalized dialogue systems aim to endow the chatbot agent with more anthropomorphic traits for human-like interactions. |
| Approach: | They propose a method to generate personalized dialogues using latent-space energy-based models by using a latent space energy-model. |
| Outcome: | The proposed method outperforms baselines in personality controllability and response quality. |
Task-Related In-Context Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Standard in-context learning assumes identical output spaces between test and retrieval datasets . however, in practice, these datasets can be fully aligned, partially alignes, or fully disjoint in label space . |
| Approach: | They propose a framework for in-context learning under output-space mismatch . they identify demonstrations relevant to the test label space via a Bayesian probabilistic criterion . |
| Outcome: | The proposed framework achieves state-of-the-art results across three LLMs, three task types, and four datasets. |
Multiple Text Style Transfer by using Word-level Conditional Generative Adversarial Network with Two-Phase Training (D19-1)
Copied to clipboard
| Challenge: | Generative adversarial network (GAN) is a popular model for text style transfer . but, training GAN often suffers from mode collapse problem, which causes that the transferred text is little related to the original text. |
| Approach: | They propose a non-parallel text style transfer model with a word-level conditional architecture and a two-phase training procedure to maintain style-unrelated words while changing others. |
| Outcome: | The proposed model outperforms state-of-the-art models on three real-world datasets in transfer accuracy and fluency. |
PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing likelihood-based methods for detecting pretraining data are limited in black-box, zero-shot settings. |
| Approach: | They propose a training-free and plug-and-play framework that reweights token-level scores to amplify distinct signals from early positions while suppressing noise from later ones. |
| Outcome: | The proposed framework amplifys signals from early positions while suppressing noise from later positions. |
From Generalist to Specialist: A Survey of Large Language Models for Chemistry (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on pretraining of LLMs on extensive web-based texts are insufficient for advanced scientific discovery, especially in chemistry. |
| Approach: | They outline methodologies for incorporating domain-specific chemistry knowledge and multi-modal information into LLMs and conceptualize chemistry LLM agents using chemistry tools. |
| Outcome: | The proposed models are based on domain-specific chemistry knowledge and multi-modal information and are capable of accelerating scientific research. |
LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization (2026.findings-acl)
Copied to clipboard
Jiaqi Tang, Yu Xia, Yi-Feng Wu, Yuwei Hu, Chen Yuhui, Qing-Guo Chen, Xiaogang Xu, Xiangyu Wu, Hao LU, Yanqing Ma, Shiyin Lu, Qifeng Chen
| Challenge: | Existing strategies for spatial localization are limited due to their limited capacity to perceive positional data. |
| Approach: | They propose a location-based approach that leverages locational data to optimize interaction preferences. |
| Outcome: | The proposed approach achieves SOTA results across offline benchmarks and real-world evaluations. |
Handling Missing Entities in Zero-Shot Named Entity Recognition: Integrated Recall and Retrieval Augmentation (2025.naacl-long)
Copied to clipboard
| Challenge: | Zero-shot Named Entity Recognition (ZS-NER) aims to recognize entities in unseen domains without specific annotated data. |
| Approach: | They propose a novel two-stage framework leveraging large language model techniques to improve the ZS-NER’s recall rate. |
| Outcome: | The proposed framework improves the ZS-NER’s recall rate and accuracy by incorporating a large language model. |
UER: An Open-Source Toolkit for Pre-training Models (D19-3)
Copied to clipboard
Zhe Zhao, Hui Chen, Jinbin Zhang, Xin Zhao, Tao Liu, Wei Lu, Xi Chen, Haotang Deng, Qi Ju, Xiaoyong Du
| Challenge: | Existing work on pre-training models have shown that it is important to use a framework to deploy various pre- training models efficiently. |
| Approach: | They propose an assemble-on-demand pre-training toolkit that assembles pre-trained models on demand and encapsulates them with rich modules. |
| Outcome: | The proposed framework can reproduce state-of-the-art models or develop models that remain unexplored. |
SELF-GUARD: Empower the LLM to Safeguard Itself (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent studies have investigated methods to improve the safety of large language models (LLMs) safety training involves fine-tuning the LLM with adversarial samples, which activate the LRM’s capabilities against jailbreak. |
| Approach: | They propose a safety training approach that integrates safety training and safeguards to train the LLM to perform harmfulness detection on its own outputs. |
| Outcome: | The proposed method reduces harmful output and adds a [harmful] or [harmless] tag to the end of the LLM's response. |
Towards Universal Dialogue State Tracking (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to dialogue state tracking are difficult to scale to large dialogue domains. |
| Approach: | They propose a universal dialogue state tracker that is independent of the number of values and shares parameters across all slots. |
| Outcome: | The proposed system significantly outperforms state-of-the-art approaches on two datasets. |
Large Dual Encoders Are Generalizable Retrievers (2022.emnlp-main)
Copied to clipboard
Jianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai, Gustavo Hernandez Abrego, Ji Ma, Vincent Zhao, Yi Luan, Keith Hall, Ming-Wei Chang, Yinfei Yang
| Challenge: | Experimental results show that dual encoders outperform sparse and dense retrievers on the BEIR dataset significantly. |
| Approach: | They challenge belief that bottleneck layer is too limited for out-of-domain generalization . they scale up the model while keeping bottleneck as a single dot-product with a fixed size . |
| Outcome: | The proposed model outperforms sparse and dense retrievers on the BEIR dataset significantly. |
User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems (2025.acl-industry)
Copied to clipboard
Jianling Wang, Yifan Liu, Yinghao Sun, Xuejian Ma, Yueqi Wang, He Ma, Zhengyang Su, Minmin Chen, Mingyan Gao, Onkar Dalal, Ed H. Chi, Lichan Hong, Ningren Han, Haokai Lu
| Challenge: | Large Language Models (LLMs) can be used to broaden user experiences beyond established preferences and reinforce feedback loops. |
| Approach: | They propose a hierarchical approach that combines hierarchic planning with LLM inference-time scaling to improve recommendation relevancy without compromising novelty. |
| Outcome: | The proposed approach shows significant gains in both user satisfaction and exploration diversity. |
VoxMind: An End-to-End Agentic Spoken Dialogue System (2026.acl-long)
Copied to clipboard
Tianle Liang, Yifu Chen, Shengpeng Ji, Yijun Chen, Zhiyang Jia, Jingyu Lu, Fan Zhuo, Xueyi Pu, Yangzhuo Li, Zhou Zhao
| Challenge: | Existing research on end-to-end spoken dialogue models has focused on core perception and generation, with limited exploration of tool-augmented extensions. |
| Approach: | They propose a framework to equip end-to-end spoken dialogue models with comprehensive agentic abilities by leveraging a 470-hour AgentChat dataset. |
| Outcome: | The proposed framework outperforms Gemini-2.5-Pro on spoken agent tasks while maintaining general conversational quality. |
Empowering Psychotherapy with Large Language Models: Cognitive Distortion Detection through Diagnosis of Thought Prompting (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing systems for mental health support are shallow and heuristic, e.g., analyzing emotions and generating comforting responses. |
| Approach: | They propose to use cognitive distortion detection to perform diagnosis on the patient’s speech via three stages: subjectivity assessment to separate the facts and the thoughts; contrastive reasoning to elicit the reasoning processes supporting and contradicting the thoughts and schema analysis to summarize the cognition schemas. |
| Outcome: | The proposed system improves on ChatGPT for cognitive distortion detection while generating high-quality rationales approved by human experts. |
TernaryBERT: Distillation-aware Ultra-low Bit BERT (2020.emnlp-main)
Copied to clipboard
| Challenge: | Transformer-based pre-training models like BERT are computationally expensive and limited to resource-constrained devices. |
| Approach: | They propose a method which ternarizes the weights in a fine-tuned BERT model. |
| Outcome: | The proposed method outperforms the other methods on the GLUE and SQUAD benchmarks while being 14.9x smaller. |
More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling (2024.findings-naacl)
Copied to clipboard
Bingsheng Yao, Guiming Chen, Ruishi Zou, Yuxuan Lu, Jiachen Li, Shao Zhang, Yisi Sang, Sijia Liu, James Hendler, Dakuo Wang
| Challenge: | Existing studies on LLM prompting focus on selecting a better set of data samples inside one single prompt input, but why not design and leverage multiple ICL prompts together to further improve the LLM’s performance? |
| Approach: | They propose a low-resource LLM prompting technique to optimize the construction of multiple ICL prompt inputs to produce confident predictions. |
| Outcome: | The proposed technique can produce confident predictions by optimizing the construction of multiple ICL prompt inputs on four NLI datasets and one QA dataset. |
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)
Copied to clipboard
Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li
| Challenge: | Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities. |
| Approach: | They propose a comprehensive benchmark covering 29 languages, built on an English benchmark. |
| Outcome: | The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark. |
Multilingual Language Model Pretraining using Machine-translated Data (2025.emnlp-main)
Copied to clipboard
Jiayi Wang, Yao Lu, Maurice Weber, Max Ryabinin, David Ifeoluwa Adelani, Yihong Chen, Raphael Tang, Pontus Stenetorp
| Challenge: | Existing methods for collecting and filtering multilingual web data lead to most languages lagging behind English performance due to the Internet's English-centric nature. |
| Approach: | They propose to translate a high-quality English web corpus into nine languages and pretrain a 1.3B-parameter model on it. |
| Outcome: | The proposed model matches or outperforms multilingual LLMs of similar size across Non-English understanding and reasoning tasks despite being trained on an order of magnitude less data. |
EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated strong machine translation capabilities for English-centric language pairs but underperform in direct non-English (x2x) translation. |
| Approach: | They propose a synthetic data generation framework that leverages models’ established English-to-x (en2x) capabilities by extending English parallel corpora into omnidirectional datasets and developing an English-referenced quality evaluation proxy. |
| Outcome: | The proposed framework achieves significant improvement across 72 x2x directions while generalizing to enhance en2x performance. |
CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to role-playing language models rely on prompt engineering or supervised fine-tuning to emulate character behaviors but neglect the underlying cognitive mechanisms driving these behaviors. |
| Approach: | They propose a novel RPLA adopting a cognize-then-respond reasoning paradigm that leverages dual cognition for more contextually grounded and psychologically coherent responses. |
| Outcome: | The proposed RPLA outperforms baselines and generalizes effectively across diverse role-playing tasks. |
On the Representation Geometry of LoRA Model Merging (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for low-rank Adaptation (LoRA) fine-tuning focus on globally shared structure . combining SVD with CUR improves performance of LoRA model merging . |
| Approach: | They propose a training-free method that combines SVD and CUR decomposition to improve LoRA merging performance. |
| Outcome: | The proposed procedure improves on vision and language benchmarks. |
TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current RAG systems concatenate and process numerous retrieved document chunks for prefill . this leads to significant latency in time-to-first-token (TTFT) Experimental results demonstrate that TurboRAG reduces TTFT by up to 9.4x compared to the conventional RAG system. |
| Approach: | They propose a hybrid offline-online paradigm that precomputes chunk-level key-value caches and stitches them together at inference time using independent–attention and reorderedRoPE techniques. |
| Outcome: | Experimental results show that TurboRAG reduces TTFT by 9.4x compared to the conventional RAG systems . long concatenated contexts consume disproportionate GPU memory, limiting throughput . |
CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies on hallucinations in large language models are limited to a single scenario, either cross-lingual or cross-modal. |
| Approach: | They propose a joint Cross-lingual and Cross-modal hallucinations benchmark to fill this gap . they incorporate cross-lingual, cross-modal scenarios to assess hallucinic capabilities . |
| Outcome: | The proposed benchmark incorporates both cross-lingual and cross-modal hallucination scenarios to assess the cross-linguistic and crossmodal capabilities of LLMs. |
Beyond the Context Window: Scaling Agentic RL via End-to-end Optimized Context Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reinforcement learning pipelines suffer from degraded instruction following, excessive rollout costs, and strict context limits. |
| Approach: | They propose a reinforcement learning (RL) fine-tuning of large language model (LLM) agents for long-horizon multi-turn tool use where context length quickly becomes a bottleneck. |
| Outcome: | The proposed framework improves the success rate while maintaining the same or even lower working context length compared to baselines. |
Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Multimodal Large Language Models have raised serious safety concerns. |
| Approach: | They propose a method for manipulating the output preference of MLLMs using a preference hijacked image. |
| Outcome: | The proposed method works at inference time and requires no model modifications. |
Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs? (2025.findings-acl)
Copied to clipboard
Qingyuan Liang, Zhao Zhang, Zeyu Sun, Zheng Lin, Qi Luo, Xiao Yueyi, Yizhou Chen, Yuqun Zhang, Haotian Zhang, Lu Zhang, Chenbin Chenbin, Yingfei Xiong
| Challenge: | Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance. |
| Approach: | They develop a series of billion-scale grammar-based code representations that incorporate grammar rules into the code generation process. |
| Outcome: | Experiments on HumanEval and MBPP show that grammar-based representations reduce syntax errors and improve performance even in billion-scale models. |
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)
Copied to clipboard
Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu
| Challenge: | Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent. |
| Approach: | They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs. |
| Outcome: | The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models. |
Xinference: Making Large Model Serving Easy (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Open-source large models are rapidly catching up with the closed-source models . however, many current inference tools are not as simple and convenient to use. |
| Approach: | They develop an open-source library to simplify the deployment and management of large models. |
| Outcome: | The proposed library outperforms open-source models and offers high throughput and low latency. |
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. |
Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning (2025.emnlp-main)
Copied to clipboard
Senjie Jin, Lu Chen, Zhiheng Xi, Yuhui Wang, Sirui Song, Yuhao Zhou, Xinbo Zhang, Peng Sun, Hong Lu, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing work focuses on enabling models to generate natural language chain-of-thought rationales or leverage executable and verifiable code, such as Python. |
| Approach: | They propose a novel training pipeline that integrates sequential P-CoT and N-Co T generation and a subtask hybrid training strategy to facilitate natural language transferability. |
| Outcome: | The proposed training pipeline improves both N-CoT and P-Co T performance over the RL baseline. |
Towards Preference Following in Tool Calling Language Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Currently, large language model (LLM)-based agents can't follow user preferences when calling tools. |
| Approach: | They propose a benchmark to evaluate agents' ability to identify personalized user preferences from interaction histories and to adhere to these preferences when calling tools. |
| Outcome: | The proposed model achieves 51.16% accuracy on the APOLLO benchmark, while GPT-4o achieves only 51.13% accuracy. |
WebSRC: A Dataset for Web-Based Structural Reading Comprehension (2021.emnlp-main)
Copied to clipboard
| Challenge: | Using a web page and a question, a machine can't understand the contents of web pages. |
| Approach: | They propose a novel dataset for web-based structural reading comprehension that consists of 400K question-answer pairs and a dataset of 6.4K web pages. |
| Outcome: | The proposed dataset consists of 400K question-answer pairs, collected from 6.4K web pages with corresponding HTML source code, screenshots, and metadata. |
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that TESTA reduces the number of visual tokens by 75% and thus accelerates video encoding. |
| Approach: | They propose a method to condense video semantics by aggregating similar frames and patches within each frame. |
| Outcome: | The proposed method reduces visual tokens by 75% and accelerates video encoding. |
H-MAS: Hierarchical Multi-Agent Scheduling for Multi-Tenant LLM Serving (2026.findings-acl)
Copied to clipboard
Yuhan Liu, Cong Xu, Qi Jia, Yihua Wang, Feiyu Chen, Liang Jin, Lu Liu, Yaqian Zhao, Yuting Ding, Xiang Li
| Challenge: | Multi-tenant Model-as-a-Service (MaaS) workloads exhibit non-stationarity across multiple time scales . existing request schedulers often rely on a fixed policy that remains unchanged at runtime . |
| Approach: | They propose a hierarchical multi-agent scheduler that operates in a layered closed loop . they propose to maintain 1.2–3.0 higher Goodput than SGLang and vLLM . |
| Outcome: | Experiments show that H-MAS achieves 1.2–3.0 higher Goodput than SGLang and vLLM . it maintains more stable QoS under diverse request lengths and heterogeneous SLO targets . |
ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary (2025.coling-main)
Copied to clipboard
| Challenge: | Literature review is an indispensable step in the research process, but literature summary is challenging and time consuming. |
| Approach: | They propose an LLM agent with human workflow guidance for comparative literature summary . they use a human workflow to extract key elements from relevant literature and generate summaries . |
| Outcome: | The proposed method outperforms the CoT model in several dimensions. |
Graph-based Relation Mining for Context-free Out-of-vocabulary Word Embedding Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing word embedding methods fail to model complex word formation well. |
| Approach: | They propose a graph-based relation mining method for OOV word embedding learning that can infer high-quality embeddables for OV words through passing and aggregating semantic attributes and relational information in the WRG. |
| Outcome: | The proposed method outperforms state-of-the-art models on both intrinsic and downstream tasks when faced with OOV words. |
Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)
Copied to clipboard
Tianrui Wang, Ziyang Ma, Yizhou Peng, Haoyu Wang, Zhikang Niu, Zikang Huang, Yihao Wu, Yi-Wen Chao, Yu Jiang, Yuheng Lu, Guanrou Yang, Xuanchen Li, Hexin Liu, Chunyu Qiang, Cheng Gong, Yifan Yang, Tianchi Liu, Junyu Wang, Nana Hou, Meng Ge, Fuming You, Yang Wei, Zhongqian Sun, Hu Haifeng, Xiaobao Wang, Eng Siong Chng, Xie Chen, Longbiao Wang, Jianwu Dang
| Challenge: | Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level. |
| Approach: | They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context. |
| Outcome: | The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set. |
InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions (2024.naacl-long)
Copied to clipboard
| Challenge: | In order to perform downstream tasks, Large Language Models (LLMs) need continual adaptation without catastrophic forgetting. |
| Approach: | They propose a new paradigm that allows for continual adaptation without catastrophic forgetting . they propose to replay previous data based on task similarity with instructions . |
| Outcome: | The proposed method improves performance over 16 tasks with different training orders. |
CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factors (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing LLMs rely on surface-level similarity or manual heuristics to evaluate personalization . Existing evaluation protocols for personalization are lacking sufficient data-driven validation. |
| Approach: | They propose a benchmark to assess personalization by mining CIPDs to quantify individual preferences. |
| Outcome: | The proposed benchmark provides a more comprehensive and discriminative standard than generic metrics. |
Seg2Act: Global Context-aware Action Generation for Document Logical Structuring (2024.emnlp-main)
Copied to clipboard
Zichao Li, Shaojie He, Meng Liao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Yanxiong Lu, Xianpei Han, Le Sun
| Challenge: | Document logical structuring is crucial for document intelligence due to the complexity of text segment dependencies in the document. |
| Approach: | They propose an end-to-end, generation-based method for document logical structuring that generates the action sequence via a global context-aware generative model and updates its global context and current logical structure based on the generated actions. |
| Outcome: | Experiments on ChCatExt and HierDoc datasets show that Seg2Act performs better than previous methods in both supervised and transfer learning settings. |
Towards Interpretable Clinical Diagnosis with Bayesian Network Ensembles Stacked on Entity-Aware CNNs (2020.acl-main)
Copied to clipboard
| Challenge: | a novel framework for text-based diagnosis of diseases requires appropriate balance between accuracy and interpretability. |
| Approach: | They propose a framework that stacks Bayesian Network Ensembles on top of CNN to build an accurate yet interpretable diagnosis system. |
| Outcome: | The proposed framework outperforms the previous automatic diagnosis methods in accuracy performance and the diagnosis explanation of the framework is reasonable. |
SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing sentence embedding methods rely on fixed prompt templates or involve modifications to the model architecture, compromising its generative capabilities. |
| Approach: | They propose a sentence-level direct preference optimization approach that boosts the sentence representations while preserving the generative ability of LLMs. |
| Outcome: | The proposed method improves representations of semantically meaningful vectors without sacrificing generation capability. |
Symbolization, Prompt, and Classification: A Framework for Implicit Speaker Identification in Novels (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for speaker identification in novel dialogues are limited to handling explicit narrative patterns and complex cases. |
| Approach: | They propose a framework which identifies implicit speakers in novels via symbolization, prompt, and classification. |
| Outcome: | The proposed framework outperforms existing methods by 4.8% accuracy on the web novel collection, which reduces 47% of speaker identification errors, and outperfies the emerging ChatGPT. |
Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions (2026.acl-long)
Copied to clipboard
Boyan Duan, Xiao Liang, Shuai Lu, Yaoxiang Wang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Mao Yang, Weizhu Chen, Yeyun Gong
| Challenge: | Existing methods for geometry theorem proving in Euclidean geometry are challenging and require a neural network to perform. |
| Approach: | They propose a method for adding auxiliary points in geometry that runs on CPUs without relying on neural network-based inference. |
| Outcome: | The proposed method achieves silver-medal-level human performance on IMO-30 benchmark. |
WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization (2026.acl-long)
Copied to clipboard
Kunpeng Kang, Shuaimin Li, Kaiyuan Zhang, Luyang Zhang, Jiasheng Si, Bing Xu, Kehai Chen, Muyun Yang, Wenpeng Lu
| Challenge: | Word sense disambiguation (WSD) is a fundamental task in natural language processing. |
| Approach: | They propose a training framework for generative WSD with chain-of-thought (CoT) and preference optimization. |
| Outcome: | The proposed framework achieves significant performance gains on rare and unseen settings and exhibits strong generalization in standard evaluation settings. |
Uncertainty Estimation on Sequential Labeling via Uncertainty Transmission (2024.findings-naacl)
Copied to clipboard
| Challenge: | Named entity recognition tasks are often suboptimal for NER . previous work focused on UE-NER, which estimates uncertainty scores for ner . |
| Approach: | They propose to use a Sequential Labeling Posterior Network to estimate uncertainty for NER . they propose to consider wrong-span cases and to evaluate the specificity of wrong-pan cases. |
| Outcome: | The proposed system improves on three datasets and AUPR on MIT-Restaurant datasets. |
Improving MLLM’s Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency (2025.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) have shown strong performance in document image tasks, especially Optical Character Recognition (OCR). However, they struggle with Document Image Machine Translation (DIMT), which requires handling both cross-modal and cross-lingual challenges. |
| Approach: | They propose a novel fine-tuning paradigm that allows the model to generate OCR text before producing translation text, which allows it to leverage its strong monolingual OCR ability while learning to translate text across languages. |
| Outcome: | The proposed model can leverage its strong monolingual OCR ability while learning to translate text across languages. |
M-CNER: A Corpus for Chinese Named Entity Recognition in Multi-Domains (L18-1)
Copied to clipboard
| Challenge: | NER is one of the most important natural language processing tasks. |
| Approach: | They propose to annotate sentences from human-computer interaction, social media, and e-commerce using two rounds of annotation. |
| Outcome: | The proposed system performs the best on all the data sets. |
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings (2025.acl-long)
Copied to clipboard
| Challenge: | Existing low-resource security alignment methods struggle with the security risks posed by additional modalities. |
| Approach: | They propose to use multimodal datasets to enhance safety alignment but it is costly to construct these datasets. |
| Outcome: | Experiments on image, video, and audio-based MLLMs show that the proposed method can synthesize a high-quality embedding on a single RTX3090 GPU within 24 seconds. |
D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing human-machine dialogue systems are not able to provide diagnostic information for depression diagnosis due to stigma associated with mental illness. |
| Approach: | They propose to construct a Chinese Dialogue Dataset for depression-diagnosis-oriented chat based on clinical depression diagnostic criteria. |
| Outcome: | The proposed system can be used to diagnose depression using a Chinese Dialogue Dataset. |
AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models (2024.findings-naacl)
Copied to clipboard
Wanjun Zhong, Ruixiang Cui, Yiduo Guo, Yaobo Liang, Shuai Lu, Yanlin Wang, Amin Saied, Weizhu Chen, Nan Duan
| Challenge: | Traditional benchmarks for evaluating foundation models often fail to accurately represent their general abilities for human-centric tasks. |
| Approach: | They propose a bilingual benchmark to assess foundation models in the context of human-centric standardized exams such as college entrance exams, law school admission tests, and math competitions. |
| Outcome: | The proposed benchmark exceeds the average human performance on SAT, LSAT, and math competitions with 95% accuracy and 92.5% on the Chinese college entrance English exam. |
Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Recent studies suggest that large language models can transfer skills learned in one language to others, but internal mechanisms behind this ability remain unclear. |
| Approach: | They find that LLMs map semantically identical inputs from different languages into a common semantic latent space that allows for consistent processing across languages. |
| Outcome: | The findings highlight the structural evolution of multilingual models during training and scaling up. |
Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation (2026.acl-long)
Copied to clipboard
Jiaju Chen, Yuxuan Lu, Xiaojie Wang, Huimin Zeng, Jing Huang, Jiri Gesi, Ying Xu, Bingsheng Yao, Dakuo Wang
| Challenge: | Existing "LLM-as-a-judge" evaluation frameworks are limited by persona descriptions and are not generalizable to other tasks. |
| Approach: | They propose a framework that can automatically construct multiple evaluator personas with distinct dimensions from relevant text documents and instantiate LLM agents with the persona. |
| Outcome: | The proposed framework can believably simulate human evaluators . it extracts stakeholders' diverse perspectives from the provided research papers and constructs personas for the agents . |
MirrorCAPTCHA: Wild CAPTCHA, Wild Distribution, Wild Web-based Platform Meet Multimodal LLM Agents (2026.acl-long)
Copied to clipboard
Xiangyu Wu, Yuwei Hu, Tianyu Cui, Yueying Tian, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Yang Yang, Jianfeng Lu
| Challenge: | Existing agent benchmarks fail to evaluate an agent's real-world capacity to handle CAPTCHA . Existing benchmarks ignore this practical challenge, failing to evaluate agents' ability to handle complex visual CAPTchas. |
| Approach: | They propose a benchmark annotated with Weighted Pass Rate and a new metric to measure agent's ability to handle CAPTCHA. |
| Outcome: | The proposed benchmark outperforms current state-of-the-art closed-source models on mirrorCAPTCHA and achieves 9.4% higher average weighted pass rate and 2.13% higher average Completion degree. |
AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists (2025.emnlp-main)
Copied to clipboard
Yifei Li, Hanane Nour Moussa, Ziru Chen, Shijie Chen, Botao Yu, Mingyi Xue, Benjamin Burns, Tzu-Yao Chiu, Vishal Dey, Zitong Lu, Chen Wei, Qianheng Zhang, Tianyu Zhang, Song Gao, Xuhui Huang, Xia Ning, Nesreen K. Ahmed, Ali Payani, Huan Sun
| Challenge: | AutoSDT-5K is the only automatically collected and the largest open dataset for data-driven scientific discovery. |
| Approach: | They propose an automatic pipeline that collects high-quality coding tasks in real-world data-driven discovery workflows. |
| Outcome: | The proposed pipeline synthesizes accurate tasks and tasks from a dataset of 5,404 tasks covering four scientific disciplines and 756 Python packages. |
IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Language models have demonstrated their capabilities in storyline creation and human-like character role-playing. |
| Approach: | They propose a director-actor coordinate agent framework that generates drama scripts . framework allows actors to role-play their characters while maintaining plot development . |
| Outcome: | The proposed framework generates drama scripts from a drama plot outline and human actors can play their characters. |
Glyph Enhanced Chinese Character Pre-Training for Lexical Sememe Prediction (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Sememes are defined as the atomic units to describe the semantic meaning of concepts. |
| Approach: | They propose a method which incorporates internal Chinese character information to help sememe prediction. |
| Outcome: | The proposed method outperforms existing non-external information models on howNet, a famous sememe knowledge base. |
From Imitation to Introspection: Probing Self-Consciousness in Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing language models demonstrate impressive abilities in areas like natural language understanding, content creation, and reasoning. |
| Approach: | They propose a definition of self-consciousness for language models and refine ten core concepts by leveraging structural causal games. |
| Outcome: | The proposed definitions are based on structural causal games and ten core concepts. |
Beyond Query Bias: Candidate-Aware Iterative Refinement for Zero-Shot Composed Image Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to retrieve target images suffer from inherent cognitive bias due to unknown candidate distribution. |
| Approach: | They propose a training-free framework that reframes ZS-CIR as a self-correcting process . they propose to use retrieved results as feedback to perceive the candidate distribution . |
| Outcome: | Experiments on public benchmarks show that CoRR outperforms other SOTA methods. |
TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models often underperform due to complex queries, noisy data, and limited numerical capabilities. |
| Approach: | They propose a framework that integrates seamlessly with mainstream LLMs to improve tabular reasoning. |
| Outcome: | The proposed framework outperforms existing methods in state-of-the-art analysis. |
CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing code pre-trained models fail to consider inherent characteristics of codes . Existing methods to interpret code pretrained model fail to take into account inherent characteristics . |
| Approach: | They propose a probing method to quantitatively interpret how CodePTMs attend code structure. |
| Outcome: | The proposed method denoises input code sequences and measures commonality between token-level attention scores and pair-wise distances between corresponding AST nodes. |
Is LLM a Reliable Reviewer? A Comprehensive Evaluation of LLM on Automatic Paper Reviewing Tasks (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing datasets and methods targeting review-related tasks have not thoroughly inspected model's review ability. |
| Approach: | They propose to evaluate GPT-3.5 and GPT-4 on two types of tasks under different settings: the score prediction task and the review generation task. |
| Outcome: | The proposed model can give passable decisions (> 60% accuracy) on single options, but it always makes mistakes. |
Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Defective queries impact the robustness of conversational AI systems such as Alexa, Siri or Google Assistant. |
| Approach: | They propose a Personalized Query Rewriting system that takes into account individual preferences or unique error patterns identified from a user's historical interactions with the conversational AI. |
| Outcome: | The proposed approach has been proven on a large-scale real-world dataset and online A/B experiments. |
Pre-trained Semantic Interaction based Inductive Graph Neural Networks for Text Classification (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for text classification have vanishing or exploding gradients when dealing with long sequences, making it difficult to handle long-distance dependencies. |
| Approach: | They propose a graph neural network based on pre-trained semantic interaction called PaSIG . they construct a text-word heterogeneity graph and use context representation capability . |
| Outcome: | The proposed model outperforms existing methods on five datasets and achieves state-of-the-art performance. |
QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA (2025.findings-emnlp)
Copied to clipboard
Jacob Dineen, Aswin Rrv, Qin Liu, Zhikun Xu, Xiao Ye, Ming Shen, Zhaonan Li, Shijie Lu, Chitta Baral, Muhao Chen, Ben Zhou
| Challenge: | QA-LIGN decomposes monolithic rewards into interpretable principle-specific evaluations . scalar rewards obscure which objectives drive the training signal . |
| Approach: | a new method decomposes monolithic rewards into interpretable principle-specific evaluations . QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate . |
| Outcome: | QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate . the results outperform DPO and GRPO with state-of-the-art reward models given equivalent training . |
WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training (2026.findings-acl)
Copied to clipboard
Yifu Chen, Shengpeng Ji, Qian Chen, Tianle Liang, Yangzhuo Li, Ziqing Wang, Wen Wang, Jingyu Lu, Haoxiao Wang, Xueyi Pu, Fan Zhuo, Zhou Zhao
| Challenge: | End-to-end spoken dialogue models have higher potential ceiling in expressiveness and perceptual ability than cascaded systems. |
| Approach: | They propose a modality-aware adaptive post-training recipe that constrains preference updates to the semantic channel and improves acoustic behavior via explicit anchoring. |
| Outcome: | The proposed model improves speech quality and expressiveness across spoken dialogue benchmarks and architectures. |
Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective (2023.eacl-main)
Copied to clipboard
Zijian Zhang, Chang Shu, Ya Xiao, Yuan Shen, Di Zhu, Youxin Chen, Jing Xiao, Jey Han Lau, Qian Zhang, Zheng Lu
| Challenge: | Recent VSE models combine simple pooling methods with hard triplet loss to improve performance. |
| Approach: | They propose an adaptive pooling strategy that allows the model to learn how to aggregate features through a combination of simple pooling methods. |
| Outcome: | The proposed strategy outperforms current state-of-the-art systems on image-to-text and text-toimage retrieval. |
AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Text summarization tasks employ Pre-trained Language Models (PLMs) to fit diverse datasets. |
| Approach: | They propose a human summarization preference alignment framework to align PLMs with human preferences. |
| Outcome: | The proposed framework narrows the gap between automatic and human evaluations by integrating three components. |
Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features (N19-2)
Copied to clipboard
Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin
| Challenge: | e-commerce companies often have the option of escalating complaints by filing grievances with a government authority . this is detrimental to an ecommerce company, but this problem is challenging to solve by integrating recurrent neural networks with manually-engineered features. |
| Approach: | They propose a model that integrates recurrent neural networks with manually-engineered features to identify cases where the customer expresses such an intent. |
| Outcome: | The proposed model outperforms baseline models and provides better recall and triage for specialized agents. |
QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions (2025.acl-long)
Copied to clipboard
Siyin Wang, Wenyi Yu, Xianzhao Chen, Xiaohai Tian, Jun Zhang, Lu Lu, Yu Tsao, Junichi Yamagishi, Yuxuan Wang, Chao Zhang
| Challenge: | Existing datasets lack comprehensive annotations for speech quality assessment . existing methods lack detailed annotations, resulting in inaccurate evaluations. |
| Approach: | They propose a low-level speech quality assessment dataset incorporating natural language descriptions and a Benchmark to evaluate low- level speech understanding capabilities of auditory large language models. |
| Outcome: | The proposed model can be used to evaluate the low-level speech understanding capabilities of auditory large language models. |
iPET: An Interactive Emotional Companion Dialogue System with LLM-Powered Virtual Pet World Simulation (2025.acl-demo)
Copied to clipboard
Zheyong Xie, Shaosheng Cao, Zuozhu Liu, Zheyu Ye, Zihan Niu, Chonggang Lu, Tong Xu, Enhong Chen, Zhe Xu, Yao Hu, Wei Lu
| Challenge: | Existing approaches to role-playing emotional companion products lack sustained personalization and contextual adaptability, limiting their effectiveness in real-world settings. |
| Approach: | They propose a virtual pet agent that can enhance user engagement through rich, dynamic pet behaviors and interactions tailored to individual preferences. |
| Outcome: | The proposed system has been deployed in a real-world, non-commercial product for 200 days and has demonstrated its effectiveness in practical applications. |
Towards More Accurate Uncertainty Estimation In Text Classification (2020.emnlp-main)
Copied to clipboard
Jianfeng He, Xuchao Zhang, Shuo Lei, Zhiqian Chen, Fanglan Chen, Abdulaziz Alhamadani, Bei Xiao, ChangTien Lu
| Challenge: | Existing models of uncertainty score depend on winning score, which is the maximum probability in a semantic vector. |
| Approach: | They propose to generate accurate uncertainty score by improving the confidence of winning scores by reducing the effect of overconfidence of winning score and considering the impact of different categories simultaneously. |
| Outcome: | The proposed model reduces the effect of overconfidence of winning score and considers impact of different categories of uncertainty simultaneously. |
MCAD: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrieval (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large-scale visual-language pretraining models have shown remarkable capabilities in understanding both vision and language. |
| Approach: | They propose a multi-teacher cross-modality alignment distillation technique to integrate the advantages of single-stream and dual-stream models. |
| Outcome: | The proposed model is lightweight and has only 100M running memory and 8.0ms search latency. |
PIVOINE: Instruction Tuning for Open-world Entity Profiling (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for information extraction focus on a closed-world setting, but PIVOINE is a promising solution to tackle the open-world problem of entity profiling. |
| Approach: | They propose to develop an LLM that performs Open-world Entity Profiling with instruction tuning to extract desirable entity profiles . they construct INSTRUCTOPENWIKI, a substantial instruction-tuning dataset for Open-World Entity Profiles . |
| Outcome: | The proposed model outperforms existing methods and ChatGPT-based baselines on unseen and out-of-ontology cases. |
MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers (2026.acl-long)
Copied to clipboard
Linrui Ma, Chun Hei Lo, Xinyu Wang, Peng Lu, Xihao Yuan, Hanting Chen, Kai Han, Xinghao Chen, Chengjun Zhan, Hanlin xu, Yichun Yin, Lifeng Shang, Feng Wen, Boxing Chen, Yufei Cui
| Challenge: | Existing approaches to improve efficiency often enforce rigid structural constraints such as local attention windows. |
| Approach: | They propose a framework that augments sparse-attention mechanisms with dynamically integrated in-context information through an efficient retrieval system. |
| Outcome: | Empirical results show that MATCH significantly improves the performance of sparse-attention models on synthetic and real-world natural-language tasks. |
Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Speculative decoding uses a small draft model to generate a single input token, instead of sequentially generating tokens until completion. |
| Approach: | They propose a method that generates varying draft models adapted to the input context using simple rules. |
| Outcome: | The proposed method is competitive with the current SOTA for self-speculative decoding while being a truly plug-and-play method. |
CodeV: Issue Resolving with Visual Data (2025.findings-acl)
Copied to clipboard
Linhao Zhang, Daoguang Zan, Quanshun Yang, Zhirong Huang, Dong Chen, Bo Shen, Tianyu Liu, Yongshun Gong, Huang Pengjie, Xudong Lu, Guangtai Liang, Lizhen Cui, Qianxiang Wang
| Challenge: | Large Language Models (LLMs) have expanded to more complex repository-level tasks. |
| Approach: | They propose a first approach to leveraging visual data to enhance the issue-resolving capabilities of Large Language Models (LLMs) they demonstrate the effectiveness of CodeV and provide valuable insights into leveraging visualization to resolve GitHub issues. |
| Outcome: | The proposed approach improves the issue-resolving capabilities of Large Language Models (LLMs) by using visual data. |
Competition-Level Problems are Effective LLM Evaluators (2024.findings-acl)
Copied to clipboard
Yiming Huang, Zhenghao Lin, Xiao Liu, Yeyun Gong, Shuai Lu, Fangyu Lei, Yaobo Liang, Yelong Shen, Chen Lin, Nan Duan, Weizhu Chen
| Challenge: | Large language models (LLMs) have demonstrated impressive reasoning capabilities, yet there is ongoing debate about their capabilities and the potential data contamination problem. |
| Approach: | They propose to evaluate the reasoning capabilities of large language models in solving recent competition-level programming problems in Codeforces. |
| Outcome: | The proposed model has experienced a cliff-like decline in problems after September 2021, which shows the potential data contamination and the challenges for any existing LLM to solve unseen complex reasoning problems. |
ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring (2026.acl-industry)
Copied to clipboard
Deyi Ji, Junyu Lu, Xuanyi Liu, Liqun Liu, Hailong Zhang, Peng Shu, Huan Yu, Jie Jiang, Tianrun Chen, Lanyun Zhu
| Challenge: | Existing regulatory policies create label inconsistencies and reasoning ambiguities in historical datasets. |
| Approach: | They propose a policy-adaptive governance system that enables evolving reinforcement through multi-agent adversarial umpiring. |
| Outcome: | The proposed system outperforms fine-tuning baselines on industrial and public datasets . it enables evolving reinforcement through multi-agent adversarial umpiring . |
More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing systems struggle with multimodal content where the emergent meaning transcends the aggregation of individual modalities. |
| Approach: | They propose a framework to characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion. |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks on H-VLI and on established benchmarks. |
Probing Language Models for Pre-training Data Detection (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown impressive capabilities, while raising concerns about the data contamination due to privacy issues and leakage of benchmark datasets in the pre-training phase. |
| Approach: | They propose to utilize the probing technique to examine the model’s internal activations to detect pre-training data contamination by examining the model's internal activates. |
| Outcome: | The proposed method outperforms baselines and achieves state-of-the-art performance on both WikiMIA and ArxivMIA, with additional experiments confirming its efficacy. |
Sparse Latents Steer Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
Chunlei Xin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Xuanang Chen, Xinyan Guan, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
| Challenge: | In this study, we uncover interpretable latents that govern RAG behavior in large language models . Sparse Autoencoders are used to control large language model (LLM) behavior . |
| Approach: | They leverage Sparse Autoencoders within the LLaMA Scope to uncover latents that govern RAG behaviors. |
| Outcome: | The proposed model can be used to control large language models without architectural modifications. |
ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference (2022.findings-acl)
Copied to clipboard
Kai Hui, Honglei Zhuang, Tao Chen, Zhen Qin, Jing Lu, Dara Bahri, Ji Ma, Jai Gupta, Cicero Nogueira dos Santos, Yi Tay, Donald Metzler
| Challenge: | State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. |
| Approach: | They propose to fine tune a pretrained encoder-decoder model using document to query generation. |
| Outcome: | The proposed model achieves comparable results to more expensive approaches while being 6.8X faster. |
The BQ Corpus: A Large-scale Domain-specific Chinese Corpus For Sentence Semantic Equivalence Identification (D18-1)
Copied to clipboard
| Challenge: | Bank Question corpus is a corpus for sentence semantic equivalence identification (SSEI) because of rich expressions in natural languages, SSEI is really a challenging task. |
| Approach: | They propose to cluster 120,000 question pairs from 1-year online bank custom service logs into stacks by the Word Mover’s Distance (WMD) based Affinity Propagation algorithm to achieve questions with the same intent. |
| Outcome: | The proposed method achieves questions with the same intent by clustering deduplicated questions into stacks by the Word Mover’s Distance (WMD) based Affinity Propagation (AP) algorithm. |
Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25 (2025.emnlp-main)
Copied to clipboard
| Challenge: | Interpretability in information retrieval (IR) models is coarse-grained and poorly understood . a cross-encoder model extracts traditional relevance signals, such as term frequency and inverse document frequency . |
| Approach: | They analyze how a common IR model extracts traditional relevance signals . this is similar to the probabilistic ranking function BM25 . |
| Outcome: | The proposed model extracts traditional relevance signals in early-to-middle layers, similar to BM25 . the model then combine these concepts in later layers, laying the groundwork for future interventions . |
Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)
Copied to clipboard
Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains. |
| Approach: | They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries. |
| Outcome: | The proposed system outperforms baselines in the open domain task-solving benchmark. |
Structured Optimal Brain Pruning for Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing pruning methods for Large Language Models rely on unstructured pruning or require special hardware to accelerate computation. |
| Approach: | They propose a retraining-free structured pruning method called SoBP . they evaluate the effectiveness of SoBP across 14 models from 3 LLM families . |
| Outcome: | The proposed method outperforms current state-of-the-art pruning methods on 8 datasets. |
DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization (D19-1)
Copied to clipboard
| Challenge: | Existing models for natural language video localization are top-down and bottom-up . however, both approaches suffer several limitations, leading to performance degradation . |
| Approach: | They propose a top-down approach for localizing a natural language description in a video sequence . they propose 'DEnse Bottom-Up Grounding' which uses the temporal boundaries of each video frame . |
| Outcome: | The proposed framework matches the speed of top-down models while surpassing the state-of-the-art models. |
SDD: Self-Degraded Defense against Malicious Fine-tuning (2025.acl-long)
Copied to clipboard
| Challenge: | Open-source Large Language Models (LLMs) employ safety alignment methods to resist harmful instructions, but malicious fine-tuning can easily bypass these safeguards. |
| Approach: | They propose a framework to prevent malicious fine-tuning of large language models on harmful data by using alignment methods that encourage them to produce irrelevant responses to harmful prompts. |
| Outcome: | The proposed framework reduces the general capability of the LLM when malicious fine-tuning fails, rendering it incapable of following harmful instructions. |
SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026.acl-long)
Copied to clipboard
Hui Wang, Jinghua Zhao, Yifan Yang, Shujie Liu, Junyang Chen, Yanzhe Zhang, Shiwan Zhao, Jinyu Li, Jiaming Zhou, Haoqin Sun, Yan Lu, Yong Qin
| Challenge: | Existing methods for evaluating the perceptual quality of synthetic speech are limited due to the complexity of perceptual quality factors and the diversity of speech generation tasks. |
| Approach: | They propose a new paradigm for enabling large language models to conduct structured speech quality evaluation using a large-scale dataset. |
| Outcome: | The proposed model performs well across tasks and languages. |
Adversarial Self-Supervised Data-Free Distillation for Text Classification (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge distillation algorithms rely on the accessibility of the training dataset, which may be unavailable due to privacy issues. |
| Approach: | They propose a data-free distillation method for a pre-trained transformer-based model that uses plug & play Embedding Guessing to craft pseudo embeddings from the teacher's hidden knowledge. |
| Outcome: | The proposed method is the first data-free distillation framework designed for NLP tasks. |
MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents (2026.acl-long)
Copied to clipboard
Ruihan Chen, Qiming Li, Xiaocheng Feng, Weihong Zhong, Xiaoliang Yang, Yuxuan Gu, Zekun Zhou, Yunfei Lu, Haoyu Ren, Kun Chen, Dandan Tu, Bing Qin
| Challenge: | Existing GUI benchmarks lack fine-grained diagnostics to identify which capabilities lead to task failures. |
| Approach: | They propose a multilingual P R GUI Benchmark to assess LVLMs' language capabilities . they propose XLI to align non-English hidden states with English ones during inference . |
| Outcome: | The proposed benchmark reveals consistent gaps between English and non-English settings . it reduces the cross-lingual gaps with an average gain of 6.5% in non- English settings compared to static benchmarks . |