Papers by Feng Wang
RETAIL: Towards Real-world Travel Planning for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing travel planning systems assume users provide explicit queries, limiting their practical utility. |
| Approach: | They propose a dataset RETAIL which supports decision-making for implicit queries while covering explicit queries. |
| Outcome: | The proposed model achieves a 1.0% pass rate, suggesting real-world travel planning remains challenging. |
POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge Distillation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Positional bias (PB) manifests as non-uniform sensitivity across contextual locations . previous studies have addressed PB by modifying the underlying architectures or employing extensive contextual awareness training. |
| Approach: | They propose a position-to-position knowledge distillation framework that leverages position-induced disparities to counteract PB. |
| Outcome: | The proposed framework reduces positional bias and improves performance on retrieval and reasoning tasks. |
AdaMix: Adaptive Mixing for Short and Long Reasoning Adapters (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for large reasoning models have improved efficiency but still face limitations such as conflicting objectives and limited adaptability. |
| Approach: | They propose an adaptive reasoning framework that applies a uniform, computation-intensive deep reasoning strategy to all problems. |
| Outcome: | The proposed framework reduces the average response length of DeepSeek-R1-Distill-Qwen-7B by 54.9% while improving accuracy by up to 4.8% on five mathematical datasets. |
CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that rule-based evaluation methods are ineffective for open-ended natural language generation. |
| Approach: | They propose a pointwise generative reward model with a dedicated two-stage rollout method and unified query-based criteria that can be trained with 5.7K high-quality data. |
| Outcome: | The proposed model achieves superior performance on diverse reward model benchmarks, especially in Best-of-N scenarios, and delivers more effective improvements in downstream RL practice. |
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs (2026.acl-long)
Copied to clipboard
Yu Li, Xiaoran Shang, Qizhi Pei, Yun Zhu, Xin Gao, Honglin Lin, Zhanping Zhong, Zhuoshi Pan, Zheng Liu, Xiaoyang Wang, Conghui He, Dahua Lin, Feng Zhao, Lijun Wu
| Challenge: | High-quality post-training data is the primary engine driving LLM capabilities . datasets are often treated as isolated artifacts, overlooking their true developmental context . |
| Approach: | They propose a framework to reconstruct the evolutionary graph of dataset development using data lineage. |
| Outcome: | The proposed framework characterizes domain-specific structural patterns in Math-oriented datasets and general-domain corpora. |
Emotion–Cause Pair Extraction in Conversations via Semantic Decoupling and Alignment (2026.findings-acl)
Copied to clipboard
| Challenge: | Emotion-Cause Pair Extraction in Conversations (ECPEC) aims to identify the set of causal relations between emotion utterances and their triggering causes within a dialogue. |
| Approach: | They propose a framework for Emotion-Cause Pair Extraction in Conversations that decouples emotion-oriented semantics from cause-oriented ones and employs optimal transport to enable many-to-many and globally consistent emotion-cause matching. |
| Outcome: | The proposed framework achieves state-of-the-art on several benchmark datasets. |
DisCo_Speech: Controllable Zero-Shot Speech Generation with A Disentangled Speech Codec (2026.acl-long)
Copied to clipboard
Tao Li, Wenshuo Ge, Zhichao Wang, Zihao Cui, Yong Ma, Yingying Gao, Chao Deng, Shilei Zhang, Junlan Feng
| Challenge: | DisCo-Speech is a zero-shot controllable text-to-speech framework . standard codecs entangle timbre and prosody, which hinders independent control in continuation-based LMs. |
| Approach: | They propose a disentangled speech codec and an LM-based generator to solve this problem . they propose fusion and reconstruction that merges content and prosody into unified tokens . |
| Outcome: | DisCo-Speech achieves competitive voice cloning and superior zero-shot prosody control. |
Exploring Question-Specific Rewards for Generating Deep Questions (2020.coling-main)
Copied to clipboard
| Challenge: | Recent question generation approaches use the sequence-to-sequence framework to optimize the log likelihood of ground-truth questions using teacher forcing. |
| Approach: | They propose to optimize for QG-specific objectives via reinforcement learning to improve question quality. |
| Outcome: | The proposed model improves the fluency, relevance, and answerability of generated questions. |
K-order Ranking Preference Optimization for Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing list-wise methods focus on optimizing list ranking consistency for LLMs to improve ranking abilities. |
| Approach: | They propose to extend the Plackett-Luce model to accommodate top-K ranking by extending the DPO’s Plact-Lucer model to dynamically determine appropriate K for different samples. |
| Outcome: | The proposed model can be extended to accommodate top-K ranking and improve training efficiency. |
Unsupervised Neural Machine Translation with Weight Sharing (P18-1)
Copied to clipboard
| Challenge: | Unsupervised neural machine translation (NMT) is a new approach for machine translation . the model uses only one shared encoder to map pairs of sentences from different languages to a shared-latent space . |
| Approach: | They propose an unsupervised approach which trains the model without labeling data . they propose two independent encoders but share some partial weights to extract high-level representations of input sentences. |
| Outcome: | The proposed approach achieves significant improvements on English-German, English-French and Chinese-to-English translation tasks. |
Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | End-to-end speech-to speech (S2S) dialogue systems face key challenges in incorporating external knowledge into their models. |
| Approach: | They propose a framework that directly retrieves relevant textual knowledge from speech queries. |
| Outcome: | The proposed framework improves the performance of end-to-end speech-tospeech dialogue systems while achieving higher retrieval efficiency. |
Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing work on document visual question answering fails to capture the differences and correlations between elements of a document and associated questions. |
| Approach: | They propose a document-visual question-answering challenge that exploits element-level semantics and employs hierarchical Graph structures to capture differences and correlations between elements. |
| Outcome: | The proposed model surpasses the state-of-the-art method and large language model in terms of Exact Match (EM) metric, demonstrating exceptional effectiveness. |
Enhancing Neural Data-To-Text Generation Models with External Background Knowledge (D19-1)
Copied to clipboard
| Challenge: | Recent neural models for data-to-text generation rely on parallel pairs of data and text to learn writing knowledge. |
| Approach: | They propose to enhance neural models with external knowledge to improve fidelity of generated text. |
| Outcome: | The proposed model improves on Wikipedia infobox-to-text datasets on 21 datasets. |
End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems (2020.emnlp-main)
Copied to clipboard
Siamak Shakeri, Cicero Nogueira dos Santos, Henghui Zhu, Patrick Ng, Feng Nan, Zhiguo Wang, Ramesh Nallapati, Bing Xiang
| Challenge: | Existing approaches for synthetic QA data generation have limited or no success in improving the downstream Reading Comprehension task. |
| Approach: | They propose an end-to-end approach for synthetic QA data generation using a transformer-based encoder-decoder network that is trained end- to-end to generate both answers and questions. |
| Outcome: | The proposed model outperforms current state-of-the-art methods in the domain adaptation of QA models. |
S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models (2026.acl-long)
Copied to clipboard
Feng Jiang, Zhiyu Lin, Yiyang Liu, Liumeng Xue, Fan Bu, Yuhao Du, Xiangying Chen, Benyou Wang, Haizhou Li
| Challenge: | Existing benchmarks rely heavily on text-based evaluation and largely ignore paralinguistic cues such as prosody, emotion, and speaker traits. |
| Approach: | They propose a speech-native benchmark for evaluating instruction-following S2S models with explicit assessment of both semantic understanding and paralinguistic expression. |
| Outcome: | The proposed system enables more natural, robust, and human-aligned speech agents. |
CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation (2026.findings-acl)
Copied to clipboard
Hu Jing, Danxiang Zhu, Xianlong Luo, Dan Zhang, Shuwei He, Yishu Lei, Shikun Feng, Hai-Tao Zheng, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap . |
| Approach: | They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models. |
| Outcome: | The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting . |
DentalGPT: Incentivizing Multimodal Reasoning in Dentistry (2026.findings-acl)
Copied to clipboard
Zhenyang Cai, Jiaming Zhang, Junjie Zhao, Ziyi Zeng, Yanchao Li, Liang Jingyi, Junying Chen, Yunjin Yang, Jiajun You, Shuzhi Deng, null Xieruiqiii, Yuanting Chen, Xiangyi Feng, Jianquan Li, Liangyi Chen, Junwen Wang, Shan Jiang, Benyou Wang
| Challenge: | Current multimodal large language models (MLLMs) show limited understanding of dental images. |
| Approach: | They propose a dental-specialized multimodal large language model trained via staged multimodal alignment and reinforcement learning. |
| Outcome: | The proposed model outperforms state-of-the-art models on disease classification and dental VQA tasks. |
CateEA: Enhancing Entity Alignment via Implicit Category Supervision (2025.coling-main)
Copied to clipboard
| Challenge: | Existing Entity Alignment methods neglect the inherent semantic information of entities, limiting alignment precision and robustness. |
| Approach: | They propose to combine implicit category information into multi-modal representations by generating pseudo-category labels from entity embeddings and integrating them into a multi-task learning framework. |
| Outcome: | Experiments on benchmark datasets show that CateEA outperforms state-of-the-art methods in various settings. |
TIGER: A Unified Generative Model Framework for Multimodal Dialogue Response Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing research on multimodal dialogues focuses on textual response generation and visual response selection based on the dialogue context. |
| Approach: | They propose a generative model framework for multimodal dialogue response generation that ground the conversation on an image. |
| Outcome: | The proposed system provides users with an enhanced conversational experience. |
HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)
Copied to clipboard
Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li
| Challenge: | Existing top-k attention methods struggle to strike a balance between efficiency and accuracy. |
| Approach: | They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention. |
| Outcome: | The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy. |
Generative-to-Discriminative Test-Time Adaptation via Manifold-Aware Diffusion and Bayesian Distillation (2026.findings-acl)
Copied to clipboard
Boyun Zhang, Zequn Xie, Fangming Feng, Zihan Zhang, Yongbo He, Chuxin Wang, Sihang Cai, Tao Jin, Qifei Zhang
| Challenge: | Existing discriminative approaches suffer from "confident but wrong" failure mode, blindly adapting to OOD noise leading to error accumulation. |
| Approach: | They propose a TTA framework that harmonizes the robustness of generative diffusion models with the efficiency of discriminative regression networks via Bayesian Diffusion Distillation (BDD). |
| Outcome: | The proposed framework reduces MAE from 0.6872 to 0.5673 and boosts binary accuracy by 5.81 percentage points (reaching 57.33%) it also reduces the MAE of the MOSI to SIMS shift and achieves an 11.18-point gain over the baseline. |
An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation (2024.acl-long)
Copied to clipboard
Kun Zhu, Xiaocheng Feng, Xiyuan Du, Yuxuan Gu, Weijiang Yu, Haotian Wang, Qianglong Chen, Zheng Chu, Jingchang Chen, Bing Qin
| Challenge: | Experimental results show that retrieval-augmented generation improves accuracy and relevance of large language models. |
| Approach: | They propose to introduce the information bottleneck theory into retrieval-augmented generation by maximizing mutual information between compression and ground output while minimizing mutual information . |
| Outcome: | The proposed approach improves accuracy and correctness of answer generation and conciseness with 2.5% compression rate. |
Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have extensive world knowledge, but often generate inaccurate geospatial knowledge. |
| Approach: | They propose a framework for evaluation of large language models to mitigate hallucinations . they use Kahneman-Tversky Optimization to align LLMs with their reality . |
| Outcome: | The proposed evaluation framework uncovers hallucinations in 20 advanced LLMs. |
A Survey on Asking Clarification Questions Datasets in Conversational Systems (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies on Asking Clarification Questions (ACQs) are incomparable due to inconsistent data, experimental setups and evaluation strategies. |
| Approach: | They analyse the current research status on Asking Clarification Questions (ACQs) and propose a set of evaluation metrics and benchmarks for multiple ACQs-related tasks. |
| Outcome: | The proposed techniques are compared with the available datasets and evaluated against benchmarks. |
Direct Multi-Turn Preference Optimization for Language Agents (2024.emnlp-main)
Copied to clipboard
| Challenge: | Extensive experiments on three multi-turn agent task datasets confirm the effectiveness and superiority of the DMPO loss function. |
| Approach: | They propose a novel loss function for multi-turn agent tasks that replaces the policy constraint with the state-action occupancy measure constraint and adds length normalization to the Bradley-Terry model. |
| Outcome: | Experiments on three multi-turn agent task datasets confirm the effectiveness and superiority of the proposed loss function. |
Personalized Generation In Large Model Era: A Survey (2025.acl-long)
Copied to clipboard
Yiyan Xu, Jinghao Zhang, Alireza Salemi, Xinting Hu, Wenjie Wang, Fuli Feng, Hamed Zamani, Xiangnan He, Tat-Seng Chua
| Challenge: | Recent advances in large generative models have catalyzed a paradigm shift in content generation to Personalized Generation (PGen). |
| Approach: | They propose a multi-level taxonomy that systematically formalizes PGen's key components, core objectives, and abstract workflows. |
| Outcome: | The proposed taxonomy bridging PGen research across multiple modalities highlights open challenges and promising directions for future exploration. |
EDIS: Entity-Driven Image Search over Multimodal Web Content (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing image retrieval methods require large datasets and a large candidate set. |
| Approach: | They propose a news-domain dataset for cross-modal image search with 1 million web images . they propose combining multimodal image-text pairs with a million candidates . |
| Outcome: | The proposed dataset challenges state-of-the-art methods with dense entities and the large-scale candidate set. |
Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance (2025.emnlp-main)
Copied to clipboard
| Challenge: | Visual Language Models (VLMs) have significant parameter size and autoregressive (AR) decoding nature impose considerable computational demands on VLA models. |
| Approach: | They propose a framework to relax acceptance utilizing the relative distances represented by the action tokens of the VLA model. |
| Outcome: | Empirical results show that the proposed framework improves the speed of the prediction task by 44%. |
STICKERCONV: Generating Multimodal Empathetic Responses from Scratch (2024.acl-long)
Copied to clipboard
Yiqun Zhang, Fanheng Kong, Peidong Wang, Shuang Sun, SWangLing SWangLing, Shi Feng, Daling Wang, Yifei Zhang, Kaisong Song
| Challenge: | Prior studies on stickers focused on sentiment analysis and recommendation systems, overlooking their vast potential in empathetic response generation. |
| Approach: | They propose a multimodal empathetic dialogue dataset, STICKERCONV, which simulates human behavior with stickers, and propose evaluative metrics based on LLM. |
| Outcome: | The proposed framework generates contextually relevant and emotionally resonant multimodal empathetic responses, contributing to the advancement of more nuanced and engaging e-dialog systems. |
Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation (2026.findings-acl)
Copied to clipboard
| Challenge: | Current approaches for Multimodal Sentiment Analysis (MSA) rely on parameter-heavy LLMs for classification, overlooking multimodal sentiment reasoning generation in resource-limited environments. |
| Approach: | They propose a multimodal sentiment reasoning distillation model that employs a teacher-assistant-student paradigm to address deployment constraints in resource-limited environments. |
| Outcome: | The proposed model performs well on a resource-limited JMSRC task with only 3B parameters and shows generalization and interpretability. |
Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles (2025.acl-long)
Copied to clipboard
| Challenge: | Existing user simulators lack authenticity and user-level diversity in interactions with large language models. |
| Approach: | They propose a user simulator with implicit user profiles that infers user profiles from human-machine interactions to simulate personalized and realistic dialogues. |
| Outcome: | The proposed framework outperforms baselines in authenticity and diversity while maintaining comparable consistency. |
Learning Geometry-Aware Representations for New Intent Discovery (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for intent classification fail to distinguish new intents due to intertwined centers . a novel framework that learns geometry-aware representations to maximally separate all intents is proposed . |
| Approach: | They propose a new intent discovery framework that learns geometry-aware representations to maximally separate all intents. |
| Outcome: | The proposed framework achieves a new state-of-the-art performance on three benchmarking datasets. |
LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient (2026.acl-long)
Copied to clipboard
Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Using generic and efficient benchmark generators, human annotators are limited by inefficiency . current benchmark generator methods rely on seed signals, leading to long cycles and high costs . |
| Approach: | They propose a framework to evaluate LLMs as generic benchmark generators and integrate them as BenchMaker. |
| Outcome: | The proposed framework achieves comparable performance to human-annotated benchmarks on most metrics. |
Gradient Consistency-based Parameter Allocation for Multilingual Neural Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Multilingual neural machine translation models are often prone to parameter interference . a common problem is that the model compromises with the language diversity to find a solution . |
| Approach: | They propose a method that allocates parameters based on consistency between the gradients of the individual language and the average gradient. |
| Outcome: | The proposed method reduces parameter interference and improves translation quality. |
Personalized Microblog Sentiment Classification via Adversarial Cross-lingual Multi-task Learning (D18-1)
Copied to clipboard
| Challenge: | Existing personalized microblog sentiment classification methods suffer from the insufficiency of discriminative tweets for personalization learning. |
| Approach: | They propose to use user-attention-based Convolutional Neural Networks to capture individuality and opinion bias in microblog posts and a novel adversarial cross-lingual learning framework to enrich the user post representation. |
| Outcome: | The proposed method outperforms state-of-the-art baseline algorithms with large margins on English and Chinese microblog datasets. |
MS2SL: Multimodal Spoken Data-Driven Continuous Sign Language Production (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing solutions for sign language production are limited due to phonological differences and data scarcity. |
| Approach: | They propose a unified framework for continuous sign language production that generates sign predictions step by step from text or speech embeddings. |
| Outcome: | The proposed model achieves competitive performance on how2sign and PHOENIX14T datasets. |
Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for data-to-text generation use a large-scale training corpus to learn semantic correspondences between structured input data and associated texts. |
| Approach: | They propose a local-to-global alignment framework that uses local and global models to learn semantic correspondences from large-scale datasets. |
| Outcome: | The proposed framework can be generalized to restaurant and computer domains and improve alignment accuracy. |
Uncertainty-Aware Routing for Principled Alignment with MoE Dynamics (2026.acl-long)
Copied to clipboard
Yilong Chen, Junyuan Shang, Yuchen Feng, Zhenyu Zhang, Naibin Gu, Ziqi Wang, Tingwen Liu, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Mixture-of-Experts (MoE) is a cornerstone for scaling LLMs, yet its training dynamics remain poorly understood, often leading to sub-optimal specialization. |
| Approach: | They propose to use Helmholtz Free Energy and Router Entropy to study the MoE lifecycle and identify a universal Three-Stage Phase Transition . |
| Outcome: | The proposed model reduces perplexity and improves expert distinctiveness, offering a principled path toward thermodynamically aligned computation. |
SURE: Mutually Visible Objects and Self-generated Candidate Labels For Relation Extraction (2025.coling-main)
Copied to clipboard
| Challenge: | Joint relation extraction models face high computational complexity, complex network architectures, difficult parameter tuning and limited interpretability. |
| Approach: | They develop a candidate label marker mechanism that prioritizes strategic label selection over simple label generation. |
| Outcome: | The proposed candidate label marks improve the SOTA methods by 2.5%, 1.9%, 1.2% . the proposed candidate labels improve the performance of the proposed methods . |
SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis (2020.acl-main)
Copied to clipboard
| Challenge: | sentiment knowledge is ignored in sentiment analysis, despite its use in pretraining. |
| Approach: | They propose to use sentiment knowledge to learn a unified sentiment representation for multiple sentiment analysis tasks. |
| Outcome: | The proposed method outperforms strong pre-training baseline on three kinds of sentiment tasks. |
OmniEvent: A Comprehensive, Fair, and Easy-to-Use Toolkit for Event Understanding (2023.emnlp-demo)
Copied to clipboard
| Challenge: | Event understanding is fundamental for humans to understand the world. |
| Approach: | They propose an event understanding toolkit called OmniEvent that is comprehensive and fair . it supports mainstream modeling paradigms and the processing of 15 widely-used datasets . |
| Outcome: | The toolkit supports mainstream modeling paradigms and the processing of 15 widely-used English and Chinese datasets. |
Log-FGAER: Logic-Guided Fine-Grained Address Entity Recognition from Multi-Turn Spoken Dialogue (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing name entity recognition methods combine pre-trained language models with supervised models such as BiLSTM/LSTM-CRF to perform poorly in a spoken dialogue context. |
| Approach: | They propose a logic-guided fine-grained address recognition method that softly applies the logic rule to improve the accuracy of FGAER. |
| Outcome: | The proposed method improves fine-grained address entity recognition from multi-turn spoken dialogues. |
Context-DPO: Aligning Language Models for Context-Faithfulness (2025.findings-acl)
Copied to clipboard
Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu
| Challenge: | Context-DPO is the first alignment method specifically designed to enhance contextfaithfulness for large language models. |
| Approach: | They propose a benchmark that simulates Retrieval-Augmented Generation scenarios with knowledge conflicts to evaluate context-faithfulness. |
| Outcome: | The proposed method improves LLMs' context-faithfulness by 35% to 280% over open-source models. |
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning (2026.acl-long)
Copied to clipboard
Yujie Feng, Hao Wang, Jian Li, Xu Chu, Zhaolu Kang, Yiran Liu, Yasha Wang, Philip S. Yu, Xiao-Ming Wu
| Challenge: | Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting. |
| Approach: | They propose a framework that aligns replay schedules with a model-centric notion of time. |
| Outcome: | Experiments on three benchmarks show that FOREVER consistently mitigates catastrophic forgetting. |
ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Multilingual Contrastive Framework (2025.acl-long)
Copied to clipboard
Hengyuan Zhang, Chenming Shang, Sizhe Wang, Dongdong Zhang, Yiyao Yu, Feng Yao, Renliang Sun, Yujiu Yang, Furu Wei
| Challenge: | Experiments show that ShifCon significantly enhances the performance of non-dominant languages due to the imbalance in training data across languages. |
| Approach: | They propose a Shift-based multilingual Contrastive framework that aligns the internal forward process of other languages toward that of the dominant one. |
| Outcome: | The proposed framework significantly improves performance of non-dominant languages, particularly for low-resource ones. |
Zero-shot Text Classification via Reinforced Self-training (2020.acl-main)
Copied to clipboard
Zhiquan Ye, Yuxia Geng, Jiaoyan Chen, Jingmin Chen, Xiaoxiao Xu, SuHang Zheng, Feng Wang, Jun Zhang, Huajun Chen
| Challenge: | Existing methods to learn from unlabeled data are difficult for zero-shot text classification tasks. |
| Approach: | They propose a self-training based method to efficiently leverage unlabeled data. |
| Outcome: | The proposed method significantly outperforms existing methods in zero-shot text classification tasks on benchmarks and a real-world e-commerce dataset. |
Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning (2025.findings-naacl)
Copied to clipboard
Xinglin Wang, Shaoxiong Feng, Yiwei Li, Peiwen Yuan, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Existing decoding strategies for chain-of-thought reasoning do not exploit prior information about question difficulty. |
| Approach: | They propose a decoding strategy called self-consistency to improve reasoning performance by adjusting the number of samples based on the posterior distribution of a set of pre-samples. |
| Outcome: | The proposed method outperforms baseline methods on arithmetic, commonsense and symbolic reasoning tasks while achieving comparable performance. |
WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning (2026.acl-long)
Copied to clipboard
Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei, Jinjie Gu
| Challenge: | Open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches. |
| Approach: | They propose a framework that compresses web agent trajectories via graph-based pruning. |
| Outcome: | The proposed framework reduces tool-call rounds by 20% while improving accuracy and efficiency while maintaining the same level of performance as existing models. |
ULN: Towards Underspecified Vision-and-Language Navigation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing vision-and-language navigation models are brittle to multi-level language underspecification. |
| Approach: | They propose to use multi-level underspecified instructions to guide agents . they propose to learn GSS for navigation agent to ground multi- level instructions . experimental results show existing VLN models are still brittle to multi-language underspecification . |
| Outcome: | Experimental results show that the proposed framework outperforms baselines on ULN by 10% relative success rate across all levels. |
MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing zero-shot dialogue generation systems rely on large-scale pre-trained language models. |
| Approach: | They propose a multilingual learning framework for zero-shot dialogue generation that can transfer knowledge from an English corpus to a non-English corpus with zero samples. |
| Outcome: | The proposed framework can transfer knowledge from an English corpus to a non-English corpus with zero samples. |
AdaTooler-V: Adaptive Tool-Use for Images and Videos (2026.findings-acl)
Copied to clipboard
Chaoyang Wang, Kaituo Feng, Dongyang Chen, Zhongyu Wang, Zhixun Li, Sicheng Gao, Meng Meng, Xu Zhou, Manyuan Zhang, Yuzhang Shang, Xiangyu Yue
| Challenge: | Existing models exhibit blind tool-use reasoning patterns, which significantly increases inference overhead and degrades model performance. |
| Approach: | They propose an MLLM that performs adaptive tool-use by determining whether a visual problem truly requires tools. |
| Outcome: | The proposed model outperforms existing methods in visual reasoning tasks. |
PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction (2021.acl-long)
Copied to clipboard
| Challenge: | Chinese spelling correction (CSC) is a task to detect and correct spelling errors in texts. |
| Approach: | They propose a Pre-trained masked Language model with Misspelled knowledgE (PLOME) which jointly learns how to understand language and correct spelling errors. |
| Outcome: | The proposed model outperforms state-of-the-art methods on widely used benchmarks and achieves superior performance against existing models. |
COM-MRC: A COntext-Masked Machine Reading Comprehension Framework for Aspect Sentiment Triplet Extraction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Aspect Sentiment Triplet Extraction (ASTE) aims to extract sentiment triplets from sentences, but when faced with multiple aspect terms, the MRC-based methods could fail due to the interference from other aspect terms. |
| Approach: | They propose a COntext-Masked MRC framework for Aspect Sentiment Triplet Extraction (ASTE) which aims to extract sentiment triplets from sentences . |
| Outcome: | The proposed framework outperforms state-of-the-art methods on benchmark datasets and shows that it can extract sentiment triplets from multiple aspect terms. |
Towards Context-Aware Code Comment Generation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for code comments generate comments manually, but they suffer from poor scalability and high maintenance cost due to the expensive overhead of writing comment templates. |
| Approach: | They propose a method to automatically generate code comments at a function level by targeting object-oriented programming languages. |
| Outcome: | The proposed approach outperforms the state-of-the-art methods and is comparable with existing methods. |
TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for table instruction tuning are limited due to limited data diversity and lack of data quality. |
| Approach: | They propose a weakness-guided data synthesis framework for table instruction tuning that explores the vast input space of table understanding tasks and then iterates through the input space. |
| Outcome: | The proposed framework boosts the average accuracy of Llama3.1-8B-instruct by 11.62% with 27K GPT-4o synthetic data and outperforms state-of-the-art data synthesis baselines which use more training data. |
GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization (2025.acl-long)
Copied to clipboard
Zhouhong Gu, Xingzhou Chen, Xiaoran Shi, Tao Wang, Suhang Zheng, Tianyu Li, Hongwei Feng, Yanghua Xiao
| Challenge: | Existing methods for achieving this require a limited understanding of constraints and can be hallucinating or brittle. |
| Approach: | They propose a framework that combines adversarial training dynamics with an encoder-only reward model to progressively learn and adapt to increasingly complex constraints. |
| Outcome: | Extensive experiments show that GAPO significantly outperforms existing methods like PPO, DPO, and KTO in fine-grained constraints. |
Pruning Pre-trained Language Models Without Fine-Tuning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods to prune Pre-trained Language Models (PLMs) are overparameterized and require fine-tuning. |
| Approach: | They propose a pruning method that uses first-order pruning to prune PLMs while fine-tuning the remaining weights. |
| Outcome: | The proposed method outperforms first-order pruning and zero-order methods at sparsity levels. |
ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models (2024.emnlp-main)
Copied to clipboard
Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana
| Challenge: | Currently, tool-augmented large language models (LLMs) only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100. |
| Approach: | They propose a multi-level diagnostic process to assess the LLM's hallucinations through two perspectives: depth and breadth. |
| Outcome: | The proposed diagnostic process assesses the hallucinations of large language models through two perspectives: depth and breadth. |
Attack Prompt Generation for Red Teaming and Defending Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies construct attack prompts via manual or automatic methods, but these methods have limitations on cost and quality. |
| Approach: | They propose an attack framework to instruct LLMs to mimic human-generated prompts through in-context learning and a defense framework that fine-tunes victim LLM's through iterative interactions with the attack framework. |
| Outcome: | The proposed approach is based on experiments on different LLMs to evaluate their effectiveness against red teaming attacks. |
Generalized Intent Discovery: Learning from Open World Dialogue System (2022.coling-1)
Copied to clipboard
| Challenge: | Existing intent classification models rely on a pre-defined intent set and supervised labels, which is limited in some practical scenarios. |
| Approach: | They propose to extend an IND intent classifier to an open-world intent set including IND and OOD intents. |
| Outcome: | The proposed task can classify IND and OOD intents while discovering new unlabeled OOD types incrementally. |
Alleviating Sparsity of Open Knowledge Graphs with Ternary Contrastive Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to learning KG triplets ignore ternary propagation patterns and ignore zero-shot, few-shot and synonymity problems. |
| Approach: | They propose a framework for contrastive learning based on ternary propagation patterns among head, relation and tail. |
| Outcome: | Experiments on benchmarks show that TernaryCL is superior to state-of-the-art models. |
From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models (2026.acl-long)
Copied to clipboard
Ziyan Wang, Enmao Diao, Qi Le, Pu Wang, Minwoo Lee, Shu-ping Yeh, Evgeny Stupachenko, Hao Feng, Li Yang
| Challenge: | Structured pruning is a practical approach to deploying large language models (LLMs) but it fails to capitalize on modest task-specific calibration signals, causing limited downstream gains. |
| Approach: | They propose a method that removes attention heads and MLP channels using loss-based important scores . they use perplexity for language modeling and a margin-based objective for decision-style tasks . |
| Outcome: | The proposed method lowers perplexity and improves accuracy at higher sparsity . it also stabilizes accuracy and mitigates perxity collapse without fine-tuning . |
PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning (2024.acl-long)
Copied to clipboard
| Challenge: | Recent research shows that training with CAD may lead models to overly focus on modified features while ignoring other important contextual information. |
| Approach: | They propose to use contrastive learning to promote global feature alignment and learning counterfactual clues to improve model performance. |
| Outcome: | The proposed method outperforms the state-of-the-art on out-of distribution (OOD) datasets. |
Multi-Step Generation of Test Specifications using Large Language Models for System-Level Requirements (2025.acl-industry)
Copied to clipboard
| Challenge: | System-level testing is a critical phase in the development of large, safety-dependent systems, such as those in the automotive industry. |
| Approach: | They propose an AI-powered assistant to aid users in creating test specifications for system-level requirements. |
| Outcome: | The proposed system reduces the effort required to derive test specifications by 30% in ROUGE-L. |
Towards Human-aligned Evaluation for Linear Programming Word Problems (2024.lrec-main)
Copied to clipboard
Linzi Xing, Xinglu Wang, Yuxi Feng, Zhenan Fan, Jing Xiong, Zhijiang Guo, Xiaojin Fu, Rindra Ramamonjison, Mahdi Mostajabdaveh, Xiongwei Han, Zirui Zhou, Yong Zhang
| Challenge: | Existing evaluation methodologies for MWPs diverge from human judgment and face challenges in recognizing mathematically equivalent answers. |
| Approach: | They propose an evaluation metric rooted in graph edit distance that features benefits such as permutation invariance and more accurate program equivalence identification. |
| Outcome: | The proposed evaluation metric features benefits such as permutation invariance and more accurate program equivalence identification. |
CPL: Counterfactual Prompt Learning for Vision and Language Models (2022.emnlp-main)
Copied to clipboard
Xuehai He, Diji Yang, Weixi Feng, Tsu-Jui Fu, Arjun Akula, Varun Jampani, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Wang
| Challenge: | Existing prompt tuning methods tend to learn spurious or entangled representations, leading to poor generalization to unseen concepts. |
| Approach: | They propose a prompt tuning technique that tunes the learnable prompt for pre-trained vision and language models. |
| Outcome: | The proposed method improves few-shot performance on vision and language tasks over existing prompt tuning methods. |
Latent Suicide Risk Detection on Microblog via Suicide-Oriented Word Embeddings and Layered Attention (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to detect suicidal ideation on social media are limited to a small group of people. |
| Approach: | They propose to use tree holes to embed words into microblogs to strengthen the sensibility of suicide-related lexicons and to use a two-layered attention mechanism to grasp intermittently changing points from individual's open blog streams. |
| Outcome: | The proposed approach can achieve over 91% accuracy with the use of suicide-oriented word embeddings and attention on a large-scale well-labelled suicide data set. |
Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to model relationships between aspects and opinion words are inefficient due to informal expressions and complexity of online reviews. |
| Approach: | They propose a dual graph convolutional networks model that considers complementarity of syntax structures and semantic correlations simultaneously. |
| Outcome: | The proposed model outperforms state-of-the-art methods on three public datasets and validates it. |
Knowledge Distillation based Contextual Relevance Matching for E-commerce Product Search (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Existing approaches to e-commerce relevance matching ignore bipartite graphs in logs . experimental results show that proposed method improves human relevance judgment . |
| Approach: | They propose an efficient knowledge distillation framework for e-commerce relevance matching to exploit the advantages of Transformer-style and classical relevance matching models. |
| Outcome: | The proposed method significantly improves human relevance judgment on large-scale real-world data. |
Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge (2025.findings-emnlp)
Copied to clipboard
| Challenge: | LLM-as-a-Judge uses large language models to evaluate the quality of LLM generated responses, but training proxy judge models using evaluation data generated by powerful teacher models introduces a critical yet previously overlooked issue: teacher preference bias. |
| Approach: | They propose a new setting that incorporates an additional assistant model, which is not biased toward the teacher model’s responses, to complement the training data. |
| Outcome: | The proposed model reduces teacher preference bias while maintaining strong performance across six evaluation benchmarks. |
Hypothetical Training for Robust Machine Reading Comprehension of Tabular Context (2023.findings-acl)
Copied to clipboard
| Challenge: | Counterfactual training is expensive because of the complexity of tabular data. |
| Approach: | They propose a hypothetical training framework that uses paired examples with different hypothetical questions to supervise the direction of model gradient towards the counterfactual answer change. |
| Outcome: | The proposed framework improves on tabular MRC datasets. |
A Unified Framework for Modeling Heterogeneous Financial Data via Dual-Granularity Prompting (2026.acl-industry)
Copied to clipboard
| Challenge: | Recent industrial credit scoring models rely heavily on manually tuned statistical learning methods due to the complexity of heterogeneous financial data and the challenge of modeling evolving creditworthiness. |
| Approach: | They propose a framework that reformulates credit scoring as a multi-scale sequential learning problem. |
| Outcome: | FinLangNet improves KS and bad debt rate by 6.3 pp in real world deployments. |
Unlocking Memorization in Large Language Models with Dynamic Soft Prompting (2024.emnlp-main)
Copied to clipboard
Zhepeng Wang, Runxue Bao, Yawen Wu, Jackson Taylor, Cao Xiao, Feng Zheng, Weiwen Jiang, Shangqian Gao, Yanfu Zhang
| Challenge: | Pretrained large language models excel in a variety of natural language processing tasks . however, they pose significant security risks due to their tendency to memorize training data . |
| Approach: | They propose a method to estimate LLM memorization using dynamic, prefix-dependent soft prompts. |
| Outcome: | The proposed method can achieve maximum relative improvement of 135.3% and 39.8% over baseline compared to state-of-the-art methods. |
Convolutional Neural Network for Universal Sentence Embeddings (C18-1)
Copied to clipboard
| Challenge: | Recent studies show that averaging word embeddings is effective for NLP but these models represent a sentence only in terms of features of words or uni-grams. |
| Approach: | They propose a CNN-based model that uses both features of words and n-grams to encode sentences. |
| Outcome: | The proposed model performs better than existing models in transfer learning setting and exceeds state of the art in supervised learning setting by initializing the parameters with the pre-trained sentence embeddings. |
A Sequence-to-Sequence Approach to Dialogue State Tracking (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for dialogue state tracking are still challenging, but they are improving . a new approach to dialogue state monitoring is proposed, called Seq2Seq-DU . |
| Approach: | They propose a new dialogue state tracking module that formalizes DST as a sequence-to-sequence problem. |
| Outcome: | The proposed method outperforms existing methods on benchmark datasets in different settings. |
SQL-to-Text Generation with Graph-to-Sequence Model (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to generate SQL-to-text using seq2seq models do not capture graph-structured information in SQL query. |
| Approach: | They propose a graph-to-sequence model to encode global structure information into node embeddings. |
| Outcome: | The proposed model outperforms the Seq2Seq and Tree2Sq baselines on the WikiSQL and Stackoverflow datasets. |
PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reward models evaluate empathy from a single perspective, overlooking bidirectional interaction nature of empathy. |
| Approach: | They propose a reward model that evaluates empathy from a single perspective . they propose PERM to integrate a bystander perspective to monitor overall interaction quality . |
| Outcome: | a new reward model outperforms state-of-the-art models on an emotional intelligence benchmark and an industrial daily conversation dataset. |
Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition (2022.acl-long)
Copied to clipboard
| Challenge: | a new approach for self-supervised speech representation learning is proposed . a phoneme inventory learning model is based on a discrete representation of speech . |
| Approach: | They propose a neural discrete representation learning model for self-supervised phoneme inventory learning with raw speech and word labels. |
| Outcome: | The proposed model learns better phoneme-level representations and lowers error rates on TIMIT and Mboshi benchmarks than previous state-of-the-art models. |
SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing alignment methods struggle to cover diverse safety scenarios and remain vulnerable to adversarial attacks. |
| Approach: | They propose a framework for 'S**afety' alignment via e**F**ficient' E**x-Ante-R**easoning that instantiates structured Ex-Ance reasoning and embeds predefined safety rules. |
| Outcome: | The proposed framework enhances safety performance while maintaining usefulness and efficiency. |
Detecting Spoilers in Movie Reviews with External Movie Knowledge and User Networks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models focus on the textual content of the review, while spoiler detection requires putting the review into the context of facts and knowledge regarding movies. |
| Approach: | They propose a network-based spoiler detection model that takes into account external knowledge about movies and user activities on movie review platforms. |
| Outcome: | The proposed model takes into account external knowledge about movies and user activities on movie review platforms while incorporating user networks. |
Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning (2024.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that fine-tuning of large language models for specific tasks can be challenging . distribution shift during fine-timing can lead to performance degradation in general task capabilities . |
| Approach: | They propose a new approach that bridges the distribution gap between task datasets and LLMs by guiding fine-tuning with a distilled dataset generated by the model itself. |
| Outcome: | The proposed approach achieves comparable or superior performance on downstream tasks compared to the vanilla approach. |
Multimodal Table Understanding (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to understanding tables rely on textual inputs and table images are difficult to access in real-world scenarios. |
| Approach: | They propose a multimodal table understanding problem where the model needs to generate correct responses to various table-related requests based on the given table image. |
| Outcome: | The proposed model outperforms open-source MLLMs on 23 benchmarks under held-in and held-out settings. |
Contrastive Learning with Generated Representations for Inductive Knowledge Graph Embedding (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for inductive knowledge Graphs are limited by sparsity and implicit transfer. |
| Approach: | They propose a Contrastive Learning framework with graph guided Variational autoencoder on Meta-KGs to capture and transfer entities. |
| Outcome: | The proposed framework outperforms state-of-the-art methods with extensive experiments. |
Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing metrics for video captioning are based on text-based comparisons with ground-truth references. |
| Approach: | They propose a reference-free benchmark that assesses video captions based on their utility . they will release the benchmark to facilitate reproducible research . |
| Outcome: | The proposed benchmark improves on human-verified, fine-grained questions . it correlates significantly better with human judgments than existing metrics . |
AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation (2025.findings-acl)
Copied to clipboard
Ming Wang, Peidong Wang, Lin Wu, Xiaocui Yang, Daling Wang, Shi Feng, Yuxin Chen, Bixuan Wang, Yifei Zhang
| Challenge: | Existing models of seeker simulations are limited by the cost and ethical concerns of involving real seekers in mental health research. |
| Approach: | They propose an emotional and cognitive dynamic agent system equipped with tertiary memory to enable dynamic control of the simulator's configurations. |
| Outcome: | The proposed system achieves more realistic seeker simulation compared to baselines. |
SEP-MLDC: A Simple and Effective Paradigm for Multi-Label Document Classification (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods focus on optimizing document features, overlooking the potential of high-quality label features to enhance classification performance. |
| Approach: | They propose a multi-label document classification paradigm that utilizes large language models to expand the label content and generate pseudo-samples for the tail categories. |
| Outcome: | The proposed method significantly outperforms state-of-the-art models. |
Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies on this topic focus on the robustness of specific detectors or particular attack methods. |
| Approach: | They stress test the detectors’ robustness to malicious attacks under realistic scenarios using LLMs and metric-based detectors. |
| Outcome: | The proposed methods are based on a set of LLM-based models and their performance is compared under different budget levels. |
TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance (2021.acl-long)
Copied to clipboard
Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, Tat-Seng Chua
| Challenge: | Existing QA systems focus on unstructured text, structured knowledge base, or semi-structured tables. |
| Approach: | They propose a large-scale question answering model based on financial reports . numerical reasoning is usually required to infer the answer . |
| Outcome: | The proposed model achieves 58.0% inF1, an 11.1% increase over the baseline model, but still lags behind the best human model. |
Interpretable Math Word Problem Solution Generation via Step-by-step Planning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to solving math word problems focus on obtaining the correct answer. |
| Approach: | They propose a step-by-step planning approach for intermediate solution generation that strategically plans the generation of the next solution step based on the MWP and the previous solution steps. |
| Outcome: | The proposed approach improves the accuracy and interpretability of the solution on automatic metrics and human evaluation. |
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering (2025.findings-acl)
Copied to clipboard
Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, An-Lan Wang, Chunhui Lin, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang
| Challenge: | Text-Centric Visual Question Answering (TEC-VQA) is a text-centric visual task understanding tool. |
| Approach: | They introduce a benchmark that features human expert annotations across 9 languages . they prioritize the text in question-answer pairs while disregarding visual text in images . |
| Outcome: | The proposed benchmarks prioritize the text in question-answer pairs while disregarding visual text in images. |
Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Adversary-aware DPO (ADPO) is a training framework that explicitly considers adversary. |
| Approach: | a new framework integrates adversarial training into a pre-trained large language model to enhance safety alignment . adversary-aware DPO provides a framework that explicitly considers adversary . |
| Outcome: | a new training framework outperforms baselines in safety alignment and general utility of large language models. |
Focused Large Language Models are Stable Many-Shot Learners (2024.emnlp-main)
Copied to clipboard
Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li
| Challenge: | In-Context Learning (ICL) enables large language models to achieve rapid task adaptation by learning from demonstrations. |
| Approach: | They propose a training-free method that disperses model attention from the query . they propose 'focus' search strategy that uses model perplexity to ensure sufficient attention . |
| Outcome: | The proposed method achieves an average performance improvement of 5.2% over vanilla ICL and scales well with many-shot demonstrations. |
Gated Mechanism Enhanced Multi-Task Learning for Dialog Routing (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for dialog routing are mostly heuristic and cannot achieve high-quality performance. |
| Approach: | They propose a multi-task learning framework with a dialog encoder and two tailored gated mechanism modules to solve this problem. |
| Outcome: | The proposed model can play the role of hierarchical information filtering and is non-invasive to existing dialog systems. |
A New Approach to Overgenerating and Scoring Abstractive Summaries (2021.naacl-main)
Copied to clipboard
| Challenge: | Abstractive summarization is a learning objective to produce system outputs that resemble reference summaries on a word-to-word basis. |
| Approach: | They propose a two-staged strategy to generate multiple variants of the target summary and score and select admissible ones according to users’ needs. |
| Outcome: | The proposed approach can achieve state-of-the-art on benchmark summarization datasets. |
InsBank: Evolving Instruction Subset for Ongoing Alignment (2025.findings-emnlp)
Copied to clipboard
Jiayi Shi, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Huan Ren, Yao Hu, Kan Li
| Challenge: | Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs. |
| Approach: | They propose to use a continuously updated repository to integrate the latest valuable instruction data with a progressive evolution framework to evolve InsBank over time. |
| Outcome: | The proposed framework outperforms baselines in InsBank evolution and extracts budget-specific subsets. |
Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown promise in software vulnerability detection, especially on function-level benchmarks like Devign and BigVul. |
| Approach: | They propose a JIT vulnerability detection benchmark linking each function to its vulnerability-introducing and fixing commits. |
| Outcome: | The proposed JIT vulnerability detection benchmark enables comprehensive evaluation of detection capabilities. |
DeepMed: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference (2026.findings-acl)
Copied to clipboard
Zihan Wang, Hao Wang, Shi Feng, Xiaocui Yang, Daling Wang, Yiqun Zhang, Jinghao Lin, Xiaozhong Ji, Haihua Yang
| Challenge: | Medical reasoning models are constrained by parametric knowledge and can induce hallucinations and spurious attributions. |
| Approach: | They propose a model that uses a multi-hop med-search QA synthesis method to apply the DR paradigm in medical contexts. |
| Outcome: | The proposed model outperforms larger medical reasoning models on medical benchmarks. |
D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents (2026.findings-acl)
Copied to clipboard
Hongze Mi, Yibo Feng, WenJie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Jun Fang, Hua Chai, Naiqiang Tan, Gang Pan
| Challenge: | Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. |
| Approach: | They propose a deliberative framework that leverages a fine-grained tip retrieval mechanism to inform its decision-making process. |
| Outcome: | The proposed framework achieves SOTA among open-source general models on AndroidWorld and ScreenSpot-V2 . it leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process . |
MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MT-RewardTree provides a framework for constructing, evaluating, and deploying process reward models in machine translation (MT) |
| Approach: | They propose a method for automatically generating token-level preference pairs using approximate Monte Carlo Tree Search. |
| Outcome: | The proposed framework achieves state-of-the-art performance in token-level evaluation and sequence-level analysis. |
Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing uncertainty sampling methods are time-consuming and can't be executed frequently. |
| Approach: | They propose adversarial uncertainty sampling in discrete space to find informative unlabeled text samples for annotation using adversarials. |
| Outcome: | The proposed approach outperforms baselines on effectiveness on five datasets. |
Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models (2025.emnlp-main)
Copied to clipboard
Yi Feng, Jiaqi Wang, Wenxuan Zhang, Zhuang Chen, Shen Yutong, Xiyao Xiao, Minlie Huang, Liping Jing, Jian Yu
| Challenge: | Existing approaches to mental health support lack realism and capture therapeutic progression over time. |
| Approach: | They propose a framework that simulates expert narrative therapists by planning therapeutic stages, guiding reflection levels, and generating contextually appropriate responses through retrieval-augmentation. |
| Outcome: | The proposed framework outperforms standard methods in quality and depth on 260 simulated clients and 230 human participants. |
EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation (2026.acl-long)
Copied to clipboard
Xinda Wang, Zhengxu Hou, Yangshijie Zhang, null Yanbingren, Jialin Liu, ChenZhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao
| Challenge: | Existing methods for story evaluation lack reasoning capabilities for open-source models . evolvR framework provides high-fidelity evaluators for story generation tasks . |
| Approach: | They propose a framework that self-synthesizes chain-of-thought data via a multi-persona strategy . they propose evolvR to provide a reward model for story generation . |
| Outcome: | The proposed framework achieves state-of-the-art performance on three evaluation benchmarks . it also enhances the quality of generated stories, validating the superiority of the framework . |
EmpCRL: Controllable Empathetic Response Generation via In-Context Commonsense Reasoning and Reinforcement Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies lack the perception of fine-grained dialogue emotion propagation, and have limitations in reasoning about the intentions of users on cognition, which affect the quality of empathetic response. |
| Approach: | They propose to use commonsense reasoning and reinforcement learning to generate empathetic response based on in-context commonsensing and contextual reasoning to broaden cognitive boundaries. |
| Outcome: | The proposed model outperforms state-of-the-art models in automatic and human evaluation. |
Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve output quality without aggregating input tokens are limited by the complexity of aggregation of responses. |
| Approach: | They propose to extract and integrate segment-level commonalities from candidate samples to enhance performance of LLMs in open-ended and reasoning tasks. |
| Outcome: | The proposed method improves performance on reasoning, code generation and mathematical reasoning tasks without requiring additional models and overlooking the knowledge present among the candidates. |
Why Do More Experts Fail? A Theoretical Analysis of Model Merging (2026.acl-long)
Copied to clipboard
Zijing Wang, Xingle Xu, YongKang Liu, Yiqun Zhang, Peiqin Lin, Shi Feng, Daling Wang, Xiaocui Yang, Hinrich Schuetze
| Challenge: | Existing methods for model merging struggle to maintain performance gains as the number of merged models increases. |
| Approach: | They propose a Reparameterized Heavy-Tailed method to extend the merged model’s coverage and enhance performance. |
| Outcome: | The proposed method extends the merged model’s coverage and enhances performance on 19 benchmarks, including knowledge-intensive and general-purpose tasks. |
Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction (2021.acl-long)
Copied to clipboard
Yifan Gao, Henghui Zhu, Patrick Ng, Cicero Nogueira dos Santos, Zhiguo Wang, Feng Nan, Dejiao Zhang, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang
| Challenge: | Open-domain question answering is a task to answer questions using passages with diverse topics. |
| Approach: | They propose a model that aggregates evidence from multiple passages to adaptively predict a single answer or a set of question-answer pairs for ambiguous questions. |
| Outcome: | The proposed model achieves state-of-the-art performance on AmbigQA dataset and shows competitive performance on NQ-Open and TriviaQA. |
DNA: Denoised Neighborhood Aggregation for Fine-grained Category Discovery (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to learn compact cluster representations from coarsely labeled data are noisy and degrade the quality of learning. |
| Approach: | They propose a framework that encodes semantic structures of data into the embedding space . they retrieve k-nearest neighbors of a query as positive keys to capture similarities . |
| Outcome: | The proposed framework can retrieve more accurate neighbors and outperform state-of-the-art models by a large margin. |
Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models struggle to adapt content to users with differing cognitive capacities, leading to cognitive misalignment. |
| Approach: | They propose a cognitive-level alignment framework that aligns both knowledge complexity and presentation style with user cognition. |
| Outcome: | The proposed framework aligns knowledge complexity and presentation style with user cognition. |
HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | In-depth research on the specific capabilities needed by the RAG generation model is lacking, leading to inconsistent document quality and retrieval system imperfections. |
| Approach: | They propose that RAG models should possess three progressively hierarchical abilities: (1) Filtering: the ability to select relevant information; (2) Combination: the capability to combine semantic information across paragraphs; (3) RAG-specific reasoning: the capacity to further process external knowledge using internal knowledge. |
| Outcome: | Experiments show that the proposed method significantly improves the model’s open-book examination capability on datasets such as RGB, PopQA, MuSiQue, HotpotQA, and PubmedQA. |
Large Language Models with Reinforcement Learning from Human Feedback Approach for Enhancing Explainable Sexism Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in natural language processing have significantly improved text comprehension. |
| Approach: | They propose a Reinforcement Learning from Human Feedback (RLHF) based fine-tuning framework for sexism detection that leverages contextual learning to understand and apply instructions to new scenarios without additional training. |
| Outcome: | The proposed framework outperforms existing models on three EDOS tasks and scores 0.8681 on binary sexism detection, 0.6829 on category classification of sexists and 0.4722 on task C. |
ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing retrieval models rank tools based on similarity between query and tool description (TD) Existing tools are not conditioned to learn tool-to-tool relationships (middle). |
| Approach: | They propose a framework that conditions retrieval models to fetch tools based on hypothetical (synthetic) TD generated using an LLM. |
| Outcome: | The proposed framework improves the performance of sparse and dense retrievers with and without training, showcasing its flexibility. |
AdaDHP: Fine-Grained Fine-Tuning via Dual Hadamard Product and Adaptive Parameter Selection (2025.acl-long)
Copied to clipboard
| Challenge: | Increasing number of parameters can be challenging under resource-constrained environments. |
| Approach: | They propose a parameter-efficient fine-tuning method with fewer parameters and finer granularity that can adaptively select important parameters for each task. |
| Outcome: | The proposed method can fine-tune important parameters for each task, while maintaining the same weights. |
CLEAR: A Clinically Grounded Tabular Framework for Radiology Report Evaluation (2025.findings-emnlp)
Copied to clipboard
Yuyang Jiang, Chacha Chen, Shengyuan Wang, Feng Li, Zecong Tang, Benjamin M. Mervak, Lydia Chelala, Christopher M Straus, Reve Chahine, Samuel G. Armato Iii, Chenhao Tan
| Challenge: | Existing metrics lack the granularity and interpretability to capture nuanced clinical differences between candidate and ground-truth radiology reports. |
| Approach: | They propose a tabular framework with E**xpert-curated labels and an attribute-level comparison for radiology report evaluation (**CLEAR) |
| Outcome: | The proposed framework can extract clinical attributes and provide automated metrics that are strongly aligned with clinical judgment. |
From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems (2025.findings-emnlp)
Copied to clipboard
Zekun Zhou, Xiaocheng Feng, Lei Huang, Xiachong Feng, Ziyun Song, Ruihan Chen, Liang Zhao, Weitao Ma, Yuxuan Gu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin
| Challenge: | rapid development of artificial intelligence (AI) technologies has inspired researchers to explore how AI can accelerate and enhance research. |
| Approach: | They organize the relevant studies into three main categories: hypothesis formulation, hypothesis validation, and manuscript publication. |
| Outcome: | The authors summarize the current state of research in three main areas: hypothesis formulation, hypothesis validation, and manuscript publication. |
AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)
Copied to clipboard
Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang
| Challenge: | Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment. |
| Approach: | They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references. |
| Outcome: | The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references. |
Examining False Positives under Inference Scaling for Mathematical Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in language models have led to significant improvements in mathematical reasoning across benchmarks. |
| Approach: | They analyze the prevalence of false positives in language models by using heuristic evaluation methods . they find that false positive models produce correct final answers but with flawed deduction paths . |
| Outcome: | The proposed model performance improvements are based on the proposed model and its evaluation metrics. |
Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing efforts to identify and avoid CDM to facilitate dialogue learning failed to solve the problem. |
| Approach: | They propose a Sentence Semantic Segmentation guided Conditional Variational Auto-Encoder which can model and take advantage of the CDM data. |
| Outcome: | The proposed method can model and take advantages of the CDM data. |
SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on multimodal faithfulness have focused on perceptual hallucinations, raising concerns about the validity of reasoning traces. |
| Approach: | They propose a diagnostic benchmark that enforces explicit visual comparison to assess faithfulness of reasoning traces. |
| Outcome: | The proposed framework improves visual routing and aligns reasoning with perception. |
DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection (2022.findings-emnlp)
Copied to clipboard
Haoran Meng, Zheng Xin, Tianyu Liu, Zizhen Wang, He Feng, Binghuai Lin, Xuemin Zhao, Yunbo Cao, Zhifang Sui
| Challenge: | DialogUSR is a plug-in and domain-agnostic module that empowers multi-intent detection for chatbots . a single user query triggers inquiries on highspeed train ticket price and weather of destination. |
| Approach: | They propose a dialog utterance splitting and reformulation task that splits multi-intent user query into multiple single-intention sub-queries and recovers all coreferred and omitted information in the sub-questions. |
| Outcome: | The proposed model can be used to split multi-intent user queries into multiple sub-queries . it can be trained in two stages and perform in-depth analyses on the proposed models . |
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. |
Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on augmenting question answering models with external knowledge (e.g., knowledge graphs) lacks transparency into the model’s prediction rationale. |
| Approach: | They propose a knowledge-aware approach that equips pre-trained language models with a multi-hop relational reasoning module that performs multi-relational reasoning over subgraphs extracted from external knowledge graphs. |
| Outcome: | The proposed model performs multi-hop, multi-relational reasoning over subgraphs extracted from external knowledge graphs. |
RAAMove: A Corpus for Analyzing Moves in Research Article Abstracts (2024.lrec-main)
Copied to clipboard
Hongzheng Li, Ruojin Wang, Ge Shi, Xing Lv, Lei Lei, Chong Feng, Fang Liu, Jinkun Lin, Yangguang Mei, Linnan Xu
| Challenge: | RAAMove is a comprehensive multi-domain corpus dedicated to the annotation of move structures in Research Article (RA) abstracts. |
| Approach: | They propose a multi-domain corpus dedicated to the annotation of move structures in RA abstracts. |
| Outcome: | The proposed corpus is based on a human-annotated dataset and a BERT-based model to verify its effectiveness. |
Unraveling Misinformation Propagation in LLM Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning, but how they propagate within their reasoning process remains underexplored. |
| Approach: | They propose a practical approach to mitigating misinformation propagation in LLMs by applying factual corrections early in the reasoning process and fine-tuning on synthesized data with early-stage corrections significantly improves reasoning factuality. |
| Outcome: | The proposed model can correct misinformation when explicitly instructed, but fails to correct misinformation less than half the time even with explicit instructions. |
DelucionQA: Detecting Hallucinations in Domain-specific Question Answering (2023.findings-emnlp)
Copied to clipboard
Mobashir Sadat, Zhengyu Zhou, Lukas Lange, Jun Araki, Arsalan Gundroo, Bingqing Wang, Rakesh Menon, Md Parvez, Zhe Feng
| Challenge: | Hallucination is a well-known phenomenon in text generated by large language models . state-of-the-art LLMs still have a number of weaknesses, including the tendency to generate hallucinatory statements without considering the factuality . |
| Approach: | They propose a dataset that captures hallucinations made by retrieval-augmented LLMs . they propose to use these methods to help detect hallucinosity in QA tasks . |
| Outcome: | The proposed method captures hallucinations made by retrieval-augmented LLMs for QA tasks. |
Revealing the Parallel Multilingual Learning within Large Language Models (2024.emnlp-main)
Copied to clipboard
Yongyu Mu, Peinan Feng, Zhiquan Cao, Yuzhang Wu, Bei Li, Chenglong Wang, Tong Xiao, Kai Song, Tongran Liu, Chunliang Zhang, JingBo Zhu
| Challenge: | Large language models (LLMs) can handle multilingual and cross-lingual text within a single input; however, previous studies focusing on using English as the pivot language to enhance language understanding and reasoning focus on using multiple languages. |
| Approach: | They propose to use parallel multilingual input to enhance the model's comprehension of the input and to examine how multilingual processing affects prediction. |
| Outcome: | The proposed model can handle multilingual and cross-lingual text within a single input, but previous studies focused on using English as the pivot language to enhance language understanding and reasoning. |
Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)
Copied to clipboard
Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yuxuan Gu, Yangfan Ye, Liang Zhao, Weihong Zhong, Baoxin Wang, Dayong Wu, Guoping Hu, Lingpeng Kong, Tong Xiao, Ting Liu, Bing Qin
| Challenge: | Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage. |
| Approach: | They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token. |
| Outcome: | The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token. |
HuatuoGPT, Towards Taming Language Model to Be a Doctor (2023.findings-emnlp)
Copied to clipboard
Hongbo Zhang, Junying Chen, Feng Jiang, Fei Yu, Zhihong Chen, Guiming Chen, Jianquan Li, Xiangbo Wu, Zhang Zhiyi, Qingying Xiao, Xiang Wan, Benyou Wang, Haizhou Li
| Challenge: | Experimental results show that the distilled language model outperforms its teacher model (ChatGPT) in most cases. |
| Approach: | They propose a Large Language Model (LLM) that leverages both distilled data from **ChatGPT** and real-world data from**doctors** in the supervised fine-tuning stage. |
| Outcome: | The proposed model outperforms the teacher model in most cases by using additional real-world data and RLMF to align the language model with the merits of both sources. |
PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning (2026.findings-acl)
Copied to clipboard
Ruixiang Feng, Yuntao Wen, Silin Zhou, Ke Shi, Yifan Wang, Ran Le, Zhenwei An, Zongchao Chen, Chen Yang, Guangyue Peng, Yiming Jia, Dongsheng Wang, Tao Zhang, Lisi Chen, Yang Song, Shen Gao, Shuo Shang
| Challenge: | Existing LRMs often suffer from "overthinking" and excessively long reasoning traces . a dual-level framework for length compression of LRM is proposed . |
| Approach: | They propose a framework for prefix-protected and difficulty-aware compression under hierarchical supervision. |
| Outcome: | The proposed framework reduces token usage while improving accuracy on math benchmarks. |
Leveraging Unpaired Feedback for Long-Term LLM-based Recommendation Tuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study highlights unpaired feedback as a key challenge for long-term LLM-based recommenders . unpaired user feedback is crucial for improving LLMs in dynamic user environments, authors say . |
| Approach: | They propose a framework that incorporates unpaired feedback into LLMs to improve long-term recommendation performance. |
| Outcome: | The proposed framework improves long-term recommendation performance by incorporating unpaired feedback without requiring paired supervision. |
Visually-Guided Policy Optimization for Multimodal Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing RLVRs lack visual faithfulness due to text-dominated reasoning . a novel framework to reinforce visual focus during policy optimization is proposed . |
| Approach: | They propose a framework to reinforce visual focus during policy optimization using visual attention compensation mechanism. |
| Outcome: | The proposed framework exhibits better visual activation and superior performance in multimodal reasoning and visual-dependent tasks. |
VideoPro: Adaptive Program Reasoning for Long Video Understanding (2026.acl-long)
Copied to clipboard
Chenglin Li, Feng Han, Yikun Wang, Ruilin Li, Shuai Dong, Haowen Hou, Haitao Li, Qianglong Chen, Feng Tao, Jingqi Tong, Yin Zhang, Jiaqi Wang
| Challenge: | Existing methods for understanding long videos are limited due to the sparsity of visual evidence relevant to a given query. |
| Approach: | They propose a framework that enables VideoLLMs to reason over long videos and refine their predictions through executable programs. |
| Outcome: | The proposed framework outperforms existing methods across long-video understanding benchmarks. |
A Timestep aware Sentence Embedding and Acme Coverage for Brief but Informative Title Generation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for title generation are based on timestep aware sentence embeddings, but they are not effective for generating a title with appropriate information in the content. |
| Approach: | They propose a Timestep aware Sentence Embedding mechanism which refreshes the sentences’ embeddings with corresponding key words in different decoding timesteps. |
| Outcome: | The proposed framework outperforms existing methods on various title generation tasks and the evaluation scores are significantly higher than previous approaches. |
Entity-level Factual Consistency of Abstractive Text Summarization (2021.eacl-main)
Copied to clipboard
Feng Nan, Ramesh Nallapati, Zhiguo Wang, Cicero Nogueira dos Santos, Henghui Zhu, Dejiao Zhang, Kathleen McKeown, Bing Xiang
| Challenge: | Existing models exhibit entity hallucination, generating names of entities that are not present in the source document. |
| Approach: | They propose to use entity-level factual consistency to improve model quality . they propose to filter the training data to reduce entity hallucination problem . |
| Outcome: | The proposed model can reduce the entity hallucination problem by filtering the training data. |
Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs (2025.coling-main)
Copied to clipboard
| Challenge: | Existing solutions to alleviate hallucination have considered utilizing LLMs’ inherent reasoning abilities to alleviating hallucinism, such as self-correction and diverse sampling methods. |
| Approach: | They propose a counterfactual multi-agent debate framework that predetermines LLMs' stances to override their inherent biases for answer inspection. |
| Outcome: | Extensive experiments on four datasets of three tasks demonstrate the superiority of the proposed framework over existing methods. |
TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM (2025.coling-main)
Copied to clipboard
| Challenge: | Empathetic conversation is a crucial characteristic in daily conversations between individuals. |
| Approach: | They propose an Emotional Knowledge Tool Calling framework which encapsulates commonsense knowledge bases as empathetic tools, enabling LLMs to integrate external knowledge flexibly. |
| Outcome: | The proposed framework can generate empathetic responses effectively on the TOOL-ED dataset. |
IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs (2025.emnlp-industry)
Copied to clipboard
Aosong Feng, Balasubramaniam Srinivasan, Yun Zhou, Zhichao Xu, Kang Zhou, Sheng Guan, Yueyan Chen, Xian Wu, Ninad Kulkarni, Yi Zhang, Zhengyuan Shen, Dmitriy Bespalov, Soumya Smruti Mishra, Yifei Teng, Darren Yow-Bang Wang, Haibo Ding, Lin Lee Cheong
| Challenge: | Existing systems require users to manually select models or employ rigid routing rules that fail to capture the continuous spectrum of query complexity. |
| Approach: | They propose a quality-constrained intelligent prompt routing framework that automatically selects optimal models based on predicted response quality and user-specified tolerance levels. |
| Outcome: | The proposed framework achieves 43.9% cost reduction while maintaining quality parity with strongest model in the Claude family and processes requests with sub-150ms latency. |
Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing transformer models are computationally demanding and prohibitively costly for long sequences due to the quadratic complexity of its selfattention module. |
| Approach: | They propose a transformer-based model that inherits weights from large pretrained models by removing redundancies in hidden sequences using the ready-made Fast Fourier Transform operator. |
| Outcome: | The proposed model outperforms the standard BART model on the long-range modeling benchmark LRA with significant improvements in speed and space. |
MUSTIE: Multimodal Structural Transformer for Web Information Extraction (2023.acl-long)
Copied to clipboard
Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Zenglin Xu, Shaoliang Nie, Sinong Wang, Madian Khabsa, Hamed Firooz, Dongfang Liu
| Challenge: | Recent sequential modeling approaches focus on extracting information from textual sources while ignoring rich information from other modalities such as image and web layout. |
| Approach: | They propose a novel MUltimodal Structural Transformer that integrates multiple modalities for web information extraction. |
| Outcome: | The proposed model outperforms existing methods on WebSRC and Common Crawl benchmarks. |
MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora (2026.findings-acl)
Copied to clipboard
Tao Feng, Yuxiang Wang, Yuancheng Wang, Xueyao Zhang, Dekun Chen, Chaoren Wang, Xun Guan, Zhizheng Wu
| Challenge: | Existing approaches to voice imitation use complex model design and a quality ceiling when synthetic speech is used as training *sources*. |
| Approach: | They propose a model that uses synthetic speech as training *sources* while retaining real recordings as *targets*. |
| Outcome: | The proposed model outperforms existing methods in naturalness while maintaining competitive similarity scores across speaker identity, accent, and emotion dimensions. |
Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing RL methods focus on generation tasks while neglecting dialogue state tracking (DST) for understanding. |
| Approach: | They propose a method that integrates RL into both understanding and generation tasks by introducing step-by-step rewards throughout the token generation. |
| Outcome: | The proposed approach achieves state-of-the-art results on three widely used datasets. |
LipoAgent: Coordinating Fine-Tuned LLM Agents for Safer Lipid Design (2026.findings-acl)
Copied to clipboard
| Challenge: | Lipid nanoparticles (LNPs) are among the most clinically mature platforms for nucleic acid delivery, yet designing lipids that are effective and biologically safe remains a major bottleneck. |
| Approach: | They propose a safety-aware multi-agent LLM framework for lipid discovery that enforces toxicity as a prerequisite for efficiency prediction. |
| Outcome: | The proposed framework achieves an average improvement in mRNA transfection efficiency prediction across multiple foundation models. |
Democratizing Reasoning Ability: Tailored Learning from Large Language Model (2023.emnlp-main)
Copied to clipboard
Zhaoyang Wang, Shaohan Huang, Yuxuan Liu, Jiahai Wang, Minghui Song, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Large language models (LLMs) exhibit impressive emergent abilities in natural language processing, but their democratization is hindered due to huge computation requirements and closed-source nature. |
| Approach: | They propose a tailored learning approach to distill the exclusive reasoning ability to smaller LMs to facilitate democratization. |
| Outcome: | The proposed approach enables the democratization of the exclusive reasoning ability by leveraging the black-box model as a reasoning teacher. |
PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling (2022.coling-1)
Copied to clipboard
Guanting Dong, Daichi Guo, Liwen Wang, Xuefeng Li, Zechen Wang, Chen Zeng, Keqing He, Jinzheng Zhao, Hao Lei, Xinyue Cui, Yi Huang, Junlan Feng, Weiran Xu
| Challenge: | Existing slot filling models memorize inherent patterns of entities and contexts from training data. |
| Approach: | They propose a perturbed semantic structure awareness transferring method for slot filling models . they use two MLM-based training strategies to learn contextual semantic structure and word distribution . |
| Outcome: | The proposed method outperforms existing methods and gains strong generalization while preventing model from memorizing inherent patterns of entities and contexts. |
Deep Cognitive Reasoning Network for Multi-hop Question Answering over Knowledge Graphs (2021.findings-acl)
Copied to clipboard
| Challenge: | Knowledge Graphs (KGs) store structured human knowledge with nodes and edges being entities and relations between them. |
| Approach: | They propose a deep cognitive reasoning network that uses two phases to find answers in large candidate entity sets. |
| Outcome: | The proposed method significantly outperforms state-of-the-art methods on benchmark datasets. |
ORANGE: Text-video Retrieval via Watch-time-aware Heterogeneous Graph Contrastive Learning (2023.emnlp-industry)
Copied to clipboard
Yucheng Lin, Tim Chang, Yaning Chang, Jianqiang Ma, Donghui Li, Ting Peng, Zang Li, Zhiyi Zhou, Feng Wang
| Challenge: | Existing methods for text-video retrieval focus on informative representations and delicate matching mechanisms, but real-world scenarios often involve brief, ambiguous queries and low-quality videos. |
| Approach: | They propose a novel method to learn informative embeddings for queries and videos . they use a watch-time-aware contrastive learning paradigm to capture dependencies . |
| Outcome: | The proposed method is effective in a real-world video-search service. |
MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to multimodal sentiment analysis treat entire modality as an independent unit for feature enhancement or denoising, which often suppresses redundant noise at the cost of weakening critical information. |
| Approach: | They propose a ModaLity-aware noise dynAmic editiNg framework that performs modality-awful block partitioning by dividing features of each modality into multiple blocks. |
| Outcome: | Experiments on five models and four datasets show that MoLAN+ achieves the state-of-the-art performance. |
AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning (2024.emnlp-main)
Copied to clipboard
Hao Sun, Jiayi Wu, Hengyi Cai, Xiaochi Wei, Yue Feng, Bo Wang, Shuaiqiang Wang, Yan Zhang, Dawei Yin
| Challenge: | Recent advances in large language models have been remarkable . users face a choice between using cloud-based LLMs for generation quality or local-based ones for lower computational cost . |
| Approach: | They propose a new LLM utilization paradigm that facilitates collaborative operation . they evaluate AdaSwitch across 7 benchmarks and compare it to other LLMs . |
| Outcome: | The proposed model improves performance of local and cloud agents across 7 benchmarks . it achieves competitive results compared to the cloud agent while utilizing less computational overhead. |
Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues (2026.findings-acl)
Copied to clipboard
Zory Zhang, Pinyuan Feng, Bingyang Wang, Tianwei Zhao, Suyang Yu, Qingying Gao, Hokin Deng, Ziqiao Ma, Yijiang Li, Dezhi Luo
| Challenge: | Where someone looks is a nonverbal communication cue that children and adults readily use. |
| Approach: | They used 1,360 real-world photos to construct evaluation stimuli for Vision-Language Models (VLMs) they found a substantial performance gap between VLMs and humans . |
| Outcome: | The proposed model outperforms existing models in predicting gaze direction using head orientation rather than eye appearance. |
SocialEval: Evaluating Social Intelligence of Large Language Models (2025.acl-long)
Copied to clipboard
Jinfeng Zhou, Yuxuan Chen, Yihan Shi, Xuanming Zhang, Leqi Lei, Yi Feng, Zexuan Xiong, Miao Yan, Xunzhi Wang, Yaru Cao, Jianing Yin, Shuai Wang, Quanyu Dai, Zhenhua Dong, Hongning Wang, Minlie Huang
| Challenge: | Existing work on LLMs does not address their social intelligence (SI) and their discrepancy with humans. |
| Approach: | They propose a script-based bilingual SI benchmark that integrates outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation by manually crafting narrative scripts. |
| Outcome: | The proposed model is based on a script-based bilingual evaluation paradigm that integrates outcome- and process-oriented evaluation by manually crafting narrative scripts. |
Multi-stage Pre-training over Simplified Multimodal Pre-training Models (2021.acl-long)
Copied to clipboard
| Challenge: | Existing multimodal pre-training models require large amounts of training data and have huge model sizes, making them impossible to apply in low-resource situations. |
| Approach: | They propose a multi-stage pre-training method which uses information at different granularities from word, phrase to sentence in both texts and images to pre-train a model in stages. |
| Outcome: | The proposed method outperforms the original model in Image-Text Retrieval task and outperformed the original LXMERT model in downstream tasks. |
A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (2025.findings-acl)
Copied to clipboard
Jinghui Lu, Haiyang Yu, Yanjie Wang, Yongjie Ye, Jingqun Tang, Ziwei Yang, Binghong Wu, Qi Liu, Hao Feng, Han Wang, Hao Liu, Can Huang
| Challenge: | Existing methods for integrating spatial layouts with text have limitations . existing methods produce overly long text sequences or lack autoregressive traits of LLMs . |
| Approach: | They introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM) they use OCR-derived text and spatial layouts to integrate with LLMs for document understanding . |
| Outcome: | The proposed model shows an increase in performance in KIE and VQA tasks. |
WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models (2025.acl-long)
Copied to clipboard
Huawen Feng, Pu Zhao, Qingfeng Sun, Can Xu, Fangkai Yang, Lu Wang, Qianli Ma, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
| Challenge: | Recent code large language models have demonstrated impressive performance on code-related tasks. |
| Approach: | They propose a paradigm that learns from expert battles to address these limitations . they create an arena where leading LLMs challenge each other with evaluations . |
| Outcome: | The proposed model improves on existing models by leveraging expert battles . it achieves state-of-the-art performance even without relying on proprietary models . |
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)
Copied to clipboard
Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei
| Challenge: | Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning. |
| Approach: | They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios. |
| Outcome: | The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics. |
Recurrent Knowledge Identification and Fusion for Language Model Continual Learning (2025.acl-long)
Copied to clipboard
Yujie Feng, Xujia Wang, Zexin Lu, Shenghong Fu, Guangyuan Shi, Yongxin Xu, Yasha Wang, Philip S. Yu, Xu Chu, Xiao-Ming Wu
| Challenge: | Continual learning (CL) is crucial for large language models without costly retraining. |
| Approach: | They propose a framework for recurrent knowledge identification and fusion that enables dynamic estimation of parameter importance distributions to enhance knowledge transfer. |
| Outcome: | The proposed framework mitigates catastrophic forgetting and enhances knowledge transfer. |
Dynamic Curriculum Learning for Low-Resource Neural Machine Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Recent work on neural machine translation (NMT) has demonstrated impressive performance improvements and became the de-facto standard. |
| Approach: | They propose a dynamic curriculum learning method to reorder training samples in training using a Transformer-based system. |
| Outcome: | The proposed method outperforms baselines on three low-resource machine translation benchmarks and different sized data of WMT’16 En-De. |
WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? (2025.emnlp-main)
Copied to clipboard
An-Lan Wang, Jingqun Tang, Lei Liao, Hao Feng, Qi Liu, Xiang Fei, Jinghui Lu, Han Wang, Hao Liu, Yuliang Liu, Xiang Bai, Can Huang
| Challenge: | Existing benchmarks for document understanding in the wild are based on scanned or digital documents . however, these benchmarks fail to capture the challenges posed by documents in the real world . |
| Approach: | They propose a new benchmark that incorporates a diverse set of manually captured document images reflecting real-world conditions. |
| Outcome: | The proposed model is based on a set of manually captured document images reflecting real-world conditions and is compared with digital or scanned documents. |
Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)
Copied to clipboard
Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions? |
| Approach: | They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values. |
| Outcome: | The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure. |
Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training (2025.findings-acl)
Copied to clipboard
Zhijun Wang, Jiahuan Li, Hao Zhou, Rongxiang Weng, Jingang Wang, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang
| Challenge: | Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data. |
| Approach: | They investigate the existence of code-switching in the pre-training corpus and categorize it into four types within two quadrants. |
| Outcome: | The proposed approach improves performance across benchmarks and representation space. |
Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models (2026.acl-long)
Copied to clipboard
Linhao Zhong, Linyu Wu, Bozhen Fang, Tianjian Feng, Chenchen Jing, Wen Wang, Jiaheng Zhang, Hao Chen, Chunhua Shen
| Challenge: | Existing Diffusion Language Models rely on hard binary masking and discrete token assignments, which hinder the revision of early decisions. |
| Approach: | They propose a diffusion-based language modeling approach that replaces hard binary masks with evolving soft token distributions. |
| Outcome: | The proposed approach outperforms existing DLMs on multiple benchmarks. |
HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to fine-tuning language models use zeroth-order optimizers to conserve GPU memory. |
| Approach: | They propose a full-parameter fine-tuning strategy which updates a subset of parameters at each training step. |
| Outcome: | The proposed approach reduces the amount of gradients and optimizer state parameters residing in GPU memory at the same time, thereby reducing GPU memory usage. |
SemanticCamo: Jailbreaking Large Language Models through Semantic Camouflage (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made safety issues of LLMs more prominent and critical. |
| Approach: | They propose a framework which attacks LLMs through semantic camouflage and replaces unsafe content with semantic features to conceal malicious intent . |
| Outcome: | The proposed framework outperforms existing models in over 80% of cases and is highly effective against various defenses. |
PKAG-DDI: Pairwise Knowledge-Augmented Language Model for Drug-Drug Interaction Event Text Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Drug-drug interactions arise when multiple drugs are administered concurrently. |
| Approach: | They propose a pairwise knowledge-augmented generative method for DDIE text generation that integrates biological functions from a knowledge set into a language model. |
| Outcome: | The proposed method outperforms existing methods in DDIE text generation on two professional datasets. |
MUSE: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing research focuses solely on text, leaving a gap with practical applications. |
| Approach: | They propose to synthesize a multimodal conversational recommendation dataset using multimodal large language models to automatically synthesized data from 7,000 conversations in the Clothing domain. |
| Outcome: | The proposed dataset contains 83,148 utterances from 7,000 conversations centered around the Clothing domain. |
SAD: A Large-Scale Strategic Argumentative Dialogue Dataset (2026.acl-long)
Copied to clipboard
YongKang Liu, Jiayang Yu, Mingyang Wang, Yiqun Zhang, Ercong Nie, Shi Feng, Daling Wang, Kaisong Song, Hinrich Schuetze
| Challenge: | Argumentation is a key part of human reasoning and decision-making . existing argumentative corpora focus on single-turn settings, but multi-turn dialogues are often realized as multi-turned dialogues . |
| Approach: | They present a dataset for strategic multi-turn argumentation dialogues . they annotate each utterance with five strategy types, allowing multiple strategies per utterrance . |
| Outcome: | The proposed dataset shows that explicit prompting improves fluency, stylistic coherence and persuasiveness. |
Marrying Up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding (P18-1)
Copied to clipboard
| Challenge: | Experimental results show that the combination of regular expressions and NNs improves learning effectiveness when a small number of training examples are available. |
| Approach: | They propose to combine a neural network (NN) with regular expressions (RE) to improve supervised learning for NLP by exploiting the rich expressiveness of REs at different levels within a NN. |
| Outcome: | The proposed approach significantly improves learning effectiveness when a small number of training examples are available. |
CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models (2025.findings-naacl)
Copied to clipboard
Shangda Wu, Yashan Wang, Ruibin Yuan, Guo Zhancheng, Xu Tan, Ge Zhang, Monan Zhou, Jing Chen, Xuefeng Mu, Yuejie Gao, Yuanliang Dong, Jiafeng Liu, Xiaobing Li, Feng Yu, Maosong Sun
| Challenge: | Current music information retrieval systems struggle to meet linguistic diversity challenges . current systems struggle with text queries in non-English languages . |
| Approach: | They propose a music information retrieval system that supports both ABC notation and MIDI . CLaMP 2 includes a multilingual text encoder and a multiple-modal music encoder . |
| Outcome: | The proposed system achieves state-of-the-art results in multilingual semantic search and music classification across modalities. |
A Co-Attention Neural Network Model for Emotion Cause Analysis with Emotional Context Awareness (D18-1)
Copied to clipboard
| Challenge: | Existing methods ignore the contexts around the emotion word which can provide an emotion cause clue. |
| Approach: | They propose a co-attention neural network model for emotion cause analysis with emotional context awareness. |
| Outcome: | The proposed model outperforms the state-of-the-art methods. |
Probing Audio-Visual Reasoning in Multimodal Language Models through the Lens of Audio (2026.acl-long)
Copied to clipboard
Kaixiong Gong, Kaituo Feng, Bohao Li, Yibing Wang, Mofan Cheng, Shijia Yang, Jiaming Han, Benyou Wang, Yutong Bai, Zhuoran Yang, Xiangyu Yue
| Challenge: | Recent multimodal large language models lack robust audio-visual integration ability and performance on DeafTest is highly correlated with AV-Odyssey accuracy. |
| Approach: | They propose a benchmarking tool that integrates audio-visual reasoning with audio-video cues to infer solutions. |
| Outcome: | The proposed model performs well on DeafTest, but lacks audio perception in simple audio tasks. |
Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation (2025.acl-long)
Copied to clipboard
Peiwen Yuan, Yueqi Zhang, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Existing efficient methods estimate performance of models on large benchmarks, but these methods rely on the assumption that target models have high prediction consistency with source models. |
| Approach: | They propose a method that conducts customized evaluation tailored to each target model. |
| Outcome: | The proposed method reduces the MAE of estimates by 31.4% on benchmarks across 300 models. |
MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Experts (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MultiPL is a special case of multiple natural languages and requires limited computational resources to generate multilingual code. |
| Approach: | They propose to extend LLMs by combining two paired experts to optimize expert selection at token and segment levels. |
| Outcome: | The proposed extension improves the performance of the base LLMs while retaining the most popular ones using limited computational resources. |
SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment (2025.coling-main)
Copied to clipboard
Yuchun Fan, Yongyu Mu, YiLin Wang, Lei Huang, Junhao Ruan, Bei Li, Tong Xiao, Shujian Huang, Xiaocheng Feng, Jingbo Zhu
| Challenge: | Large language models (LLMs) have demonstrated significant improvements in reasoning abilities, but these improvements are primarily focused on English, leading to inferior performance in non-English scenarios. |
| Approach: | They propose a multilingual reasoning alignment approach that fine-tunes the layers responsible for multilingual comprehension in one stage. |
| Outcome: | The proposed method fine-tunes 6 of the 9 layers responsible for multilingual comprehension, while reducing training time by 4.1-11.9 compared to the two-stage method. |
SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning (2026.eacl-long)
Copied to clipboard
| Challenge: | Long-context understanding is a critical capability for large language models . evaluating this capability requires extensive human annotation, which is time-consuming and costly. |
| Approach: | They propose a benchmark to assess citation-grounded long-context reasoning in academic writing. |
| Outcome: | The proposed benchmark compares state-of-the-art models with human experts on two tasks . human experts achieve 90% accuracy, but most models struggle with the cloze-style task . |
DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence? (2024.findings-emnlp)
Copied to clipboard
Zhouhong Gu, Lin Zhang, Xiaoxuan Zhu, Jiangjie Chen, Wenhao Huang, Yikai Zhang, Shusen Wang, Zheyu Ye, Yan Gao, Hongwei Feng, Yanghua Xiao
| Challenge: | Existing LLMs' abilities to detect evidence in long contexts are far inferior to humans. |
| Approach: | They propose a benchmark to assess LLMs' abilities in evidence and multi-step commonsense reasoning within a long context. |
| Outcome: | The proposed method improves the performance of LLMs in evidence detection and commonsense reasoning. |
Boundary Detection with BERT for Span-level Emotion Cause Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | Emotion cause analysis (ECA) is an emerging topic in natural language processing, which aims to identify the reasons behind a given emotion. |
| Approach: | They propose to detect the precise boundaries of text spans conveying accurate emotion causes from the given context by a sequence labeling and position identification problem. |
| Outcome: | The proposed methods outperform existing models on two benchmark datasets on the emotion cause analysis task. |
Mixture-of-LoRAs: An Efficient Multitask Tuning Method for Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Instruction Tuning has the potential to stimulate or enhance specific capabilities of large language models. |
| Approach: | They propose a mixture-of-LoRAs architecture which is a parameter-efficient tuning method designed for multi-task learning with LLMs. |
| Outcome: | The proposed method can be iteratively adapted to a new domain, enabling quick domain-specific adaptation. |
ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to conversational Query Reformulation (CQR) suffer from high dependency on external supervision from annotations or large language models and insufficient alignment between the rewriter and downstream retrievers. |
| Approach: | They propose a framework that transforms context-dependent queries into self-contained forms suitable for off-the-shelf retrievers. |
| Outcome: | The proposed framework outperforms existing methods on topiOCQA and QReCC datasets while using smaller 3B parameter models without external supervision. |
Controllable LLM Reasoning via Sparse Autoencoder-Based Steering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods struggle to control fine-grained reasoning strategies due to conceptual entanglement in LRMs’ hidden states. |
| Approach: | They propose to decompose strategy-entangled hidden states into a disentangled feature space by using Sparse Autoencoders to identify the few strategy-specific features from the vast pool of SAE features. |
| Outcome: | The proposed method outperforms existing methods by 15% in control effectiveness. |
Don’t Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting (2021.findings-emnlp)
Copied to clipboard
| Challenge: | a method for user targeting is developed to identify online users to whom an ad should be targeted. |
| Approach: | They propose a method for automatic augmentation of positive and negative clickthrough data for user targeting models. |
| Outcome: | The proposed method can increase positive and negative instances of positive training instances on two datasets. |
Breaking Language Preference in Multilingual RAG via Language-Controllable Retrieval and Language-Agnostic Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to improve retrieval accuracy and generation quality of large language models suffer from language preference. |
| Approach: | They propose a framework that explicitly disentangles multilingual RAG into language-controllable retrieval and language-agnostic reasoning. |
| Outcome: | Experimental results show that the proposed approach outperforms baselines across multilingual benchmarks. |
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences (2026.acl-long)
Copied to clipboard
Zizhen Li, Chuanhao Li, Yibin Wang, Jianwen Sun, Yukang Feng, Jiaxin Ai, Fanrui Zhang, Mingzhu Sun, Yifei Huang, Kaipeng Zhang
| Challenge: | Recent advances in large language models have expanded the role of board games as creative co-designers . however, current systems lack the capacity to offer constructive critique grounded in the emergent user experience . |
| Approach: | They propose a large language model that internalizes persona-specific reasoning patterns to accurately simulate the subjective feedback of diverse player archetypes. |
| Outcome: | The proposed model outperforms commercial models in community alignment and critique quality. |
Pixel-Level Reasoning Segmentation via Multi-turn Conversations (2025.acl-long)
Copied to clipboard
| Challenge: | Existing visual perception systems focus on region-level segmentation in single-turn dialogues . existing systems cannot reason at the pixel level and comprehend dynamic user intent . |
| Approach: | They propose a task that tracks evolving user intent via multi-turn interactions for fine-grained segmentation. |
| Outcome: | The proposed method outperforms existing baselines in segmentation and reasoning metrics. |
StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) approaches face two challenges: the near-miss reward problem and exploration stagnation. |
| Approach: | They propose an algorithm that partitions valid reasoning chains into reasoning steps using multi-level stepwise hints. |
| Outcome: | The proposed method outperforms competing RLVR enhancement methods across six mathematical benchmarks and two out-of-domain benchmarks. |
DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to augment self-training (ST) in attribute-controllable language generation are limited and limited. |
| Approach: | They propose a new ST framework that integrates self-generated pseudo text into attribute-controllable language generation. |
| Outcome: | The proposed framework can be applied to semi-supervised controllable language generation. |
M2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning (2024.emnlp-main)
Copied to clipboard
Taowen Wang, Yiyang Liu, James Liang, Junhan Zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu
| Challenge: | Multimodal Large Language Models (MLLMs) exhibit remarkable performance across a wide range of domains. |
| Approach: | They propose a multimodal prompt tuning approach for efficient instruction tuning of MLLMs. |
| Outcome: | The proposed approach shows superior performance on multimodal evaluation datasets compared to state-of-the-art methods. |
MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs (2020.acl-main)
Copied to clipboard
Jifan Yu, Gan Luo, Tong Xiao, Qingyang Zhong, Yuquan Wang, Wenzheng Feng, Junyi Luo, Chenyu Wang, Lei Hou, Juanzi Li, Zhiyuan Liu, Jie Tang
| Challenge: | Massive open online courses (MOOCs) are a popular educational platform for advanced research. |
| Approach: | They propose to use MOOCCube to build a large-scale data repository of over 700 MOOC courses, 100k concepts, 8 million student behaviors with an external resource. |
| Outcome: | The proposed datasets show that they can facilitate research in MOOCs. |
AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing LLMs are delicate and elusive in prompt words and styles. |
| Approach: | They propose an LLM-acquainted prompting technique that includes proficient "native-speaking" they propose to use in-context learning to prompt LLMs to perform high-performance reasoning . |
| Outcome: | The proposed technique achieves step-wise prompts in zero-shot scenarios while maintaining the prompt quality. |
Data Swarms: Optimizable Generation of Synthetic Evaluation Data (2026.findings-acl)
Copied to clipboard
| Challenge: | Extensive experiments demonstrate that Data Swarms outperforms eight data generation baselines across five evaluation objectives. |
| Approach: | They propose an algorithm to optimize the generation of synthetic evaluation data and advance quantitative desiderata of LLM evaluation. |
| Outcome: | The proposed algorithm outperforms baseline evaluations and Adversarial Swarms generates harder data while learning from such data. |
EmoCharacter: Evaluating the Emotional Fidelity of Role-Playing Agents in Dialogues (2025.naacl-long)
Copied to clipboard
| Challenge: | EmoCharacter evaluates emotional fidelity of role-playing agents in dialogues . current evaluations focus on personality fidelity, tone imitation, and knowledge consistency . |
| Approach: | They propose a benchmark to assess emotional fidelity of role-playing agents in dialogues using large language models. |
| Outcome: | The proposed benchmark measures emotional fidelity of role-playing agents and the characters they portray. |
Diffusion Language Model Inference with Monte Carlo Tree Search (2026.findings-eacl)
Copied to clipboard
Zheng Huang, Kiran Ramnath, Yueyan Chen, Aosong Feng, Sangmin Woo, Balasubramaniam Srinivasan, Zhichao Xu, Kang Zhou, Shuai Wang, Haibo Ding, Lin Lee Cheong
| Challenge: | Existing methods for inference use heuristics to determine which positions to unmask and which tokens to commit . MEDAL is an inference-time scaling framework that integrates Monte Carlo Tree SEarch initialization for Diffusion Language Model inference. |
| Approach: | They propose a framework that integrates Monte Carlo Tree SEarch initialization for Diffusion Language Model inference. |
| Outcome: | The proposed framework achieves 22.0% improvement over existing inference strategies across multiple benchmarks. |
DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing retrieval-based dialogue systems suffer from slow inference or huge number of parameters. |
| Approach: | They propose a lightweight fully convolutional architecture for response selection using convolution. |
| Outcome: | The proposed architecture extracts matching features of context and response from 3D views. |
Concise and Precise Context Compression for Tool-Using Language Models (2024.findings-acl)
Copied to clipboard
Yang Xu, Yunlong Feng, Honglin Mu, Yutai Hou, Yitong Li, Xinghao Wang, Wanjun Zhong, Zhongyang Li, Dandan Tu, Qingfu Zhu, Min Zhang, Wanxiang Che
| Challenge: | Existing methods suffer from key information loss and difficulty in adjusting the length of compressed sequences based on documentation lengths. |
| Approach: | They propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models. |
| Outcome: | The proposed approach achieves comparable performance to the upper-bound baseline under 16x compression ratio. |
On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference (2026.acl-long)
Copied to clipboard
| Challenge: | Existing work reveals only randomly permuted activations to the client, allowing adversaries to extract model weights. |
| Approach: | They propose an attack that aligns differently shuffled activations to a common permutation and exploits them to extract model weights. |
| Outcome: | The proposed attack can align shuffled activations to a common permutation and exploit them to extract model weights with a query cost of approximately $1. |
DR-HM: Distill-then-Reinforce Training with Cognition-Aware Data Synthesis for Harmful Meme Detection (2026.findings-acl)
Copied to clipboard
Zihan Cheng, Jianxiang Ma, Xiaocui Yang, Peidong Wang, Wen Zhang, Shi Feng, Daling Wang, Yifei Zhang, Mingfu Zhang
| Challenge: | Current methods for harmful meme detection lack the knowledge required to identify such hate . current methods lack the ability to identify cultural stereotypes and visual metaphors . |
| Approach: | They propose a framework that decomposes meme analysis into a human-inspired reasoning process . they propose DR-HM to transfer knowledge from closed-source models while mitigating biases . |
| Outcome: | The proposed framework outperforms existing methods on three benchmark datasets. |
A Novel Two-step Fine-tuning Framework for Transfer Learning in Low-Resource Neural Machine Translation (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing transfer learning methods for neural machine translation use a well-trained translation model to initialize a child model with corresponding datasets. |
| Approach: | They propose a two-step fine-tuning framework for transfer learning in low-resource neural machine translation that adjusts the parent model to fit the child language by using the child source data. |
| Outcome: | The proposed framework improves on five low-resource translations on high-resolution languages. |
MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains (2025.findings-naacl)
Copied to clipboard
Guoli Yin, Haoping Bai, Shuang Ma, Feng Nan, Yanchao Sun, Zhaoyang Xu, Shen Ma, Jiarui Lu, Xiang Kong, Aonan Zhang, Dian Ang Yap, Yizhe Zhang, Karsten Ahnert, Vik Kamath, Mathias Berglund, Dominic Walsh, Tobias Gindele, Juergen Wiest, Zhengfeng Lai, Xiaoming Simon Wang, Jiulong Shan, Meng Cao, Ruoming Pang, Zirui Wang
| Challenge: | Existing benchmarks focus on specific application scenarios, emphasizing task completion but failing to dissect the underlying skills that drive these outcomes. |
| Approach: | They propose a Massive Multitask Agent Understanding benchmark that evaluates LLMs across five domains and offline tasks. |
| Outcome: | The Massive Multitask Agent Understanding (MMAU) benchmark evaluates models across five domains including Tool-use, Directed Acyclic Graph (DAG) QA, Data Science and Machine Learning coding, Contest-level programming and Mathematics. |
SURVEYFORGE : On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing (2025.acl-long)
Copied to clipboard
| Challenge: | SURVEYFORGE automates survey paper writing, but quality gap between LLM-generated and human-written surveys remains significant. |
| Approach: | They propose a survey tool that automatically generates and refines human-written surveys. |
| Outcome: | Experiments show that SURVEYFORGE outperforms previous work such as AutoSurvey in outline quality and content quality. |
Probing and Boosting Large Language Models Capabilities via Attention Heads (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to identifying capabilities rely on external signals with limited structural grounding . emergence of specific capabilities remains poorly understood . |
| Approach: | They propose a lightweight approach that links LLM capabilities to internal components by identifying correspondences at the level of attention heads. |
| Outcome: | The proposed approach improves accuracy on MMLU and BBH by 1 to 1.5 points over gradient-based method and 5 to 6 points over other intermediate-state baselines. |
Triviality Corrected Endogenous Reward (2026.acl-long)
Copied to clipboard
Xinda Wang, Zhengxu Hou, Yangshijie Zhang, null Yanbingren, Jialin Liu, ChenZhuo Zhao, Zhibo Yang, Bin-Bin Yang, Feng Xiao
| Challenge: | Recent work on unsupervised reinforcement learning for mathematical reasoning using confidence-based endogenous rewards focuses on open-ended text generation, requiring either annotated data or powerful closed-source models. |
| Approach: | They propose a method that rewards the relative information gain between a specialist and a generalist reference policy, modulated by a probability-dependent correction mechanism. |
| Outcome: | The proposed model improves on multiple writing benchmarks and model architectures without external supervision and validates generality across different generation tasks. |
Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing pre-training methods are not effective for machine translation tasks. |
| Approach: | They propose a method to pre-train a universal multilingual neural machine translation model . they use random aligned substitution technique to bring words and phrases with similar meanings closer in the representation space. |
| Outcome: | The proposed approach improves translation quality on low, medium, rich resource languages. |
R3: End-to-End Reasoning-based Planning for Multi-step Retrosynthesis via Reinforcement Learning (2026.acl-long)
Copied to clipboard
YiFei Wang, Qizhi Pei, Jiangtao Feng, Yuntian Shi, Yi Duan, Lihao Wang, Lei Bai, Lijun Wu, Wei-Ying Ma, Hao Zhou
| Challenge: | Experimental results show that R3 is a superior alternative to traditional search algorithms for multistep retrosynthesis planning. |
| Approach: | They propose a framework that reformulates multistep retrosynthetic planning as a generative reasoning task. |
| Outcome: | The proposed framework achieves state-of-the-art Top-1 accuracy of 43.7% on retrobench . it leverages Large Language Models to reformulate multistep retrosynthesis as a generative reasoning task. |
InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles (2025.emnlp-main)
Copied to clipboard
Zizhen Li, Chuanhao Li, Yibin Wang, Qi Chen, Diping Song, Yukang Feng, Jianwen Sun, Jiaxin Ai, Fanrui Zhang, Mingzhu Sun, Kaipeng Zhang
| Challenge: | Recent large language models (LLMs) have demonstrated strong reasoning abilities across complex mathematical and scientific domains. |
| Approach: | They propose a framework to assess whether LLMs can capture and apply personalized reasoning styles in social deduction games. |
| Outcome: | The proposed framework evaluates LLMs on the game Avalon and shows that they can capture and apply individualized reasoning styles. |
Co-VQA : Answering by Interactive Sub Question Sequence (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to Visual Question Answering (VQA) answer questions directly, but people usually decompose a complex question into a sequence of simple sub questions. |
| Approach: | They propose a conversation-based VQA framework that decomposes questions into sub questions and answers them one-by-one. |
| Outcome: | The proposed framework achieves state-of-the-art on VQA 2.0 and VQA-CP v2 datasets. |
An Intra-Class Relation Guided Approach for Code Comment Generation (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent work in code comment generation assumes that all information required to generate comments is encoded in the target function itself, yet in most realistic situations, it is hard to understand a function in isolation from the surrounding context. |
| Approach: | They propose a graph-based learning framework to capture various relations among functions in a class file. |
| Outcome: | The proposed method outperforms baseline models on automatic and human evaluation metrics on a Java dataset collected from real-world projects. |
Operation-guided Neural Networks for High Fidelity Data-To-Text Generation (D18-1)
Copied to clipboard
| Challenge: | Recent neural models for data-to-text generation generate descriptions that are not consistent with structured data. |
| Approach: | They propose a framework for data-to-text generation that uses symbolic operations to generate texts from structured data. |
| Outcome: | The proposed framework improves the fidelity of the generated texts to the input structured data. |
Humans or LLMs as the Judge? A Study on Judgement Bias (2024.emnlp-main)
Copied to clipboard
| Challenge: | Proprietary models such as GPT-4, Claude, Gemini-Pro and others are being democratized to improve evaluations of LLMs. |
| Approach: | They propose a framework that is free from referencing groundtruth annotations for investigating **Misinformation Oversight Bias**, **Gender Bia**,**Authority Bia* and **Beauty Bia's** on LLM and human judges. |
| Outcome: | The proposed framework investigates **Misinformation Oversight Bias**, **Gender Bia**,**Authority Bia* and **Beauty Bia' on LLM and human judges. |
MHGRL: An Effective Representation Learning Model for Electronic Health Records (2024.lrec-main)
Copied to clipboard
| Challenge: | Effective EHR representations are key to achieving high performance in healthcare applications. |
| Approach: | They propose a multimodal heterogeneous graph-enhanced representation learning to learn EHR representations using medical ontology and textual notes. |
| Outcome: | The proposed model outperforms baseline models on two real clinical datasets in downstream tasks. |
Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits (2025.coling-main)
Copied to clipboard
Bohan Li, Jiannan Guan, Longxu Dou, Yunlong Feng, Dingzirui Wang, Yang Xu, Enbo Wang, Qiguang Chen, Bichen Wang, Xiao Xu, Yimeng Zhang, Libo Qin, Yanyan Zhao, Qingfu Zhu, Wanxiang Che
| Challenge: | Existing data on MBTI personality detection are based on self-reported labels and fail to capture the full range of population personality traits. |
| Approach: | They construct a manually annotated MBTI personality detection dataset with soft labels under the guidance of psychologists and use them to identify the task. |
| Outcome: | The MBTIBench is the first manually annotated MBti personality detection dataset with soft labels under the guidance of psychologists. |
Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective (2025.findings-acl)
Copied to clipboard
Yipeng Kang, Junqi Wang, Yexin Li, Mengmeng Wang, Wenming Tu, Quansen Wang, Hengli Li, Tingjun Wu, Xue Feng, Fangwei Zhong, Zilong Zheng
| Challenge: | Current approaches to value alignment focus on a few core values, such as helpfulness, harmlessness, and honesty. |
| Approach: | They propose to use latent causal value graphs to guide two lightweight value-steering methods . role-based prompting and sparse autoencoder (SAE) steering are also used . |
| Outcome: | Experiments on Gemma-2B-IT and Llama3-8B- IT show that the proposed methods are effective and controllable. |
Can Graph Descriptive Order Affect Solving Graph Problems with LLMs? (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have achieved significant success in reasoning tasks, including mathematical reasoning and logical deduction. |
| Approach: | They conduct the first comprehensive analysis of how the order of graph descriptions impacts LLM performance. |
| Outcome: | The results show that graph descriptions significantly improve LLMs’ comprehension of graph structures, and the robustness of LLM models to graph description order varies across different tasks. |
ReList: A Multi-objective Reasoning Framework for Diversified Listwise Query Recommendation (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods for related search have limited semantic redundancy and wasted retrieval quota . generative retrieval approaches lack explicit reasoning, relying on superficial click-through rate rewards . |
| Approach: | They propose a framework that transforms related search into a reasoning-enhanced listwise generation task. |
| Outcome: | Experimental results show that ReList outperforms state-of-the-art methods in query diversity and user engagement. |
Transformation of Dense and Sparse Text Representations (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to NLP to leverage sparsity have been limited due to the gap with dense representations. |
| Approach: | They propose a Semantic Transformation method to bridge dense and sparse spaces and propose supervised NLP tasks to use both spaces. |
| Outcome: | Experiments with classification tasks and natural language inference tasks show that the proposed method is effective. |
SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget (2024.acl-long)
Copied to clipboard
| Challenge: | Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) but memory-constrained devices are a major concern in edge AI training and serving. |
| Approach: | They propose a framework for efficient serving of MoE-based large language models with tunable memory budgets. |
| Outcome: | Experiments show that SwapMoE can reduce memory consumption while maintaining reasonable accuracy. |
MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value Extraction (2023.findings-acl)
Copied to clipboard
Li Yang, Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Yu Chen, Madian Khabsa, Sinong Wang, Zenglin Xu, Dongfang Liu
| Challenge: | Existing methods for product attribute value extraction focus on extracting values for a set of known attributes with sufficient training data. |
| Approach: | They propose a prompt tuning approach to extract attributes from product information using mixed prompts. |
| Outcome: | The proposed approach improves on two product benchmarks and shows parameter-efficient training and avoids model overfitting. |
Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning (2025.acl-long)
Copied to clipboard
Yongxin Xu, Ruizhe Zhang, Xinke Jiang, Yujie Feng, Yuzhen Xiao, Xinyu Ma, Runchuan Zhu, Xu Chu, Junfeng Zhao, Yasha Wang
| Challenge: | Existing methods for integrating internal and external knowledge lack effective control mechanisms for generating hallucinations and dealing with outdated knowledge. |
| Approach: | They propose a framework that decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness. |
| Outcome: | The proposed framework decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness. |
TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos (2025.acl-long)
Copied to clipboard
Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang, Shi Feng, Daling Wang, Linhao Yu, Xingguang Ji, Yu Tian, V. W., Fuzheng Zhang
| Challenge: | Existing benchmarks for video understanding often focus on specific aspects, overlooking the holistic nature of video content. |
| Approach: | They propose a temporal-oriented benchmark for fine-grained understanding on dense dynamic videos with two complementary tasks: captioning and QA. |
| Outcome: | The proposed model performs well on diverse video scenarios and dynamic videos, with interpretable and robust evaluation criteria. |
Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs (2024.findings-acl)
Copied to clipboard
| Challenge: | Controllable text generation is increasingly tailored to individual preferences. |
| Approach: | They propose to evaluate the attribute intensity of text generated by large language models on five different attributes for error, variation of the generated sentence's intensities and relevance to the generation questions. |
| Outcome: | The proposed methods are based on Elo rating system and GPT4 and are able to be trained without training. |
Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression (2026.acl-long)
Copied to clipboard
Liang Zhao, Xiaocheng Feng, Weihong Zhong, Lei Huang, Kun Zhu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin
| Challenge: | Recent methods to reduce the KV cache size fail to identify crucial KVs for generation while excluding others accurately, resulting in severe information loss. |
| Approach: | They propose an intention-aware KV cache eviction method that identifies and retains crucial KVs according to the attention distribution of intention, which semantically reflects the user’s goal and determines which part of the context is relevant. |
| Outcome: | The proposed method can maintain the model performance while reducing the KV cache size from 128K to 2K, leading to a 6.3x increase in decoding speed and 7.8x enhancement in memory efficiency compared to the default setting. |
Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization (2025.findings-acl)
Copied to clipboard
| Challenge: | Extensive experiments on real-world datasets demonstrate that DPL significantly enhances LLM personalization. |
| Approach: | They propose a novel approach that emphasizes extracting inter-user differences to enhance LLM personalization. |
| Outcome: | The proposed approach extracts inter-user differences to enhance LLM personalization. |
Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization (2025.acl-long)
Copied to clipboard
| Challenge: | Protein language models pose significant risks of generating harmful sequences, e.g., viral transmissibility, drug resistance, environmental imbalances, public health crises, etc. |
| Approach: | They propose a protein-based model that integrates prior knowledge via a Protein Safety Knowledge Graph to minimize the risk of generating harmful sequences. |
| Outcome: | The proposed framework reduces the likelihood of producing hazardous sequences while maintaining high functionality. |
Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation (2022.acl-long)
Copied to clipboard
Mingzhe Li, XieXiong Lin, Xiuying Chen, Jinxiong Chang, Qishen Zhang, Feng Wang, Taifeng Wang, Zhongyi Liu, Wei Chu, Dongyan Zhao, Rui Yan
| Challenge: | Existing studies focus on contrastive learning on the instance level without discriminating the contribution of each word. |
| Approach: | They propose a hierarchical contrastive learning mechanism which can unify semantic meaning in the input text. |
| Outcome: | The proposed model outperforms baselines on storytelling, paraphrasing, dialogue generation, and storytelling tasks. |
Soft Orthogonal Low-Rank Adaptation for Knowledge Sharing in Large Language Model Continual Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for continual learning (CL) are designed to mitigate catastrophic forgetting while neglecting knowledge sharing across tasks. |
| Approach: | They propose a framework that facilitates knowledge transfer while mitigating catastrophic forgetting by assigning task-specific parameter subspaces to new tasks . they then leverage attribution scores to evaluate task similarity and employ soft orthogonality between task- specific subspace . |
| Outcome: | The proposed framework facilitates knowledge transfer while mitigating catastrophic forgetting. |
Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding (2026.eacl-long)
Copied to clipboard
| Challenge: | Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts. |
| Approach: | They propose a lightweight auxiliary model trained with a GAE-inspired objective to predict final instruction-following quality from partial generations. |
| Outcome: | The proposed model achieves 10 points improvement in CLAP score over baseline AR models while maintaining computational parity with best-of-N decoding. |
HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have incorporated reward models to guide response selection or decoding, aiming to obtain higher-quality data. |
| Approach: | They propose a Hierarchical Sampling framework for self-taught reasoners that allocates a fixed sampling budget to problem boundary-level problems and then reallocates the remaining budget toward high-utility problems during a re-sampling phase. |
| Outcome: | The proposed framework outperforms baseline models without additional sampling budgets across multiple reasoning benchmarks and backbone LLMs. |
PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator (2024.acl-long)
Copied to clipboard
| Challenge: | Recent efforts to democratize ChatGPT have focused on leveraging real user and ChatGPP dialogues, but the most direct human needs are often ignored. |
| Approach: | They propose a method to simulate human behavior better by using real human-like questions extracted from real human conversations as a learning goal and a user simulator called ‘Socratic’. |
| Outcome: | The proposed model achieves SoTA performance among LLaMA-based 7B models in MT-Bench. |
UCL-Bench: A Chinese User-Centric Legal Benchmark for Large Language Models (2025.findings-naacl)
Copied to clipboard
Ruoli Gan, Duanyu Feng, Chen Zhang, Zhihang Lin, Haochen Jia, Hao Wang, Zhenyang Cai, Lei Cui, Qianqian Xie, Jimin Huang, Benyou Wang
| Challenge: | Existing legal benchmarks focusing on knowledge and logic evaluate LLMs on various tasks in legal domain, but few have explored the practical application of LLM by actual users. |
| Approach: | They propose a Chinese user-centric legal benchmark that aims to assess the practical application of LLMs by real users. |
| Outcome: | The proposed model outperforms existing models on various tasks in legal domain but does not outperfect ChatGPT. |
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. |
Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Light Latent-space Decoding (L2D) is an efficient and efficient latent- space decoding method. |
| Approach: | They propose to bypass language-space decoding by matching candidate items with LLM's internal thought representations in the latent space. |
| Outcome: | The proposed method is 10x faster than language-space decoding while maintaining or enhancing performance. |
Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods suffer from incomprehensive persona tags that have unique and obscure meanings to describe human’s personality. |
| Approach: | They propose a graph convolution network model with addressee selecting mechanism that integrates personas, dialogue utterances, and external text knowledge in a unified graph. |
| Outcome: | The proposed model outperforms baselines by large margins and improves persona consistency in the generated responses. |
Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent studies on ABSA focus on Target-oriented Opinion Words (or Terms) Extraction . Experimental results indicate that TSMSA outperforms the benchmark methods on TOWE significantly . |
| Approach: | They propose to use a pre-trained language model with multi-head self-attention to integrate TOWE with AOPE to extract aspects and opinion terms in pairs. |
| Outcome: | The proposed structure outperforms the benchmark methods on TOWE significantly . the proposed structure is similar or even better than state-of-the-art AOPE models . |
Enabling Unsupervised Neural Machine Translation with Word-level Visual Representations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Unsupervised neural machine translation methods have been observed to make particular errors in comparison to supervised machine translation, such as confusing nouns that pertain to the same semantic category. |
| Approach: | They propose a method that incorporates images at the word level to augment lexical mappings. |
| Outcome: | Experiments on a multi-lingual dataset show that the proposed method generates more accurate translations with only monolingual data. |
KC-ISA: An Implicit Sentiment Analysis Model Combining Knowledge Enhancement and Context Features (2022.coling-1)
Copied to clipboard
| Challenge: | Existing research results on explicit sentiment analysis are limited . implicit sentiment analysis is a process of analyzing text based on whether it contains explicit sentiment words. |
| Approach: | They propose a model that integrates external knowledge and contextual features . they use a knowledge graph to supplement implicit sentiment expression . |
| Outcome: | The proposed model can achieve better results on the SMP2019 implicit sentiment analysis dataset. |
Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for novel category discovery focus on the scenario where known and novel categories are of the same granularity. |
| Approach: | They propose a novel scenario for fine-grained category discovery under coarse-grain supervision that allows for adapting models to categories of different granularity from known ones. |
| Outcome: | The proposed model can adapt models to categories of different granularity from known ones and reduce labeling cost. |
Word-level Cross-lingual Structure in Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated exceptional performance across a broad spectrum of cross-lingual Natural Language Processing (NLP) tasks. |
| Approach: | They propose to use Word-level Cross-lingual Structure to prove that the word-level embedding on the hidden layers isomorphic between languages. |
| Outcome: | The proposed method significantly improves on two representative LLM foundations, LLaMA2 and BLOOM. |
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory (2026.acl-long)
Copied to clipboard
Zihao Tang, Xin Yu, Ziyu Xiao, Zengxuan Wen, Zelin Li, Jiaxi Zhou, Hualei Wang, Haohua Wang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Existing methods for retrieving historical messages are based on similarity-based mechanisms. |
| Approach: | They propose a system that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection. |
| Outcome: | The proposed framework achieves state-of-the-art on long-term memory benchmarks and 93.9 on LoCoMo and 91.6 on LongMemEval-S. |
MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free (2026.findings-acl)
Copied to clipboard
Yishu Lei, Shuwei He, Hu Jing, Dan Zhang, Xianlong Luo, Danxiang Zhu, Shikun Feng, Rui Liu, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Existing research on Large Language Models (LLMs) limited to textual input modality . acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context. |
| Approach: | They propose a sparse Mixture-of-Experts architecture to decouple acoustic information by routing audio tokens to specialized experts. |
| Outcome: | The proposed architecture outperforms existing models on audio semantic and paralinguistic tasks while retaining shared experts for global context. |
Guiding Variational Response Generator to Exploit Persona (2020.acl-main)
Copied to clipboard
Bowen Wu, MengYuan Li, Zongsheng Wang, Yifu Chen, Derek F. Wong, Qihang Feng, Junhong Huang, Baoxun Wang
| Challenge: | Neural Response Generators (NRGs) use persona information of users to perform personalized conversations . current studies focus on incorporating explicit meta-data of user profiles or character descriptions to generate persona-aware responses. |
| Approach: | They propose to use persona information of users in Neural Response Generators to perform personalized conversations. |
| Outcome: | The proposed method improves persona-aware response generation and the metrics are reasonable to evaluate them. |
Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)
Copied to clipboard
Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni
| Challenge: | MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture. |
| Approach: | They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content. |
| Outcome: | The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context. |
DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models are limited by challenges in factuality and hallucinations to be directly employed off-the-shelf for judging the veracity of news articles. |
| Approach: | They propose to integrate large language models into the news pipeline by generating news reactions and generating proxy tasks. |
| Outcome: | The proposed model outperforms state-of-the-art baselines by 16.8% in macro f1-score on seven datasets with three LLMs. |
Neighborhood Matching Network for Entity Alignment (2020.acl-main)
Copied to clipboard
| Challenge: | Structural heterogeneity between knowledge graphs is an outstanding challenge for entity alignment. |
| Approach: | They propose a framework for entity alignment that uses a neighborhood matching module to combine neighborhood differences. |
| Outcome: | The proposed framework outperforms existing methods on three datasets. |
CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing pruning methods rely on spatial proximity and remove relevant relations, thereby undermining reliable spatial reasoning. |
| Approach: | They propose a scene graph pruning model that integrates fuzzy semantic relevance with spatial proximity to estimate the importance of relations. |
| Outcome: | Experiments show that CAPruner outperforms proximity-based pruning with negligible cost savings. |
IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)
Copied to clipboard
Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen
| Challenge: | Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content. |
| Approach: | They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question . |
| Outcome: | The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types. |
LLMEdgeRefine: Enhancing Text Clustering with LLM-Based Boundary Point Refinement (2024.emnlp-main)
Copied to clipboard
| Challenge: | LLMEdgeRefine is an iterative clustering method enhanced by large language models . existing clustering methods struggle with domain-specific fine-tuning and outliers . |
| Approach: | They propose an iterative clustering method enhanced by large language models focusing on edge points refinement . authors propose to use LLMs to iterate clusters and iterating to improve semantic coherence . |
| Outcome: | The proposed method outperforms state-of-the-art methods and offers robustness, adaptability, and cost-efficiency for diverse text clustering applications. |
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 . |
Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large vision-language models exhibit an imbalance in multilingual capabilities . |
| Approach: | They propose a training recipe that achieves efficient multilingual enhancement for LVLMs by Precise Language Specific layers fine-tuning. |
| Outcome: | The proposed training recipe achieves efficient multilingual enhancement for LVLMs by fine-tuning language specific layers. |
Disco-RAG: Discourse-Aware Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
Dongqi Liu, Hang Ding, Qiming Feng, Xurong Xie, Zhucun Xue, Chengjie Wang, Jian Li, Jiangning Zhang, Yabiao Wang
| Challenge: | Existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing structural cues and constrains its ability to synthesize knowledge from dispersed evidence across documents. |
| Approach: | They propose a framework that explicitly injects discourse signals into the generation process. |
| Outcome: | Experiments on question answering and long-document summarization benchmarks show the efficacy of the proposed framework. |
CoV: Chain-of-View Prompting for Spatial Reasoning (2026.findings-acl)
Copied to clipboard
Haoyu Zhao, Akide Liu, Zeyu Zhang, Weijie Wang, Feng Chen, Ruihan Zhu, Gholamreza Haffari, Bohan Zhuang
| Challenge: | Embodied question answering requires collecting context that is distributed across multiple viewpoints . most recent vision–language models (VLMs) are constrained to a fixed and finite set of input views . |
| Approach: | They propose a training-free, test-time reasoning framework that transforms a VLM into an active viewpoint reasoner through a coarse-to-fine exploration process. |
| Outcome: | The proposed framework improves LLM-Match performance by 11.98% on four mainstream VLMs. |
The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation (2023.findings-acl)
Copied to clipboard
| Challenge: | Event extraction (EE) is a fundamental information extraction task aimed at extracting events from plain texts. |
| Approach: | They propose to specify data preprocessing, standardize outputs, and provide pipeline evaluation results to avoid these pitfalls. |
| Outcome: | The results show that the evaluations are reliable and lack pipeline evaluations. |
CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for predicting clinical outcomes have focused on capturing temporal interactions within individual samples and fusing multimodal information, overlooking critical temporal patterns across different patients. |
| Approach: | They propose a cross-modal temporal pattern discovery framework to extract temporal patterns from multimodal EHR data. |
| Outcome: | The proposed framework extracts meaningful cross-modal temporal patterns from multimodal EHR data. |
LLaMA Pro: Progressive LLaMA with Block Expansion (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies have demonstrated that pre-trained LLMs are limited in certain domains, such as programming, mathematics, biomedical, or finance. |
| Approach: | They propose a new post-pretraining method with an expansion of Transformer blocks to tune the expanded blocks using only new corpus, efficiently and effectively improving the model’s knowledge while mitigating forgetting. |
| Outcome: | The proposed model outperforms existing models in programming and math and its instruction-following counterpart LLaMA Pro-8.3B in general tasks, programming, and mathematics. |
Improving Language Model Reasoning with Self-motivated Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Large-scale high-quality training data is important for improving the performance of models. |
| Approach: | They propose a framework that motivates the model to automatically generate rationales on existing datasets and improves the performance of reasoning through reinforcement learning. |
| Outcome: | The proposed model outperforms InstructGPT on multiple reasoning datasets and outperformed InstructGPT on other datasets. |
Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL (2025.findings-acl)
Copied to clipboard
Wichayaporn Wongkamjan, Yanze Wang, Feng Gu, Denis Peskoff, Jonathan K. Kummerfeld, Jonathan May, Jordan Lee Boyd-Graber
| Challenge: | Future human-AI interaction tools can build on our methods for deception detection by triggering friction to give users a chance to interrogate suspicious proposals. |
| Approach: | They propose to use CTRL-D to detect deception in a board game called Diplomacy . CTRL is a counterfactual RL that has a good recall and almost perfect precision . future tools could build on this to reevaluate trust in suspicious negotiations . |
| Outcome: | The proposed method detects human deception with a high precision when compared to a Large Language Model approach that flags many true messages as deceptive. |
Generic Temporal Reasoning with Differential Analysis and Explanation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing temporal reasoning models drop to random guessing on TODAY, suggesting that they heavily rely on spurious information rather than proper reasoning for temporal predictions. |
| Approach: | They propose a task called TODAY that evaluates whether systems can correctly understand the effect of incremental changes in temporal relation distributions. |
| Outcome: | The proposed task outperforms existing models, including GPT-3.5, on in-domain benchmarks while allowing for more appropriate annotations. |
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. |
Easy First Relation Extraction with Information Redundancy (D19-1)
Copied to clipboard
| Challenge: | Existing relation extraction models make decisions globally using integer linear programming . Existing approaches require time and memory to encode redundant information for ILP . |
| Approach: | They propose an easy first approach for relation extraction with information redundancies embedded in local sentence extractors to resolve conflict decisions with domain and uniqueness constraints. |
| Outcome: | The proposed approach outperforms both ILP and neural network-based methods in relation extraction (RE) studies have shown that the proposed approach improves the efficiency and accuracy of RE models. |
What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection (2024.acl-long)
Copied to clipboard
| Challenge: | Social media bot detection has always been an arms race between advancements in machine learning and adversarial bot strategies to evade detection. |
| Approach: | They propose a mixture-of-heterogeneous-experts framework to divide and conquer diverse user information modalities and propose LLM-guided manipulation of user textual and structured information to evade detection. |
| Outcome: | The proposed framework outperforms state-of-the-art baselines on 1,000 annotated examples while bringing down existing detectors by 29.6% and harming calibration and reliability of bot detection systems. |
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities (2025.findings-naacl)
Copied to clipboard
Jiarui Lu, Thomas Holleis, Yizhe Zhang, Bernhard Aumayer, Feng Nan, Haoping Bai, Shuang Ma, Shen Ma, Mengyu Li, Guoli Yin, Zirui Wang, Ruoming Pang
| Challenge: | Recent advances in large language models have led to a growing interest in tool assisted LLMs . toolSandbox includes stateful tool execution, implicit state dependencies between tools . |
| Approach: | a new tool-based evaluation tool is released to help LLMs evaluate their tool-use capabilities. a tool-driven evaluation tool includes stateful tool execution, implicit state dependencies between tools and a built-in user simulator. |
| Outcome: | the toolSandbox evaluation benchmark shows that open source and proprietary models have a performance gap . the benchmarks show that even the most capable LLMs are challenged by state dependent tasks . |
JX4MEI: Multimodal Semantically-Enhanced LLM for Joint Multimodal Emotion-Intent Explanation and Classification (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing multimodal emotion and intent recognition tasks focus on classification, not rationale and intrinsic connections between these states. |
| Approach: | They propose a task that requires models to jointly predict emotion and intent while generating natural language explanations for why they co-occur. |
| Outcome: | The proposed model outperforms baseline models in prediction and explanation generation. |
AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation (2026.findings-acl)
Copied to clipboard
Wentao Shi, Yu Wang, Yuyang Zhao, Yuxin Chen, Fuli Feng, Xueyuan Hao, Xi Su, Qi GU, Hui Su, Xunliang Cai, Xiangnan He
| Challenge: | Existing approaches to verify agent behaviors in complex environments rely on rule-based verifiers or LLM-as-a-Judge models. |
| Approach: | They propose a benchmark to evaluate Agent-as-a-Judge across three domains . the benchmark covers search, data systems, and graphical user interfaces - with 155 tasks and 516 trajectories . |
| Outcome: | The proposed benchmark outperforms existing benchmarks in search, data systems, and GUI domains while revealing open challenges in agent-based verification. |
CogLM: Tracking Cognitive Development of Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have recently shown remarkable abilities across a wide variety of tasks, but few studies have explored the reasons behind the evolutionary relationship among various abilities. |
| Approach: | They construct a benchmark CogLM based on Piaget's Theory of Cognitive Development (PTC) which measures the cognitive levels of Large Language Models (LLMs) using 1,220 questions spanning 10 cognitive abilities crafted by more than 20 human experts. |
| Outcome: | The proposed framework provides a comprehensive testbed for the cognitive levels of LLMs. |
RouterHGC: Optimized Router for LLM-based Multi-Agent Systems via Heterogeneous Graph Contrastive Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs)-driven Multi-Agent Systems (MAS) have demonstrated remarkable scalability and generalizability across complex tasks. |
| Approach: | They propose a new framework for routing using large language models . they formalize routing as node selection through edge-weight prediction . |
| Outcome: | The proposed framework outperforms the best single LLM and baselines on five datasets . it achieves 0.80%–6.17% accuracy gains on MATH and HotpotQA while reducing inference cost by 27.40%. |
ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks focus on image-based question answering (QA) but ignore the fundamental challenges of efficient retrieval, comprehension, and reasoning within dense visual documents. |
| Approach: | They propose a novel multi-agent RAG framework tailored for complex reasoning across visual documents that employs a Gaussian Mixture Model (GMM)-based hybrid strategy to handle multi-modal retrieval. |
| Outcome: | The proposed framework outperforms existing methods by over 10% on the competitive ViDoSeek benchmark. |
FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for retrieval-augmented generation struggle with a trade-off between flexibility and retrieval quality. |
| Approach: | They propose a flexible modular KG-RAG framework that uses query text instead of KGs . they propose to use query text to infer the structural information of reasoning paths . |
| Outcome: | The proposed method achieves state-of-the-art performance with high efficiency and low resource consumption. |
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning (2026.acl-long)
Copied to clipboard
Siyuan Gan, Jiaheng Liu, Boyan Wang, Tianpei Yang, Runqing Miao, Yuyao Zhang, Fanyu Meng, Junlan Feng, Linjian Meng, Jing Huo, Yang Gao
| Challenge: | Existing work on large reasoning models (LRMs) focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query. |
| Approach: | They propose to use reinforcement learning to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query. |
| Outcome: | The proposed model reduces token usage by around 50%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5b, while significantly improving accuracy. |
Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing video QA models lack the capacity for deep video understanding and flexible multistep reasoning. |
| Approach: | They propose a video question answering model which performs dynamic multistep reasoning between questions and videos. |
| Outcome: | The proposed model improves on three widely used video QA datasets and displays better interpretability by backtracing along with the attention mechanisms to the video scene graphs. |
PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs (2024.findings-acl)
Copied to clipboard
Rongzhi Zhang, Jiaming Shen, Tianqi Liu, Haorui Wang, Zhen Qin, Feng Han, Jialu Liu, Simon Baumgartner, Michael Bendersky, Chao Zhang
| Challenge: | Knowledge distillation (KD) is a technique for transferring expertise from large teacher models to compact student models with reduced memory footprints and inference costs. |
| Approach: | They propose to transfer knowledge from large teacher models to compact student models by exploiting teacher-student capacity discrepancies to generate pseudo-preference pairs where teacher outputs are preferred over student outputs. |
| Outcome: | The proposed framework exploits teacher-student capacity discrepancy to generate pseudo-preference pairs where teacher outputs are preferred over student outputs. |
Multimodal Sentiment Detection Based on Multi-channel Graph Neural Networks (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies only considered the representation of a single image-text post . Fig. 1 shows that multimodal sentiment expressions have global characteristics . |
| Approach: | They propose a multi-channel Graph Neural Networks with Sentiment-awareness approach for image-text sentiment detection. |
| Outcome: | The proposed approach is effective for image-text sentiment detection on three publicly available datasets. |
Cross-lingual Feature Extraction from Monolingual Corpora for Low-resource Unsupervised Bilingual Lexicon Induction (2022.coling-1)
Copied to clipboard
| Challenge: | Unsupervised bilingual lexicon induction models fail on low-resource language pairs due to insufficient initialization. |
| Approach: | They propose a method to learn cross-lingual features from monolingual corpora for low-resource UBLI by integrating cross-linguistic representations with pre-trained word embeddings in a fully unsupervised initialization. |
| Outcome: | The proposed method outperforms state-of-the-art methods on low-resource language pairs and improves representational ability and robustness of existing embedding models. |
FrontCoder: Scaling Visual Fidelity in Front-End Code Generation (2026.findings-acl)
Copied to clipboard
Jun Feng, Jian Yang, Wei Zhang, Jing Wang, Keyi Chen, Xiaokun Yang, Weicheng Gu, Yihang Lou, Yan Bai, Xianglong Liu
| Challenge: | Existing work on front-end code generation fails to provide visual fidelity and rendering quality for front- end developers. |
| Approach: | They propose a three-stage pipeline to enhance front-end code generation capabilities in LLMs . they use synthetic data, quality-controlled supervised fine-tuning, and reinforcement learning . |
| Outcome: | The proposed model achieves competitive performance with frontier models while maintaining generation efficiency. |
Enhancing Key-Value Memory Neural Networks for Knowledge Based Question Answering (N19-1)
Copied to clipboard
| Challenge: | Existing Key-value Memory Neural Networks are effective for shallow reasoning over documents . but extending them to Knowledge Based Question Answering is not trivial . |
| Approach: | They propose a mechanism to enable conventional KV-MemNNs models to perform interpretable reasoning for complex questions. |
| Outcome: | The proposed solution provides better reasoning abilities on complex questions and achieves state-of-the-art performance. |
Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for hierarchical text classification focus on modeling the text, but the concept of sharing among classes has been ignored in previous work. |
| Approach: | They propose a concept-based method that explicitly represents the concept and model the sharing mechanism among classes for the hierarchical text classification. |
| Outcome: | The proposed method outperforms state-of-the-art methods on two widely used datasets. |
APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models (2023.emnlp-main)
Copied to clipboard
Qifan Wang, Yuning Mao, Jingang Wang, Hanchao Yu, Shaoliang Nie, Sinong Wang, Fuli Feng, Lifu Huang, Xiaojun Quan, Zenglin Xu, Dongfang Liu
| Challenge: | Existing prompt tuning methods only introduce prompts at the input layer, limiting performance and leaving large room for improvement. |
| Approach: | They propose a method that involves tuning a small set of soft prompts for pre-trained language models. |
| Outcome: | The proposed method outperforms state-of-the-art methods with pre-trained models on the SuperGLUE benchmark. |
RASD: Retrieval-Augmented Speculative Decoding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for generating draft tokens rely on lightweight draft models or additional model structures to generate tokens and retrieve context from databases. |
| Approach: | They propose to use a pruning method to enhance model-based speculative decoding by combining the best-fit model with the best retrieval tree. |
| Outcome: | The proposed method achieves state-of-the-art inference acceleration across tasks such as DocQA, Summary, Code, and In-Domain QA. |
Ask Again, Then Fail: Large Language Models’ Vacillations in Judgment (2024.acl-long)
Copied to clipboard
| Challenge: | Existing large language models often waver in their judgments when faced with follow-up questions . this is a challenge for generating reliable responses and building user trust . |
| Approach: | They propose a Follow-up Questioning Mechanism and two metrics to quantify this inconsistency . they also develop a framework that teaches large language models to maintain original correct judgments . |
| Outcome: | The proposed framework improves the general capabilities of large language models by allowing them to maintain original correct judgments. |
Length Controlled Generation for Black-box LLMs (2025.acl-long)
Copied to clipboard
Yuxuan Gu, Wenjie Wang, Xiaocheng Feng, Weihong Zhong, Kun Zhu, Lei Huang, Ting Liu, Bing Qin, Tat-Seng Chua
| Challenge: | Existing length control methods involve fine-tuning the parameters of LLMs, which is inefficient and suboptimal for practical use. |
| Approach: | They propose an iterative sampling framework that regulates LLMs to generate length-constrained text without modifying the underlying parameters. |
| Outcome: | The proposed method achieves 100% success rates on Llama3.1 tasks with minimal additional computational overhead. |
HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning (2025.findings-acl)
Copied to clipboard
Xiaoyuan Li, Moxin Li, Rui Men, Yichang Zhang, Keqin Bao, Wenjie Wang, Fuli Feng, Dayiheng Liu, Junyang Lin
| Challenge: | Existing studies show that large language models are robust in commonsense reasoning . however, some variations in questions can lead to incorrect responses . |
| Approach: | They propose a large-scale bilingual benchmark consisting of 11,200 cases . they conduct extensive experiments on 41 representative LLMs . |
| Outcome: | The proposed benchmark systematically evaluates the robustness of large language models in commonsense reasoning. |
MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation (2026.acl-long)
Copied to clipboard
Xiaoyuan Li, Keqin Bao, Yubo Ma, Moxin Li, Wenjie Wang, Rui Men, Yichang Zhang, Fuli Feng, Dayiheng Liu
| Challenge: | Recent advances in Large Language Models (LLMs) have shown promising results in complex reasoning tasks. |
| Approach: | They propose to use a multi-turn reasoning evaluation framework to cover multi-turn interactions with the environments of large language models. |
| Outcome: | The proposed framework covers diverse reasoning capabilities, fine-grained difficulty granularity, and necessitates multi-turn interactions with the environments. |
Dynamic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for predicting sentiment polarity of aspects are susceptible to interference caused by irrelevant contexts and lack sentiment knowledge at a data-specific level. |
| Approach: | They propose a novel Aspect-based sentiment analysis method that leverages attention scores to model the relationships between aspects and contexts. |
| Outcome: | The proposed method is able to predict sentiments from a set of five benchmark datasets. |
Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to multi-turn Text-to-SQL tasks rely on unstable APIs or expensive fine-tuning. |
| Approach: | They propose a training-free framework that leverages small-scale LRMs through in-context learning to enable accurate context-dependent parsing. |
| Outcome: | The proposed framework outperforms in-context learning baselines at the 4B scale and surpasses state-of-the-art models at the 8B and 14B scales. |
Can LLM Graph Reasoning Generalize beyond Pattern Memorization? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies seek to enhance the graph reasoning capabilities of Large Language Models (LLMs) by specialized instruction tuning. |
| Approach: | They propose to evaluate LLM graph reasoning generalization using in-distribution settings . they propose to use three strategies to improve LLM generalization . |
| Outcome: | The proposed benchmark evaluates LLM graph reasoning generalization with in-distribution settings only . it shows that LLMs struggle to generalize across reasoning and real-world patterns . |
FedCSR: A Federated Framework for Multi-Platform Cross-Domain Sequential Recommendation with Dual Contrastive Learning (2025.coling-main)
Copied to clipboard
Dongyi Zheng, Hongyu Zhang, Jianyang Zhai, Lin Zhong, Lingzhi Wang, Jiyuan Feng, Xiangke Liao, Yonghong Tian, Nong Xiao, Qing Liao
| Challenge: | Existing federated frameworks for cross-domain sequential recommendation rely on user alignment, which increases communication costs and privacy risks. |
| Approach: | They propose a federated cross-domain sequential recommendation framework that eliminates the need for user alignment between platforms. |
| Outcome: | The proposed framework eliminates the need for user alignment between platforms. |
LEVEN: A Large-Scale Chinese Legal Event Detection Dataset (2022.findings-acl)
Copied to clipboard
Feng Yao, Chaojun Xiao, Xiaozhi Wang, Zhiyuan Liu, Lei Hou, Cunchao Tu, Juanzi Li, Yun Liu, Weixing Shen, Maosong Sun
| Challenge: | Existing legal event detection datasets only cover incomprehensive event types and have limited annotated data. |
| Approach: | They present a large-scale Chinese legal event detection dataset . they use legal events as side information to promote downstream applications . |
| Outcome: | The proposed method improves 2.2 points precision in low-resource judgment prediction and 1.5 points precision for unsupervised case retrieval. |
RoBGuard: Enhancing LLMs to Assess Risk of Bias in Clinical Trial Documents (2025.coling-main)
Copied to clipboard
Changkai Ji, Bowen Zhao, Zhuoyao Wang, Yingwen Wang, Yuejie Zhang, Ying Cheng, Rui Feng, Xiaobo Zhang
| Challenge: | Existing approaches to assess the risk of bias in RCTs focus on manually crafted prompts and a restricted set of simple questions, limiting their accuracy and generalizability. |
| Approach: | They propose a framework for enhancing Large Language Models to assess the risk of bias in RCTs by reformulation, document parsing and multi-expert collaboration. |
| Outcome: | The proposed framework outperforms existing methods on the RoB-Item and RoB domains. |
UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction (2021.findings-acl)
Copied to clipboard
| Challenge: | Mainstream methods that ignore the diversity among keyphrases or weakly capture the relation between tasks implicitly ignore keyphrase diversity. |
| Approach: | They propose a novel end-to-end learning framework that jointly learns to extract and generate keyphrases by exploiting latent semantic relation between extraction and generation. |
| Outcome: | The proposed approach outperforms mainstream methods on a benchmarked document on keyphrase prediction. |
SSMLoRA: Enhancing Low-Rank Adaptation with State Space Model (2025.naacl-long)
Copied to clipboard
| Challenge: | Fine-tuning requires substantial computational resources and is prone to overfitting when applied to small datasets. |
| Approach: | They propose a parameter-efficient fine-tuning method that integrates a State Space Model (SSM) to interconnect low-rank matrices. |
| Outcome: | The proposed method achieves comparable performance to LoRA on the general language understanding evaluation (GLUE) benchmark while using only half the parameters. |
GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs (2026.findings-acl)
Copied to clipboard
Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, Binbin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong, Jian Wang, Peng Wei, Jinjie Gu
| Challenge: | Existing rankers excel in lexical-matching scenarios, while they struggle with complex queries requiring deep reasoning. |
| Approach: | They propose a new paradigm that balances flexibility and context awareness to unlock the full potential of groupwise reranking. |
| Outcome: | The proposed approach achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED while delivering a 6.4 inference speedup. |
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. |
HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing (2026.findings-acl)
Copied to clipboard
Chengyu Du, Xintao Wang, Aili Chen, Weiyuan Li, Rui Xu, Junteng Liu, Zishan Huang, Rong Tian, Zijun Sun, Yuhao Li, Liheng Feng, Deming Ding, Pengyu Zhao, Yanghua Xiao
| Challenge: | Existing models for LLM role-playing lack high-quality datasets with explicit reasoning traces and reliable reward signals aligned with human preferences. |
| Approach: | They propose a unified framework for cognitive-level persona simulation that strictly distinguishes characters’ first-person thinking processes from LLMs’ third-person reasoning. |
| Outcome: | The proposed framework outperforms the Qwen3-32B baseline model and achieves a 30.26% and 14.97% performance on the minimax benchmarks. |
Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition (2025.acl-long)
Copied to clipboard
Kehua Feng, Keyan Ding, Tan Hongzhi, Kede Ma, Zhihua Wang, Shuangquan Guo, Cheng Yuzhou, Ge Sun, Guozhou Zheng, Qiang Zhang, Huajun Chen
| Challenge: | Existing methods for evaluation of large language models are inefficient and inefficient due to inaccuracy of standard metrics in human perception of text quality and inefficiency in sampling informative test examples. |
| Approach: | They propose a sample-efficient human evaluation method for large language models based on the principle of MAximum Discrepancy (MAD) competition. |
| Outcome: | The proposed method achieves the “golden” ranking of LLMs with a minimum set of input instructions, which in turn reveal their relative strengths and weaknesses. |
ProxyQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models (2024.acl-long)
Copied to clipboard
Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Yunlong Feng, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, Linqi Song
| Challenge: | Existing evaluation methods for large language models are labor-intensive and lack efficiency. |
| Approach: | They propose a framework dedicated to assessing long-text generation that includes in-depth human-curated meta-questions spanning various domains . they use a set of proxy-quests with pre-annotated answers to assess the content's quality by incorporating the generated texts as contextual background. |
| Outcome: | The proposed framework assesses the quality of long-text content by matching it with references through human evaluation or automated metrics. |
DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for reconstruction of large language models overlook diversity among experts, leading to potential redundancy. |
| Approach: | They propose a pruning-based expert reconstruction method that prunes a specific LLM and retrains it on routers, experts and normalization modules. |
| Outcome: | The proposed method outperforms pruning and MoE reconstruction methods on Llama-style models with open-source training corpora. |
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)
Copied to clipboard
Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin
| Challenge: | Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation. |
| Approach: | They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets. |
| Outcome: | The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark. |
Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets (N18-1)
Copied to clipboard
| Challenge: | Experimental results show that the proposed model consistently outperforms the traditional RNNSearch and the newly emerged state-of-the-art Transformer on English-German and Chinese-English translation tasks. |
| Approach: | They propose an approach for applying GANs to NMT by building a conditional sequence generative adversarial net with two adversarials. |
| Outcome: | The proposed model outperforms the existing RNNSearch and Transformer on English-German and Chinese-English translation tasks. |
Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks rely on partially observable traces that capture only agent outputs . lack of full execution traces obscures many failure causes, authors argue . |
| Approach: | They propose a benchmark that allows attribution under full execution observability . they find full traces improve attribution accuracy by up to 76.5% over a partial-observation counterpart . |
| Outcome: | The proposed benchmark improves attribution accuracy by up to 76.5% over a partial-observation counterpart. |
SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs (2025.emnlp-main)
Copied to clipboard
Yuanyang Yin, Yaqi Zhao, Yajie Zhang, Yuanxing Zhang, Ke Lin, Jiahao Wang, Xin Tao, Pengfei Wan, Wentao Zhang, Feng Zhao
| Challenge: | Multimodal Large Language Models (MLLMs) integrate visual and textual inputs, yet modality alignment remains one of the most challenging aspects. |
| Approach: | They propose a token-level supervision alignment method that enables more precise visual-text alignment during pretraining. |
| Outcome: | The proposed method improves performance across various model sizes, with smaller models benefiting the most. |
Improving Autoformalization Using Direct Dependency Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for hallucinate formal dependencies lack scalability and precision to leverage ever-growing public datasets. |
| Approach: | They propose a retrieval-augmented framework based on Direct Dependency Retrieval to generate formal dependencies from natural-language mathematical descriptions and verify their existence via an efficient Suffix Array Check (SAC). |
| Outcome: | The proposed framework outperforms state-of-the-art methods in retrieval precision and recall and can be used to validate formal representations in a public dataset. |
Global-Local Modeling with Prompt-Based Knowledge Enhancement for Emotion Inference in Conversation (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies on emotion recognition focus on recognizing emotions through a speaker’s utterance, while research on emotion inference predicts emotions of addressees through previous utterations. |
| Approach: | They propose a global-local modeling method based on recurrent neural networks and pre-trained language models to do emotion inference in conversation. |
| Outcome: | The proposed method achieves state-of-the-art on three datasets. |
SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models (2026.findings-acl)
Copied to clipboard
Yifu Huo, Chenglong Wang, Ziming Zhu, Shunjie Xing, Peinan Feng, Tongran Liu, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Zhengtao Yu, Tong Xiao
| Challenge: | Reinforcement learning (RL) training typically improves single-sample success rates but limited exploration of diverse reasoning trajectories. |
| Approach: | They propose a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL) they propose 'Steering Probability Squeezing' to enhance exploration without external supervision . |
| Outcome: | The proposed training paradigm improves Pass@k and improves exploration of diverse reasoning trajectories without external supervision. |
Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluations focus on problem-solving from examiner perspective, overlooking a dual perspective of examiner regarding error identification and correction. |
| Approach: | They propose to use an annotated dataset to evaluate large language models from the examiner perspective and to use diverse prompts to evaluate eleven representative LLMs. |
| Outcome: | The proposed model outperforms all models while LLaMA-2-7B has comparable abilities to closed-source models GPT-3.5 and Gemini Pro. |
Token-level Proximal Policy Optimization for Query Generation (2025.emnlp-main)
Copied to clipboard
Yichen Ouyang, Lu Wang, Fangkai Yang, Pu Zhao, Chenghua Huang, Jianfeng Liu, Bochen Pang, Yaming Yang, Yuefeng Zhan, Hao Sun, Qingwei Lin, Saravan Rajmohan, Weiwei Deng, Dongmei Zhang, Feng Sun
| Challenge: | Large Language Models (LLMs) have improved search engines and recommendation systems through their text understanding capabilities. |
| Approach: | They propose a token-level proximal policy optimization approach to empower LLMs to perform better in query generation through fine-tuning. |
| Outcome: | The proposed approach outperforms existing LLMs on an open-source and industrial dataset. |
CMB: A Comprehensive Medical Benchmark in Chinese (2024.naacl-long)
Copied to clipboard
Xidong Wang, Guiming Chen, Song Dingjie, Zhang Zhiyi, Zhihong Chen, Qingying Xiao, Junying Chen, Feng Jiang, Jianquan Li, Xiang Wan, Benyou Wang, Haizhou Li
| Challenge: | Large Language Models (LLMs) provide a great breakthrough in medicine, says a new study . existing studies on LLMs leverage subjective evaluation, but evaluation in medicine is professional . |
| Approach: | They propose a localized medical benchmark in Chinese rooted in native Chinese . they propose to use traditional Chinese medicine to evaluate large-scale LLMs . |
| Outcome: | a new benchmark is developed to evaluate large-scale LLMs in china . the proposed model is rooted in the native Chinese linguistic and cultural framework . |
Towards Non-task-specific Distillation of BERT via Sentence Representation Approximation (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for transferring knowledge from BERT into a model with large parameters are not efficient due to their large-scale and high computational cost. |
| Approach: | They propose a sentence representation approximating oriented distillation framework that can distill pre-trained BERT into a simple LSTM based model without specifying tasks. |
| Outcome: | The proposed model outperforms other distillation methods and larger models on multiple NLP tasks with efficiency well-improved. |
Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)
Copied to clipboard
Yiwei Li, Jiayi Shi, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Ji Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases. |
| Approach: | They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases. |
| Outcome: | The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases. |
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision (2026.acl-long)
Copied to clipboard
Zhen Fang, Ruiyan Han, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, Yi Cao, Feng Zhao
| Challenge: | Unified Multimodal Models have achieved remarkable success in cross-modal comprehension, but a gap persists in their ability to translate internal knowledge into faithful and controllable synthesis. |
| Approach: | They propose a self-improvement framework that partitions a single UMM into three collaborative roles: Proposer, Solver, and Judge. |
| Outcome: | The proposed framework improves on TIIF, DPG, CompBench and UniCycle benchmarks. |
IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters (2026.acl-industry)
Copied to clipboard
Hongwei Zheng, Weiqi Wu, Zhengjia Wang, Guanyu Jiang, Haoming Li, Tianyu Wu, Yongchun Zhu, Jingwu Chen, Feng Zhang
| Challenge: | Existing efforts focus on activation within ongoing dialogues, while overlooking a key real-world bottleneck. |
| Approach: | They propose a conversation starter generation system that generates personalized starters to guide users into conversation without explicit user intent. |
| Outcome: | The proposed system improves user active days by +1.84 and click-through rate by +94.25 and has been deployed in production. |
Do LLMs Know and Understand Domain Conceptual Knowledge? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Concept sememe tree is a hierarchical structure that represents lexical meaning by combining sememes and their relationships. |
| Approach: | They introduce a Neighbor Semantic Structure (NSS) and a Chain-of-Thought prompting method to evaluate the effectiveness of various Large Language Models (LLMs) in generating concept sememe trees. |
| Outcome: | The proposed method guides LLMs through an analysis of a term’s intrinsic core concepts, essential attributes, and semantic relationships, enabling the generation of concept sememe trees. |
CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit (2026.acl-long)
Copied to clipboard
| Challenge: | Diffusion large language models generate text through iterative denoising with bidirectional attention, enabling richer contextual dependencies. |
| Approach: | They propose a training-free parallel decoding method that fuses Trace Credit with current logits to boost the confidence of correct but underconfident tokens. |
| Outcome: | The proposed method achieves 5.48 times speedup with +0.48 accuracy on LLaDA-8B and is orthogonal to mainstream inference optimizations. |
Consistency-Aware Online Multi-Objective Alignment for Related Search Query Generation (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing methods fail to reconcile click-through rate (CTR) optimization with topic expansion. |
| Approach: | They propose a query generation framework that aligns click-through rate and topic expansion goals through an online DPO paradigm. |
| Outcome: | The proposed approach achieves significant CTR gains (+2.3%) and higher human-rated query quality compared to state-of-the-art methods. |
Improving Role-Oriented Dialogue Summarization with Interaction-Aware Contrastive Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for encoding dialogues do not capture interaction information between roles, thus ignore interaction-related key information. |
| Approach: | They propose a contrastive learning based interaction-aware model for the role-oriented dialogue summarization namely CIAM and use it to train the decoder to learn role-level interaction. |
| Outcome: | The proposed model captures interaction information between different roles and produces informative summaries on two public datasets. |
Improving Retrospective Language Agents via Joint Policy Gradient Optimization (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have sparked interest in creating autonomous agents. |
| Approach: | They propose a framework that jointly optimizes both task-planning and self-reflective evolution capabilities in language agents. |
| Outcome: | The proposed framework improves task planning and self-reflective evolution capabilities in language agents. |
Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LLM-based recommenders lack explicit modeling of geographic signals . without explicit modeling geographic signals, recommenders struggle to capture core mobility patterns . |
| Approach: | They propose a framework that utilizes geography as a decision variable within the reasoning process. |
| Outcome: | The proposed framework achieves over 10% relative gains in hit rate over strongest LLM-based baselines and improves cross-city transfer. |
A Simple Recipe towards Reducing Hallucination in Neural Surface Realisation (P19-1)
Copied to clipboard
| Challenge: | Recent neural language generation systems often hallucinate contents when trained on loosely corresponding pairs of the input structure and text. |
| Approach: | They propose to integrate a language understanding module for data refinement with self-training iterations to induce strong equivalence between the input data and the paired text. |
| Outcome: | Experiments on the E2E challenge dataset show that the proposed framework reduces relative unaligned noise by 50% compared with the current state-of-the-art ensemble generator. |
Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to extract aspect triplets ignore the relationships between words . Enhanced Multi-Channel Graph Convolutional Network model can be used to learn relation-aware node representations. |
| Approach: | They propose an Enhanced Multi-Channel Graph Convolutional Network model to fully utilize the relations between words for ASTE task. |
| Outcome: | The proposed model outperforms state-of-the-art methods significantly on a benchmark dataset. |
Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM’s Nest (2025.acl-long)
Copied to clipboard
| Challenge: | Massive high-quality data, both pre-training raw texts and post-training annotations, have been carefully prepared to incubate advanced large language models (LLMs). |
| Approach: | They propose to reframe next-token prediction into extraction for tokens already present in the context of LLMs by reframing next-tongue prediction into IE models. |
| Outcome: | The proposed model learns 102.6M extractive data converted from pre-training and post-training data with better performance than existing pre-trained IE models. |
Text-like Encoding of Collaborative Information in Large Language Models for Recommendation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to adapt Large Language Models for Recommendation (LLMRec) do not represent collaborative information in a text-like format, which may not align optimally with LLMs. |
| Approach: | They propose a novel LLMRec method that integrates collaborative information through text-like encoding. |
| Outcome: | Extensive experiments show that BinLLM integrates collaborative information better with LLMs. |
Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to optimize large language models with human preferences suffer from preference conflicts in the data. |
| Approach: | They propose to construct Pareto-optimal responses to resolve preference conflicts by using a self-improving DPO framework that enables LLMs to self-generate and select Paret-optimized responses. |
| Outcome: | The proposed framework achieves superior Pareto Front performance over baselines on two datasets. |
Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Semi-autoregressive (Semi-AR) decoding suffers from inherent block constraints . naive lookahead decoding is unreliable, token stability closely correlates with convergence trend, and historical information is isolated. |
| Approach: | They propose a training-free, plug-and-play dynamic decoding strategy that monitors the stability of tokens in real time through dynamic anchors. |
| Outcome: | The proposed approach reduces decoding steps by 80% while improving performance by 3.67% on the BBH benchmark. |
When One LLM Drools, Multi-LLM Collaboration Rules (2026.acl-long)
Copied to clipboard
Shangbin Feng, Wenxuan Ding, Alisa Liu, Zifeng Wang, Weijia Shi, Yike Wang, Shannon Zejiang Shen, Xiaochuang Han, Hunter Lang, Chen-Yu Lee, Tomas Pfister, Yejin Choi, Yulia Tsvetkov
| Challenge: | a single general-purpose LLM is not enough to produce a reliable output, argues this paper . a multi-LLM collaboration approach addresses reliability, democratization, and pluralism . |
| Approach: | They argue that a single general-purpose LLM is not enough to produce a reliable output . they organize existing multi-LLM collaboration methods into a hierarchy based on access and information exchange . |
| Outcome: | The proposed method addresses reliability, democratization, and pluralism challenges a single LLM fails to produce a reliable output. |
LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network (2020.acl-main)
Copied to clipboard
Wanjun Zhong, Duyu Tang, Zhangyin Feng, Nan Duan, Ming Zhou, Ming Gong, Linjun Shou, Daxin Jiang, Jiahai Wang, Jian Yin
| Challenge: | Existing methods for fact checking textual statements are not yet available. |
| Approach: | They propose a neural network approach capable of leveraging logical operations for fact checking . they use a textual statement and semi-structured tables to generate a program from it . |
| Outcome: | The proposed approach achieves state-of-the-art performance on TABFACT dataset . it derives a program (a.k.a. logical form) of the statement in semantic parsing manner . |
From Discrimination to Generation: Low-Resource Intent Detection with Language Model Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies fine-tune discriminative models on specific defined intent classes, preventing them from being directly adopted to new intent domains. |
| Approach: | They propose to use a pre-trained generative intent model to detect new intents from different domains with no parameter updates. |
| Outcome: | The proposed model outperforms baselines that need further fine-tuning or domain-specific samples. |
Boosting Event Extraction with Denoised Structure-to-Text Augmentation (2023.findings-acl)
Copied to clipboard
Bo Wang, Heyan Huang, Xiaochi Wei, Ge Shi, Xiao Liu, Chong Feng, Tong Zhou, Shuaiqiang Wang, Dawei Yin
| Challenge: | Existing methods for event extraction neglect grammatical incorrectness, structure misalignment, and semantic drifting . et al., 2004; Ahn, 2006) show that the proposed method generates more diverse text representations for event extracting compared with the state-of-the-art. |
| Approach: | They propose a framework for event extraction that generates additional training data and iteratively selects the effective subset from the generated training data. |
| Outcome: | The proposed method generates more diverse representations of training data and achieves comparable results with the state-of-the-art. |
Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning (2024.findings-acl)
Copied to clipboard
Zhiyang Xu, Chao Feng, Rulin Shao, Trevor Ashby, Ying Shen, Di Jin, Yu Cheng, Qifan Wang, Lifu Huang
| Challenge: | Recent vision-language models (VLMs) have shown impressive capabilities as general visual assistants, but there are two challenges to their performance: (1) lacking task diversity in pretraining and visual instruction tuning; (2) annotation error and bias in GPT-4 synthesized instruction tuning data. |
| Approach: | They propose a two-stage instruction tuning framework that fine tunes VLMs firstly and further tuned on GPT-4 synthesized data. |
| Outcome: | The proposed framework outperforms the traditional single-stage visual instruction tuning framework and achieves state-of-the-art performance across a wide range of multi-modal evaluation benchmarks. |
Improving Factual Consistency of Abstractive Summarization via Question Answering (2021.acl-long)
Copied to clipboard
Feng Nan, Cicero Nogueira dos Santos, Henghui Zhu, Patrick Ng, Kathleen McKeown, Ramesh Nallapati, Dejiao Zhang, Zhiguo Wang, Andrew O. Arnold, Bing Xiang
| Challenge: | Recent studies show that about 30% of summaries generated by neural text summarization suffer from fact fabrication. |
| Approach: | They propose an automatic evaluation metric to measure factual consistency and a learning algorithm that maximizes the metric during model training. |
| Outcome: | The proposed method improves factual consistency and overall quality of summarization models. |
Semi-Supervised Disfluency Detection (C18-1)
Copied to clipboard
| Challenge: | Detecting disfluency can be difficult because of the flexible nature of reparandum structure and the lack of a nested structure. |
| Approach: | They propose a semi-supervised approach which extracts hidden features from self-attention without any Recurrent Neural Network (RNN) or Convolutional Neural Net (CNN). |
| Outcome: | The proposed approach improves over baselines by using unlabelled data . identifying and removing non-fluent factors would help to improve spontaneous speech quality . |
Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to finding effective predictive signals from financial data are limited by their complexity and low signal-to-noise ratio. |
| Approach: | They propose a framework that combines code-level alpha representation with LLM-driven reasoning and evolutionary search. |
| Outcome: | The proposed framework combines code-level alpha representation with LLM-driven reasoning and evolutionary search. |
Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart (2026.findings-acl)
Copied to clipboard
null Chenkang, Fan Yu, Junjie Nian, Sihan Zhao, Zhuoka Feng, Zijun Yao, Wang Heng, Yu Minshen, Yixin Cao
| Challenge: | Experiments show that extended generation does not guarantee correctness . a recurring pattern in Long-CoT failures is a problem for large reasoning models . |
| Approach: | They propose a test-time control framework that truncates the trajectory before the trap segment and adaptively restarts decoding. |
| Outcome: | Experiments show that TAAR improves reasoning performance without fine-tuning model parameters. |
Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing automatic question generation methods focus on encoding passage and answer to generate question. |
| Approach: | They propose an automatic question generation approach which integrates question generation with its dual problem, question answering, into a unified primal-dual framework. |
| Outcome: | The proposed approach outperforms existing methods on SQuAD and HotpotQA benchmarks. |
Customizing In-context Learning for Dynamic Interest Adaption in LLM-based Recommendation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing Large Language Model (LLM)-based recommender systems face challenges to adapt to dynamic user interests without any model-level updates. |
| Approach: | They propose a framework that establishes recommendation-oriented in-context learning by structuring recent user interactions and current inputs into ICL formats. |
| Outcome: | The proposed model adapts to dynamic user interests without model updates without any model updates and is available online at https://anonymous.4open.science/r/RecICL-8003. |
Robust Prompt Optimization for Large Language Models Against Distribution Shifts (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing research has explored automatic prompt optimization methods to eliminate manual effort in identifying effective prompts for a given task. |
| Approach: | They propose a framework for prompt optimization that can be generalized to an unlabeled target group. |
| Outcome: | The proposed framework improves on target group and source group while generalizing to unlabeled target group. |
Generalized Category Discovery with Large Language Models in the Loop (2024.findings-acl)
Copied to clipboard
Wenbin An, Wenkai Shi, Feng Tian, Haonan Lin, QianYing Wang, Yaqiang Wu, Mingxiang Cai, Luyan Wang, Yan Chen, Haiping Zhu, Ping Chen
| Challenge: | Generalized Category Discovery (GCD) is a crucial task that aims to recognize both known and novel categories from a set of unlabeled data. |
| Approach: | They propose a framework that introduces Large Language Models into the training loop to generate category names without human effort. |
| Outcome: | The proposed framework outperforms SOTA models on three benchmark datasets and generates accurate category names for the discovered clusters. |
Mixup Decoding for Diverse Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating multiple translations for source and target languages neglect the one-to-many mapping between the source and the target languages. |
| Approach: | They propose a method to generate different translations for the input sentence by linearly interpolating it with different sentence pairs sampled from the training corpus during decoding. |
| Outcome: | Experiments on WMT’16 en-ro, WMT'14 en de, and WMT ‘17 zh-en show that the proposed method outperforms all previous diverse machine translation methods. |
GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labeling (2025.findings-acl)
Copied to clipboard
Hao Fang, Yuejie Zhang, Rui Feng, Yingwen Wang, Qing Wang, Wen He, Xiaobo Zhang, Tao Zhang, Shang Gao
| Challenge: | Document-level relation extraction (DocRE) solves problems of document quality . number of entities and entity-pair relations increases, causing incomplete annotations . |
| Approach: | a framework that reduces the problem space using a graph-enhanced Transformer-based model is proposed . GLiM leverages large language models for reasoning to reduce the problem-space . |
| Outcome: | GLiM boosts average recall and F1 scores on biomedical datasets . compared with existing models, GLim outperforms existing models on biomedicine benchmarks compared to existing models . |
SWING: Balancing Coverage and Faithfulness for Dialogue Summarization (2023.findings-eacl)
Copied to clipboard
Kung-Hsiang Huang, Siffi Singh, Xiaofei Ma, Wei Xiao, Feng Nan, Nicholas Dingwall, William Yang Wang, Kathleen McKeown
| Challenge: | Existing approaches to dialogue summarization rely on features of conversation data. |
| Approach: | They propose to use natural language inference models to improve coverage and faithfulness . they use fine-grained training signals to encourage model to generate missing content . |
| Outcome: | The proposed model achieves higher faithfulness and coverage while maintaining conciseness compared to prior methods. |
Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have produced significant advances in the field of recommender systems. |
| Approach: | They propose to retrieve up-to-date structure information from the knowledge graph to augment recommendations by leveraging external knowledge sources. |
| Outcome: | Experiments on a large dataset show that the proposed method is effective in enhancing LLM-based recommendations. |
Look Within or Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Parameter-Efficient Fine-Tuning (PEFT) is an alternative to Full-Parameter Fine-tuning, but its effectiveness on complex tasks such as reasoning and instruction-following remains unclear. |
| Approach: | They propose to use PEFT to reduce the number of trainable parameters while freezing the weights of LLMs. |
| Outcome: | The proposed methods perform well on standard tasks, but weaknesses on complex and adversarial settings call for new directions beyond current paradigms. |
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs (2026.findings-acl)
Copied to clipboard
Zijing Wang, YongKang Liu, Mingyang Wang, Ercong Nie, Deyuan Chen, Zhengjie Zhao, Shi Feng, Daling Wang, Xiaocui Yang, Yifei Zhang, Hinrich Schuetze
| Challenge: | Multimodal instruction fine-tuning degrades textual reasoning capability, undermining multimodal performance. |
| Approach: | They propose a plateau-guided model merging method that selectively injects base language model parameters into MLLMs to mitigate this degradation. |
| Outcome: | The proposed framework reduces multimodal instruction fine-tuning degradation by incorporating a plateau-guided model merging method into MLLMs. |
PAR: Political Actor Representation Learning with Social Context and Expert Knowledge (2022.emnlp-main)
Copied to clipboard
Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Ningnan Wang, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo
| Challenge: | Existing approaches focus on textual data and voting records to induce political actors' stances. |
| Approach: | They propose a Political Actor Representation learning framework that leverages social context and expert knowledge to model ideological stances. |
| Outcome: | The proposed framework improves political text understanding and improves roll call vote prediction and political perspective detection. |
Teaching LLMs to Abstain across Languages via Multilingual Feedback (2024.emnlp-main)
Copied to clipboard
Shangbin Feng, Weijia Shi, Yike Wang, Wenxuan Ding, Orevaoghene Ahia, Shuyue Stella Li, Vidhisha Balachandran, Sunayana Sitaram, Yulia Tsvetkov
| Challenge: | Existing studies on LLM abstention focus on English, but they show that it can reduce the accuracy of the model by 20.5% . |
| Approach: | They propose to teach LLMs to abstain in the face of knowledge gaps by generating multiple feedback items in related languages. |
| Outcome: | Extensive experiments show that the proposed approach outperforms baselines and achieves 9.2% improvement for low-resource languages. |
Answer-guided and Semantic Coherent Question Generation in Open-domain Conversation (D19-1)
Copied to clipboard
| Challenge: | Existing methods for question generation suffer from dullness and deviation problem, which can lead to deviated or dull questions. |
| Approach: | They propose two methods to enhance semantic coherence between question and answer by using a coherent score and adversarial training to explicitly control question generation. |
| Outcome: | The proposed methods outperform state-of-the-art baseline algorithms with large margins in raising semantic coherent questions. |
CIRAG: Construction–Integration Retrieval and Adaptive Generation for Multi-hop Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for iterative retrieval-augmented generation (iRAG) suffer from greedy single-path expansion and granularity–demand mismatch . |
| Approach: | They propose a model that constructs candidate triples and history-conditionally integrates them to distill core triples to generate the next-hop query. |
| Outcome: | The proposed model mitigates the greedy single-path expansion and granularity–demand mismatch by preserving multiple plausible evidence chains. |
Counterfactual Active Learning for Out-of-Distribution Generalization (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies on active learning methods focus on the out-of-distribution generalization of out- of-distortion samples. |
| Approach: | They propose a counterfactual active learning approach that empowers active learning with counterfact thinking to bridge the seen samples with unseen cases. |
| Outcome: | The proposed approach outperforms existing active learning methods on public datasets with comparable IID performance. |
A Diffusion Weighted Graph Framework for New Intent Discovery (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to learn from unlabeled data generate noisy supervisory signals . current methods only rely on semantic similarities to generate supervisory signal . |
| Approach: | They propose a weighted DWGF framework to capture semantic similarities and structure relationships in data. |
| Outcome: | The proposed method outperforms state-of-the-art models on evaluation metrics across multiple benchmark datasets. |
A Hybrid Model of Classification and Generation for Spatial Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies only focus on spatial relations extraction as a classification task . spatial information is one kind of critical information for natural language understanding . |
| Approach: | They propose a hybrid model that generates null-role relations and extracts non-null-rol . they propose varying kinds of schemes to represent spatial relation . |
| Outcome: | The proposed model outperforms the baselines on the spatial relation extraction task on SpaceEval. |
A Simple Model for Distantly Supervised Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Recent methods focus on exploiting bag representations with complex de-noising scheme to achieve remarkable performance. |
| Approach: | They propose a BERT-based Graph convolutional network model that exploits bag representations . their model extracts key information from each instance and constructs a bag graph . |
| Outcome: | The proposed model improves on two benchmark datasets, i.e., NYT10 and GDS. |
ContraCLM: Contrastive Learning For Causal Language Model (2023.acl-long)
Copied to clipboard
Nihal Jain, Dejiao Zhang, Wasi Uddin Ahmad, Zijian Wang, Feng Nan, Xiaopeng Li, Ming Tan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Bing Xiang
| Challenge: | Existing studies show that causal language models lack expressiveness due to poor discrimination ability. |
| Approach: | They propose a contrastive learning framework that enhances discrimination of representations and bridges the gap with encoder-only models. |
| Outcome: | The proposed framework improves discrimination and source code generation capabilities on a variety of downstream tasks. |
Cascaded Mutual Modulation for Visual Reasoning (D18-1)
Copied to clipboard
| Challenge: | Visual reasoning is a multi-step and compositional problem that requires intensive text-vision interactions. |
| Approach: | They propose a visual reasoning model that uses a feature-wise linear modulation technique to enable textual/visual pipelines to mutually control each other. |
| Outcome: | The proposed model outperforms existing models on visual reasoning benchmarks CLEVR and NLVR . it can generate a textual answer to a visual question answering problem with images . |
Advancing Sequential Numerical Prediction in Autoregressive Models (2025.acl-short)
Copied to clipboard
| Challenge: | Autoregressive models are the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences. |
| Approach: | They propose a novel approach to entropy loss by extending the Earth Mover’s Distance to preserve ordinal relationships between numerical values and sequence-level to penalize the overall discrepancy between predicted and actual sequences. |
| Outcome: | Extensive experiments show that NTIL improves numerical prediction and integrates effectively with LLMs/MLLMs. |
Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to self-detection only retrospectively evaluate LLM-generated answers, leading to over-trust in incorrectly generated answers. |
| Approach: | They propose a self-detection paradigm that considers the comprehensive answer space beyond LLM-generated answers to mitigate the over-trust in LLM generated incorrect answers. |
| Outcome: | The proposed framework can be integrated with existing approaches for superior self-detection. |
LLaMA-Rider: Spurring Large Language Models to Explore the Open World (2024.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have used Large Language Models to help decision-making and planning in environments, but their capacity to acquire environmental knowledge and adapt in an open world remains uncertain. |
| Approach: | They propose an approach to spur LLMs to explore the open world, gather experiences, and learn to improve their task-solving capabilities by using a feedback-revision mechanism. |
| Outcome: | The proposed model enhances the efficiency of the LLM in exploring the open world and improves its ability to accomplish more tasks through fine-tuning with merely 1.3k instances of collected data, showing minimal training costs compared to baseline using reinforcement learning. |
CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation (2024.acl-long)
Copied to clipboard
Pei Ke, Bosi Wen, Andrew Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang
| Challenge: | Existing models for NLP evaluations lack the ability to generate informative critiques in pointwise grading and pairwise comparison especially without references. |
| Approach: | They propose a method which can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings. |
| Outcome: | The proposed method outperforms all open-source models and even GPT-4 in system-level correlations of pointwise grading. |
EAVE: Efficient Product Attribute Value Extraction via Lightweight Sparse-layer Interaction (2024.findings-emnlp)
Copied to clipboard
Li Yang, Qifan Wang, Jianfeng Chi, Jiahao Liu, Jingang Wang, Fuli Feng, Zenglin Xu, Yi Fang, Lifu Huang, Dongfang Liu
| Challenge: | Existing methods to extract product attribute value require multiple extractions to obtain all corresponding values. |
| Approach: | They propose an Efficient product Attribute Value Extraction approach using lightweight sparse-layer interaction. |
| Outcome: | The proposed method achieves significant efficiency gains with neutral or marginal loss in performance when the context is long and number of attributes is large. |
Language-agnostic BERT Sentence Embedding (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning bilingual sentence embeddings are not well explored. |
| Approach: | They propose to combine best methods for learning multilingual sentence embeddings with pre-trained models to achieve 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba. |
| Outcome: | The proposed model achieves 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba, above the 65.5% achieved by LASER. |
SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to detect and correct spelling errors in Chinese take external input or just heuristic rules. |
| Approach: | They propose to incorporate phonological and visual similarity knowledge into Chinese language models by using a specialized graph convolutional network. |
| Outcome: | The proposed method outperforms existing models on three human-annotated datasets. |
From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen (2025.acl-long)
Copied to clipboard
Peiwen Yuan, Chuyi Tan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Existing methods to control text length are lacking in LCTG, posing a major limitation for practical applications. |
| Approach: | They propose a plug-and-play approach that decomposes LCTG sub-abilities with human patterns as reference and performs detailed error analysis. |
| Outcome: | The proposed method significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability. |
Language Models as Continuous Self-Evolving Data Engineers (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their further evolution is often hampered by the scarcity of high-quality training data and the heavy reliance of traditional methods on expert-labeled data. |
| Approach: | They propose a paradigm that enables LLMs to train themselves by generating, cleaning, reviewing and annotating data with preference information. |
| Outcome: | The proposed model can generate, clean, review, and annotate data with preference information significantly reducing time and cost of post-training data construction. |
NEAT: Neuron-Based Early Exit for Large Reasoning Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to reduce overthinking require additional rollout computation or externally labeled datasets. |
| Approach: | They propose a Neuron-based Early reAsoning exiT framework that monitors neuron-level activation dynamics to enable training-free early exits. |
| Outcome: | The proposed framework reduces the amount of reasoning steps generated by LRMs while maintaining accuracy. |
HoWToBench: Holistic Evaluation for LLM’s Capability in Human-level Writing using Tree of Writing (2026.acl-long)
Copied to clipboard
Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo, Lin Fan, Irene Zhou, Zikang Wang, Xiaotao Gu, Jie Tang, Hongning Wang, Minlie Huang
| Challenge: | Evaluating the writing capabilities of large language models remains a significant challenge due to the multidimensional nature of writing skills and the limitations of existing metrics. |
| Approach: | They propose to model the aggregation weights of sub-features in a tree-structured workflow and propose a Chinese writing benchmark that mitigates biases. |
| Outcome: | The proposed tree-of-writing (ToW) measures the writing capabilities of large language models (LLMs) in Chinese and shows that it mitigates biases and achieves a *0.93* Pearson correlation with human judgments. |
CoAug: Combining Augmentation of Labels and Labelling Rules (2023.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) tasks require large labeled datasets to perform well. |
| Approach: | They propose a co-augmentation framework that bootstraps predictions from each model to improve few-shot models and rule-augmentation models by bootstrapping them. |
| Outcome: | The proposed model outperforms strong weak-supervision-based models by 6.5 F1 points . the proposed model can learn from limited labeled data and perform better on small datasets . |
Mixed Distillation Helps Smaller Language Models Reason Better (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have demonstrated impressive multiple step-by-step reasoning capabilities in recent NLP reasoning tasks. |
| Approach: | They propose a mixed distillation framework that distills multiple step-by-step reasoning abilities into smaller language models (SLMs) they leverage LLMs to generate multiple step by step reasoning rationales by sampling automatically. |
| Outcome: | The proposed framework outperforms existing models on SVAMP, GSM8K and ASDIV, while a single model generated by MD exceeds the comprehensive performance of two individual CoT and PoT distilled models. |
AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models (2026.findings-acl)
Copied to clipboard
Feng Luo, Yu-Neng Chuang, Guanchu Wang, Hoang Anh Duy Le, Shaochen Zhong, Hongyi Liu, Jiayi Yuan, Yang Sui, Vladimir Braverman, Vipin Chaudhary, Xia Hu
| Challenge: | Existing approaches to distilling large language models (LLMs) are inefficient and generate excessively long chain-of-thought reasoning even for inputs that admit concise solutions. |
| Approach: | They propose a distillation framework that empowers non-reasoning LLMs to think only when necessary. |
| Outcome: | The proposed framework reduces reasoning length up to 71% with minimal accuracy loss while preserving accuracy. |
Jointly Learning Entity and Relation Representations for Entity Alignment (D19-1)
Copied to clipboard
| Challenge: | Entity alignment is a viable method for integrating heterogeneous knowledge among different knowledge graphs (KGs). |
| Approach: | They propose a Graph Convolutional Network-based framework for learning relation representations by embedding relation seeds into entities and incorporating relation approximation into entities to iteratively improve alignment. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on three real-world cross-lingual datasets. |
Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing research has focused on enhancing graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data. |
| Approach: | They propose to unlock generalizable learning of graph with post-training alignment with synthetic graph data by aligning off-the-shelf LLMs and LLM fine-tuned on synthetic graphs. |
| Outcome: | The proposed algorithm improves on synthetic graph problems and out-of-domain tasks with implicit graph structures. |
Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)
Copied to clipboard
Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li
| Challenge: | Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples. |
| Approach: | They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes. |
| Outcome: | The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance. |
PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism (2023.acl-long)
Copied to clipboard
| Challenge: | Existing generative models for dialogue use the last hidden state to summarize the history of the dialogue. |
| Approach: | They propose a Pseudo-Variational Gated Recurrent Unit (PVGRU) that summarises the accumulated distribution variations of subsequences and builds a model based on it. |
| Outcome: | The proposed model can improve diversity and relevance of responses on two benchmark datasets. |
Exploring Logographic Image for Chinese Aspect-based Sentiment Classification (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for aspect-based sentiment classification have focused on English text, but Chinese is a language derived from pictographs and different from other phonetic languages. |
| Approach: | They propose to use a logographic image to capture internal morphological structure from character sequence . they propose to explicitly incorporate a symbolic image with review text for sentiment classification . |
| Outcome: | The proposed method improves over baselines and improves on existing methods. |
GeoEdit: Geometric Knowledge Editing for Large Language Models (2025.emnlp-main)
Copied to clipboard
Yujie Feng, Li-Ming Zhan, Zexin Lu, Yongxin Xu, Xu Chu, Yasha Wang, Jiannong Cao, Philip S. Yu, Xiao-Ming Wu
| Challenge: | Existing training-based model editing methods struggle to incorporate new knowledge while preserving unrelated general knowledge. |
| Approach: | They propose a framework that uses geometric relationships to differentiate between neurons associated with new knowledge updates and those related to general knowledge perturbations. |
| Outcome: | The proposed framework avoids updating neurons with directions approximately orthogonal to existing knowledge, thus preserving the model’s generalization ability. |
Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies assessing the spatial abilities of VLMs lack a solid theoretical foundation and lack measurable data. |
| Approach: | They propose a psychometric framework defining five basic spatial abilities in Visual Language Models. |
| Outcome: | The proposed framework defines five basic spatial abilities in Visual Language Models (VLMs) it provides a comprehensive evaluation benchmark and methodological perspective for embodied AI development . |
Clear Up Confusion: Iterative Differential Generation for Fine-grained Intent Detection with Contrastive Feedback (2025.coling-main)
Copied to clipboard
| Challenge: | Recent studies on fine-grained intent detection have focused on collecting large-scale and high-quality samples via crowdsourcing resulting in data scarcity. |
| Approach: | They propose an iterative differential generation framework with contrastive feedback to generate high-quality pseudo samples and accurately capture the crucial nuances in target class distribution. |
| Outcome: | The proposed framework generates high-quality pseudo samples and captures crucial nuances in target class distribution. |
Tunable LLM-based Proactive Recommendation Agent (2025.acl-long)
Copied to clipboard
| Challenge: | Current methods focus on catering to existing user interests, leading to polarized recommendation distributions. |
| Approach: | They propose an LLM-based Actor-Critic Agent framework to cultivate latent interests through multi-step recommendations. |
| Outcome: | The proposed framework optimizes long-term rewards and dynamically evolves with user feedback. |
PuzzleGPT: Emulating Human Puzzle-Solving Ability for Time and Location Prediction (2025.findings-naacl)
Copied to clipboard
| Challenge: | PuzzleGPT is a modular and iterative puzzlesolving method for predicting time and location from images. |
| Approach: | They propose to formalize this ability into core skills and implement it using different modules in an expert pipeline called PuzzleGPT. |
| Outcome: | The proposed method outperforms large VLMs and finetuned models on TARA and WikiTilo and rivals or surpasses finetuned models. |
STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to learn speech representations for end-to-end speech-totext translation (ST) neglect the representation discrepancy across modalities. |
| Approach: | They propose a method to calibrate the representation discrepancy between modalities by mixing up the representation sequences of different modality inputs. |
| Outcome: | The proposed method alleviates the cross-modal representation discrepancy and improves on a strong baseline on eight translation directions. |
Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on prompt engineering or framework scheduling of one/multiple LLMs. |
| Approach: | They propose to integrate LLMs as agents into their training corpus by decomposition and redesigning the training corpu . they propose to use LLM-FLAN to effectively fine-tune LANguage models for Agents by reducing hallucinations. |
| Outcome: | The proposed model outperforms prior best models by 3.5% across agent evaluation datasets. |
Wait, We Don’t Need to “Wait”! Removing Thinking Tokens Improves Reasoning Efficiency (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in large reasoning models often introduce significant overthinking . this leads to verbose and redundant outputs that hinder efficiency. |
| Approach: | They propose a plug-and-play solution that disables explicit self-reflection . it suppresses tokens such as "Wait" and "Hmm" during inference . |
| Outcome: | The proposed approach reduces chain-of-thought trajectory length by up to 27%–51% in five R1-style model series without compromising model utility. |
xLAM: A Family of Large Action Models to Empower AI Agent Systems (2025.naacl-long)
Copied to clipboard
Jianguo Zhang, Tian Lan, Ming Zhu, Zuxin Liu, Thai Quoc Hoang, Shirley Kokane, Weiran Yao, Juntao Tan, Akshara Prabhakar, Haolin Chen, Zhiwei Liu, Yihao Feng, Tulika Manoj Awalgaonkar, Rithesh R N, Zeyuan Chen, Ran Xu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
| Challenge: | Autonomous agents powered by large language models (LLMs) have attracted significant research interest, but there are few standards for developing specialized models for agent tasks. |
| Approach: | They propose a series of large action models with dense and mixture-of-expert architectures that unifies, augments, and synthesizes diverse datasets to enhance agent generalizability and performance. |
| Outcome: | The proposed models outperform GPT-4, Claude-3, and many other models in terms of tool use and outperformed GPT-based models on multiple agent ability benchmarks. |
Lock on Target! Precision Unlearning via Directional Control (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for unlearning harmful, sensitive, or outdated knowledge suffer from two critical limitations: (1) collateral forgetting, where erasing target data inadvertently removes related but desirable knowledge, and (2) generality forgetting degrades the model’s general capabilities. |
| Approach: | They propose a method that identifies and leverages a targeted "unlearning direction" in the model's parameter space and selectively updates along this direction. |
| Outcome: | Experiments show that the proposed method achieves state-of-the-art unlearning precision while preserving both related knowledge and general capabilities. |
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Reasoning Models (LRMs) introduce a new paradigm of explicitly reasoning before answering, but they pose great safety risks against harmful queries and adversarial attacks. |
| Approach: | They propose a safety aha moment that activates safety reasoning and leads to a safe response. |
| Outcome: | The proposed model can generalize to unseen jailbreak prompts while maintaining general abilities. |
MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings (2026.acl-long)
Copied to clipboard
| Challenge: | Multi-turn, long-horizon tasks require dozens of sequential model calls per episode. |
| Approach: | They propose a cost-aware multi-turn LLM routing tool which encodes interaction history and candidate models into joint history–model embeddings and learns an outcome estimator from logged trajectories to predict turn-level model utility. |
| Outcome: | The proposed model reduces cost and performance by 58.7% on ScienceWorld and on Humanity’s Last Exam (HLE) and even reduces costs for held-out tasks. |
SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning (2026.acl-long)
Copied to clipboard
Peidong Wang, Zhiming Ma, Xin Dai, YongKang Liu, Shi Feng, Xiaocui Yang, Wenxing Hu, Zhihao Wang, Mingjun Pan, Li Yuan, Daling Wang
| Challenge: | Existing methods for fraud detection rely on transcribed text, lacking acoustic cues . a proposed framework for audio-based slow-thinking fraud detection eliminates transcription errors . |
| Approach: | They propose a framework for audio-based slow-thinking fraud detection that eliminates transcription errors and rewards slow-thought reasoning by capturing fine-grained audio details. |
| Outcome: | The proposed method improves accuracy, inference efficiency, and real-time processing capabilities. |
Let’s Negotiate! A Survey of Negotiation Dialogue Systems (2024.findings-eacl)
Copied to clipboard
Haolan Zhan, Yufei Wang, Zhuang Li, Tao Feng, Yuncheng Hua, Suraj Sharma, Lizhen Qu, Zhaleh Semnani Azad, Ingrid Zukerman, Reza Haf
| Challenge: | Recent research has focused on negotiation dialogue systems, but no systematic review of this task has been conducted. |
| Approach: | They propose to provide a systematic review of negotiation dialogue systems and to provide an overview of current research. |
| Outcome: | The proposed systems are based on the literature and are compared against existing systems. |
A Survey on Natural Language Counterfactual Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in NLP are driven by a variety of Large Language Models (LLMs), such as GPT-3 (175B) and PaLM (540B). |
| Approach: | They propose a taxonomy that categorizes the methods into four groups and summarizes the metrics for evaluating the generation quality. |
| Outcome: | The proposed taxonomy categorizes the generation methods into four groups and summarizes the metrics for evaluating the quality. |
Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for converting visual tokens into tokens are limited by their high volume . et al., 2023; Zheng e.t., 2023): a revolution in video understanding. |
| Approach: | They propose a language-aware dynamic token compression system that converts video clips into soft caption tokens as visual representations. |
| Outcome: | The proposed method reduces FLOPs by 49% while maintaining competitive performance. |
Towards Reverse Engineering of Language Models: A Survey (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Due to the vast amounts of data and computational resources required for model development, protecting the model’s parameters and training data has become an urgent and crucial concern. |
| Approach: | They define "reverse engineering" techniques as attacks on large language models and provide an in-depth analysis of them. |
| Outcome: | The proposed attacks are described as “reverse engineering” techniques on LMs and provide an introduction to existing protective strategies. |
My Words Imply Your Opinion: Reader Agent-Based Propagation Enhancement for Personalized Implicit Emotion Analysis (2025.acl-long)
Copied to clipboard
| Challenge: | Current studies personalize emotion analysis by focusing on the author but neglect the impact of the intended reader on implicit emotional feedback. |
| Approach: | They propose a model which incorporates reader feedback into implicit emotion analysis (IEA) they use large language models to create reader agents to simulate reader feedback . |
| Outcome: | The proposed model outperforms state-of-the-art models in a text-centric environment. |
AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning (2025.emnlp-main)
Copied to clipboard
Yujie Feng, Jian Li, Xiaoyu Dong, Pengfei Xu, Xiaohui Zhou, Yujia Zhang, Zexin Lu, Yasha Wang, Alan Zhao, Xu Chu, Xiao-Ming Wu
| Challenge: | Recent model merging-based methods struggle to effectively manage the trade-off between learning new knowledge and preventing catastrophic forgetting. |
| Approach: | They propose a model merging framework that utilizes learning and forgetting signals from the training trajectory to dynamically monitor the model’s training status. |
| Outcome: | The proposed framework achieves significant performance improvements over existing state-of-the-art methods on three CL benchmarks with various model sizes (from 770M to 13B). |
MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generation (2025.acl-industry)
Copied to clipboard
Hsin-Ling Hsu, Cong-Tinh Dao, Luning Wang, Zitao Shuai, Thao Nguyen Minh Phan, Jun-En Ding, Chun-Chieh Liao, Pengfei Hu, Xiaoxue Han, Chih-Ho Hsu, Dongsheng Luo, Wen-Chih Peng, Feng Liu, Fang-Ming Hung, Chenwei Wu
| Challenge: | Existing systems focus primarily on assessment rather than treatment planning. |
| Approach: | They propose a framework that structures LLM reasoning to align with real-life workflows. |
| Outcome: | The proposed framework outperforms baseline approaches in assessment accuracy and treatment plan quality. |
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following (2026.acl-long)
Copied to clipboard
Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Kumar Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Hassan Awadalla, Manaal Faruqui
| Challenge: | Recent advances in large language models (LLMs) have shown impressive performance on a range of tasks, yet advanced instruction following (IF) remains a significant challenge. |
| Approach: | They propose a benchmark that features over 1,600 prompts and expert-curated rubrics that assess LLMs’ ability to follow complex, multi-turn, and system-level instructions. |
| Outcome: | The proposed framework improves instruction-following abilities of large language models, achieving a 6.7% gain on AdvancedIF and strong results on public benchmarks. |
Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning (2025.emnlp-industry)
Copied to clipboard
Ruizhe Chen, Tianze Luo, Zhiting Fan, Heqing Zou, Zhaopeng Feng, Guiyang Xie, Hansheng Zhang, Zhuochen Wang, Zuozhu Liu, Zhang Huaijian
| Challenge: | Existing methods for video temporal grounding suffer from limited temporal awareness and poor generalization. |
| Approach: | They propose a two-stage training framework that integrates supervised fine-tuning with reinforcement learning to improve both the accuracy and robustness of VTG models. |
| Outcome: | The proposed training framework outperforms existing models on multiple benchmarks on open-domain and challenging scenarios. |
RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training (2023.findings-emnlp)
Copied to clipboard
Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, Madian Khabsa
| Challenge: | Several perspectives of robustness for pre-trained language models have been studied independently, but lacking a unified consideration in multiple perspectives. |
| Approach: | They propose a technique to enhance the multi-perspective robustness of LMs by introducing adversarial perturbation while the model parameters are selectively updated upon their relative importance. |
| Outcome: | The proposed technique improves the robustness of LMs by incorporating four perspectives on model robustness. |
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. |
QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for processing large textual content face insufficient adaptation to task-specific needs and missing multi-segmentation relationships. |
| Approach: | They propose a question then reflection memory mechanism which integrates a dual-structured memory pool and a structured graph guidance to facilitate a reflective trial-and-error approach for navigating and identifying relevant segments. |
| Outcome: | The proposed model achieves superior performance on multiple-choice questions and multi-doc QA. |
Cat-MoD: Accelerating Multimodal Alignment via Caption Token Guided Asymmetric Mixture-of-Depths (2026.acl-long)
Copied to clipboard
| Challenge: | Existing query-based alignment modules enforce uniform cross-attention across all layers, leading to computational redundancy. |
| Approach: | They propose a framework that allows for asynchronous query-based alignment with large-scale visual features. |
| Outcome: | The proposed framework matches or surpasses baseline performance while reducing alignment FLOPs by approximately 37% during training and inference. |
STRUDEL: Structured Dialogue Summarization for Dialogue Comprehension (2022.emnlp-main)
Copied to clipboard
Borui Wang, Chengcheng Feng, Arjun Nair, Madelyn Mao, Jai Desai, Asli Celikyilmaz, Haoran Li, Yashar Mehdad, Dragomir Radev
| Challenge: | Abstractive dialogue summarization is an important standalone task in natural language processing, but no previous work has explored whether it can be used to boost an NLP system's performance on other important dialogue comprehension tasks. |
| Approach: | They propose a novel type of dialogue summarization task that decomposes and imitates the hierarchical, systematic and structured mental process that human beings usually go through when understanding and analyzing dialogues. |
| Outcome: | The proposed model improves the performance of transformer encoder language models on two important dialogue comprehension tasks. |
Investigating Human and LLMs’ Decisions in Unverifiable Environments: A Case Study with GitHub Activity Overview (2026.findings-acl)
Copied to clipboard
| Challenge: | examining the behaviors of Large Language Models as artificial social actors is underexplored, especially in unverifiable scenarios where conventional benchmarking has little to help improve their abilities. |
| Approach: | They propose a method to collect, compare, and reason about human and LLMs' decisions in an unverifiable scenario and use it to examine their behaviors. |
| Outcome: | The proposed method compared human and LLM decisions in an unverifiable scenario on GitHub and found that proprietary LLMs behave more like humans than open-source LLM systems. |
SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models incur high inference costs during deployment, causing hallucination . no dedicated routing methods exist for RAG, and existing training-based routers face challenges scaling to this domain . |
| Approach: | They propose a plug-and-play routing framework that optimizes performance and cost . the framework delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x . |
| Outcome: | The proposed framework delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x compared to existing methods. |
Large Language Models are Complex Table Parsers (2023.emnlp-main)
Copied to clipboard
| Challenge: | Extensive experiments and results on Complex Table QA datasets, i.e., the open-domain dataset HiTAB and the aviation domain dataset AIT-QA show that our approach significantly outperforms previous work on both datasets. |
| Approach: | They propose to incorporate Generative Pre-trained Transformer 3.5 to address the specific challenges posed by Complex Table QA by reconstructing tables into tuples and using prompt templates to create dialogues. |
| Outcome: | The proposed approach outperforms previous work on complex table parsing datasets and leads to state-of-the-art (SOTA) performance. |
Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them (2025.findings-emnlp)
Copied to clipboard
Guanyu Chen, Peiyang Wang, Yizhou Jiang, Yuqian Liu, Chujie Zhao, Ying Fang, Tianren Zhang, Feng Chen
| Challenge: | Existing large language models can perform abstract reasoning tasks but are they actually engaging in rule-based reasoning beyond mere memorization? |
| Approach: | They propose a method to examine whether large language models perform abstract reasoning . they fine-tune the model to learn those contradictory rules and assess its generalization ability . |
| Outcome: | The proposed approach examines whether large language models perform abstract reasoning by altering their original understanding of fundamental rules. |
Generative Dense Retrieval: Memory Can Be a Burden (2024.eacl-long)
Copied to clipboard
| Challenge: | Empirical results show that Generative Dense Retrieval (GDR) achieves an average of 3.0 R@100 improvement on NQ dataset under multiple settings and has better scalability. |
| Approach: | They propose a Generative Dense Retrieval paradigm that auto-decodes document identifiers given a query and uses memory to avoid memory confusion. |
| Outcome: | Empirical results show that the proposed paradigm improves on the small-scale corpora and improves scalability. |
Bi-Tuning with Collaborative Information for Controllable LLM-based Sequential Recommendation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to optimize sequential recommendation systems rely on item ID sequences, but they lack collaborative knowledge and limited controllability. |
| Approach: | They propose a simple bi-tuning framework with collaborative information for controllable Large Language Model-based Sequential Recommendation (Laser) they incorporate learnable virtual tokens at prefix and suffix of input text to adapt LLMs with collaborative knowledge . |
| Outcome: | The proposed framework outperforms state-of-the-art recommendations on real-world datasets. |
Knowledge-Enhanced Named Entity Disambiguation for Short Text (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for named entity disambiguation are weak for short text . performance of existing methods drops dramatically for short texts . |
| Approach: | They propose a knowledge-enhanced method for named entity disambiguation . they use factual knowledge graph and conceptual knowledge graph to provide additional knowledge . |
| Outcome: | The proposed method achieves significant improvement on a large manually annotated short-text dataset and the state-of-the-art on three standard datasets. |
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to cross-lingual knowledge graph (KG) alignment rely on entity embeddings derived from monolingual KG structural information. |
| Approach: | They propose a topic entity graph to represent entities with contextual information in KGs. |
| Outcome: | The proposed model outperforms state-of-the-art methods by a large margin. |
Improving Entity Linking through Semantic Reinforced Entity Embeddings (2020.acl-main)
Copied to clipboard
| Challenge: | Existing entity embeddings are effective, but too distinctive for linking models to learn contextual commonality. |
| Approach: | They propose a method to inject fine-grained semantic information into entity embeddings . they use word embedds of type words to generate semantic embeddngs based on existing embeddables a sample of semantic information is injected into the embedded entities . |
| Outcome: | The proposed method reduces the distinctiveness of existing embeddings and improves performance. |
Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing defense methods struggle with two key issues: inadequate defense capabilities and over-defensiveness. |
| Approach: | They propose a multi-agents-based framework that leverages accurate external information to provide an unbiased summary of user intentions and safety response guidance. |
| Outcome: | Experiments on popular jailbreak attacks and benign datasets show that the proposed framework can enhance LLM's robustness against jailbreaks without compromising its general functionality. |
LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence (2026.findings-acl)
Copied to clipboard
Wenjin Liu, Haoran Luo, Xin Feng, Xiang Ji, Lijuan Zhou, Rui Mao, Jiapu Wang, Shirui Pan, Erik Cambria
| Challenge: | Existing benchmarks for legal general intelligence (GI) are result-oriented and do not evaluate the legal intelligence of large language models (LLMs). |
| Approach: | They propose a Chinese legal benchmark for evaluating legal GI in large language models . they use recent legal cases and exam questions to create multiple-choice questions . |
| Outcome: | The proposed benchmarks lack a systematic evaluation of the legal intelligence of large language models (LLMs) the results show that even the best LLMs lagging behind human legal professionals. |
Answer-Supervised Question Reformulation for Enhancing Conversational Machine Comprehension (D19-58)
Copied to clipboard
| Challenge: | Existing question reformulation models are based on supervised question labels without considering feedback information from answers. |
| Approach: | They propose a question reformulation model that integrates conversational history information with reinforcement learning. |
| Outcome: | The proposed model is more effective in conversational machine comprehension with reinforcement learning. |
Counter-Interference Adapter for Multilingual Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multilingual machine translation suffer from performance degradation, resulting in a single model being inferior to separately trained bilingual models on resource-rich languages. |
| Approach: | They propose a transformer-based model with a small parameter overhead for multilingual machine translation that outperforms strong multilingual baselines on 64 of 66 language directions. |
| Outcome: | The proposed model outperforms strong multilingual baselines on 64 of 66 language directions, 42 of which have above 0.5 BLEU improvement. |
Dual Class Knowledge Propagation Network for Multi-label Few-shot Intent Detection (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies on multi-label intent detection are confused by the identical representation of the utterance with multiple labels and overlook the intrinsic intra-class and inter-class relations. |
| Approach: | They propose a dual class knowledge propagation network to learn well-separated representations for utterances with multiple intents. |
| Outcome: | The proposed method outperforms baselines on two multi-label intent datasets by a large margin. |
MotifAgent: Learning Molecular Assembly through Multi-Agent Collaboration for Chemical Language Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to molecular understanding are limited to static motif recognition without understanding connection rules governing how motifs assemble into valid topological structures. |
| Approach: | They propose a multi-agent reinforcement learning framework inspired by emergent collective intelligence to solve a problem where each motif is represented by an agent sharing a common LLM backbone. |
| Outcome: | Extensive experiments show that the proposed framework surpasses specialized expert models in molecular understanding tasks. |
OpenICL: An Open-Source Framework for In-context Learning (2023.acl-demo)
Copied to clipboard
| Challenge: | In-context Learning (ICL) is a new paradigm for large language model evaluation. |
| Approach: | They propose an open-source toolkit for ICL and LLM evaluation. |
| Outcome: | The proposed framework is highly flexible and flexible and can be easily combined with other tools to suit users' needs. |
Poor-Supervised Evaluation for SuperLLM via Mutual Consistency (2024.findings-acl)
Copied to clipboard
| Challenge: | evaluating superLLMs is especially difficult because of their intelligence-intensive nature. |
| Approach: | They propose an evaluation benchmark with accurate labels for SuperLLMs whose capabilities surpass those of humans . they first prove that consistency between model under evaluation and reference model can equalize the true capabilities of the model to be evaluated . |
| Outcome: | The proposed evaluation benchmarks can assess the true capabilities of the model to be evaluated without accurate labels. |
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding (2022.findings-emnlp)
Copied to clipboard
Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Yuhui Cao, Weichong Yin, Yongfeng Chen, Yin Zhang, Shikun Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
| Challenge: | Existing methods for visually rich document understanding lack layout-centered knowledge . experimental results show that ERNIE-Layout improves layout awareness . |
| Approach: | They propose a document pre-training solution with layout knowledge enhancement in the whole workflow to learn better representations that combine the features from text, layout, and image. |
| Outcome: | The proposed model outperforms existing models on key downstream tasks. |
Mitigating the Discrepancy Between Video and Text Temporal Sequences: A Time-Perception Enhanced Video Grounding method for LLM (2025.coling-main)
Copied to clipboard
| Challenge: | Existing video LLMs excel at capturing the overall description of a video but lack the ability to demonstrate an understanding of temporal dynamics and localized content within the video. |
| Approach: | They propose a Time-Perception Enhanced Video Grounding via Boundary Perception and Temporal Reasoning to improve LLMs' understanding of video temporality. |
| Outcome: | The proposed method improves on three datasets: ActivityNet, Charades, and DiDeMo (up to 11.2% improvement on R@0.3). |
HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns (2026.acl-long)
Copied to clipboard
Xintao Wang, Jian Yang, Weiyuan Li, Rui Xie, Jen-tse Huang, Jun Gao, Shuai Huang, Yueping Kang, Yuanli Guo, Hongwei Feng, Yanghua Xiao
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs). |
| Approach: | They propose a framework that treats psychological patterns as interacting causal forces and synthesizes 113 scenarios where 2-5 patterns reinforce, conflict, or modulate each other. |
| Outcome: | The proposed framework outperforms Qwen3-32B on multi-pattern dynamics despite 4 fewer parameters. |
More Victories, Less Cooperation: Assessing Cicero’s Diplomacy Play (2024.acl-long)
Copied to clipboard
Wichayaporn Wongkamjan, Feng Gu, Yanze Wang, Ulf Hermjakob, Jonathan May, Brandon Stewart, Jonathan Kummerfeld, Denis Peskoff, Jordan Boyd-Graber
| Challenge: | Diplomacy is a boardgame that offers a challenge for communicative and cooperative AI. |
| Approach: | They run two dozen games with Cicero and annotate in-game communication with abstract meaning representation to separate in- game tactics from general language. |
| Outcome: | The proposed method can outperform Cicero in communicating with humans, but it's difficult to deceive and persuade AI. |
LAiW: A Chinese Legal Large Language Models Benchmark (2025.coling-main)
Copied to clipboard
Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang
| Challenge: | Xie et al., 2023) show that large language models (LLMs) can generate legal text, but lack the legal syllogism . legal experts are cautious about their practical application due to the opaque nature of the LLMs. |
| Approach: | They propose a Chinese legal LLM benchmark structured around the legal syllogism . they evaluate LLMs across three levels of capability, each reflecting a more complex stage of legal . |
| Outcome: | The proposed benchmark identifies that LLMs lack the legal syllogism, which hinders trust and understanding from legal experts. |
HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing (2024.findings-emnlp)
Copied to clipboard
Jing Chen, Xinyu Zhu, Cheng Yang, Chufan Shi, Yadong Xi, Yuxiang Zhang, Junjie Wang, Jiashu Pu, Tian Feng, Yujiu Yang, Rongsheng Zhang
| Challenge: | Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in the realm of literary creation. |
| Approach: | They propose a framework for unleashing the creativity of large language models (LLMs) they assign LLMs to different roles involved in real-world scenario, they write . |
| Outcome: | The proposed framework outperforms baselines in terms of coherence, relevance, interestingness and overall quality on automatically generated screenplays. |
How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs (2025.findings-acl)
Copied to clipboard
Guhao Feng, Kai Yang, Yuntian Gu, Xinyue Ai, Shengjie Luo, Jiacheng Sun, Di He, Zhenguo Li, Liwei Wang
| Challenge: | Despite the success of transformer-based large language models, understanding and enhancing their mathematical capabilities remains a significant challenge. |
| Approach: | They propose to use numerical precision as a key factor that influences LLMs' effectiveness in arithmetical tasks to determine their effectiveness. |
| Outcome: | The proposed models perform better in arithmetic tasks than transformer-based models with standard numerical precision. |
Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning (2026.acl-long)
Copied to clipboard
YiFan Zhang, Tao Yu, Feng Li, Chaoyou Fu, Yibo Hu, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin
| Challenge: | supervised fine-tuning (SFT) is crucial for multimodal large language models, yet a comprehensive scaling law is lacking . et al.: scaling laws focus on model size, pre-training tokens, and MLLM SFT data volumes . |
| Approach: | They propose two scaling laws to guide optimal model-data configuration . they propose one applicable when training data volumes are well defined by researchers . |
| Outcome: | The proposed scaling laws provide valuable recommendations for optimal resource allocation . they show that the proposed laws are more accurate than existing models . |
Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization (2025.acl-long)
Copied to clipboard
Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yangfan Ye, Weihong Zhong, Yuxuan Gu, Baoxin Wang, Dayong Wu, Guoping Hu, Bing Qin
| Challenge: | Existing frameworks for retrieval-augmented large language models (LLMs) are lacking in LFQA faithfulness testing. |
| Approach: | They propose a framework to teach retrieval-augmented large language models to explicitly discriminate between faithful and unfaithful generations. |
| Outcome: | The proposed framework outperforms GPT-4o in LFQA scenarios and outperformed existing benchmarks. |
RATION: Entropy-Driven Task-Adaptive Visual Attention Allocation Framework for Multimodal Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior studies have focused on strengthening multimodal reasoning by improving representation alignment or increasing computation, but these methods do not characterize the differences in visual demands across tasks. |
| Approach: | They propose an entropy-driven task-adaptive visual attention allocation framework that uses visual attention entropic as a control signal to dynamically allocate attention according to task demands. |
| Outcome: | The proposed framework achieves consistent performance gains across diverse reasoning tasks, datasets, and models, providing a clear direction toward more reliable multimodal reasoning. |
Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation (P19-1)
Copied to clipboard
| Challenge: | Existing generative methods overlook grammatical structure or make factual mistakes in generated texts. |
| Approach: | They propose a template-based method to ensure the readability of generated type descriptions . they also propose measurable metrics to measure the readibility of the generated type description . |
| Outcome: | The proposed method improves substantially compared with baselines and achieves state-of-the-art performance on both datasets. |
Crab: A Novel Configurable Role-Playing LLM with Assessing Benchmark (2025.acl-long)
Copied to clipboard
Kai He, Yucheng Huang, Wenqing Wang, Delong Ran, Dongming Sheng, Junxuan Huang, Qika Lin, Jiaxing Xu, Wenqiang Liu, Mengling Feng
| Challenge: | Existing RP-LLMs employ only a single role with numerous dialogues, but Crab enables dynamic configuration of desired roles, thereby enhancing related flexibility and adaptability. |
| Approach: | They propose a Configurable Role-Playing LLM with Assessing Benchmark that combines a Role dataset curation, persona-emodying Llm construction, and comprehensive benchmark creation for RP dialogue generation. |
| Outcome: | The proposed model outperforms existing LLMs in performing fine-grained evaluations of RP while keeping dialogue per role minimal. |
TC-Bench: Benchmarking Temporal Compositionality in Conditional Video Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing video generation models struggle to interpret compositional changes and synthesize components across different time steps. |
| Approach: | They propose a temporal compositionality benchmark that uses text prompts and ground truth videos to evaluate compositional changes in video. |
| Outcome: | The proposed benchmark can be used for text-to-video and image-to video generation. |
Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation (2024.findings-acl)
Copied to clipboard
| Challenge: | Stochastic sampling strategies are not widely used in open-domain dialogue systems. |
| Approach: | They propose a dynamic decoding strategy which can adjust the decoding space w.r.t. different contexts. |
| Outcome: | The proposed decoding strategy can improve the performance of pre-trained models when coupled with four well-used stochastic decoding algorithms. |
BERT-BC: A Unified Alignment and Interaction Model over Hierarchical BERT for Response Selection (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent performance boosting for dialogue response selection task achieved by Cross-Encoder based models is limited and the learned models have poor generalization capability in realistic scenarios. |
| Approach: | They propose a model that combines the representation-based Bi-Encoder and interaction-based Cross-Encoding to achieve better semantic representation. |
| Outcome: | The proposed model can achieve state-of-the-art performance on three benchmark datasets for multi-turn response selection. |
Improving the Robustness of Deep Reading Comprehension Models by Leveraging Syntax Prior (D19-58)
Copied to clipboard
| Challenge: | Recent studies indicate that the current machine reading comprehension systems suffer from weak robustness against adversarial samples. |
| Approach: | They propose to take sentence syntax as the leverage in the answer predicting process and exploit the syntactic elements of a question to improve the generalization and robustness of MRC models. |
| Outcome: | The proposed method improves generalization and robustness against adversarial samples, with performance well-maintained. |
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to training multi-turn attackers to probe model safety vulnerabilities rely on turn-level optimization, which is insufficient for learning long-term attack strategies. |
| Approach: | They propose a multi-turn reinforcement learning problem that optimizes the harmfulness of the final-turn response as the outcome reward. |
| Outcome: | The proposed approach improves attack success rates across multiple models and benchmarks, highlighting the effectiveness of the proposed approach. |
CBP-Tuning: Efficient Local Customization for Black-box Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Customized black-box prompt tuning is a new approach to customize large language models . however, as models grow, the resources required for training and deployment become increasingly expensive . |
| Approach: | They propose a framework that facilitates efficient local customization while preserving bidirectional privacy. |
| Outcome: | The proposed framework facilitates efficient local customization while preserving bidirectional privacy. |
Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal Prompt (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies require massive labeled data to train models for multimodal data analysis. |
| Approach: | They propose a novel multimodal prompt model that captures specific aspect terms in a few-shot scenario. |
| Outcome: | The proposed model outperforms baselines on two MABSA-related tasks on a few-shot dataset. |
M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have shown their potential to deliver human-like judgments. |
| Approach: | They propose a systematic LLM-based multi-agent framework for advanced LLM as-a-judge MT evaluation that integrates dimension-specific results into a final evaluation judgment. |
| Outcome: | The proposed framework outperforms existing LLM-as-a-judge methods and competes with state-of-the-art automatic metrics even when powered by a suboptimal model like GPT-4o mini. |
Query-aware Multi-modal based Ranking Relevance in Video Search (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Existing relevance ranking methods focus on text modality, incapable of fully exploiting cross-modal cues present in video. |
| Approach: | They propose a QUery-Aware pre-training model with multi-modality that integrates video tag information as alignment targets and enhances ranking optimization method based on ordinal regression. |
| Outcome: | The proposed model significantly improves video search performance. |
Flow-Based Page Unique Semantic Mapping Architecture for Document Visual Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Document Visual Question Answering (DocVQA) aims to generate answers by understanding textual, layout, and visual elements within document images. |
| Approach: | They propose a Flow-Based Page Unique Semantic Mapping Architecture to solve the distinguishability problem among semantically similar pages. |
| Outcome: | The proposed model outperforms existing methods in evidence localization and answer generation. |
ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing speech-to-speech large language models rely on ASR transcription or use encoders to extract latent representations, weakening affective information and contextual coherence in multi-turn dialogues. |
| Approach: | They propose a framework for speech-based empathetic response generation that captures turn-level affective states and dialogue-level emotional dynamics. |
| Outcome: | The proposed framework outperforms baselines in automatic and human evaluations and remains robust across different Large Language Model (LLM) backbones. |