Papers by Tao Shen
OOP: Object-Oriented Programming Evaluation Benchmark for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | None Large language models (LLMs) are emerging as a key tool for automated programming. |
| Approach: | They compare performance of None Large language models with language understanding models on functional programming and object-oriented programming benchmarks. |
| Outcome: | The models perform relatively well on functional programming (FP) and object-oriented programming (OOP) benchmarks, while exhibiting poor performance on OOP benchmarks. |
A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions (2025.findings-acl)
Copied to clipboard
Hongbin Na, Yining Hua, Zimu Wang, Tao Shen, Beibei Yu, Lilin Wang, Wei Wang, John Torous, Ling Chen
| Challenge: | Large language models (LLMs) can handle extensive context and multi-turn reasoning. |
| Approach: | They propose a taxonomy dividing psychotherapy into stages of assessment, diagnosis, and treatment to examine LLM advancements and challenges. |
| Outcome: | The proposed taxonomy reveals imbalances in current research, such as a focus on common disorders, linguistic biases, fragmented methods, and limited theoretical integration. |
Corpus-Steered Query Expansion with Large Language Models (2024.eacl-short)
Copied to clipboard
| Challenge: | Recent studies show query expansions generate hypothetical documents that answer queries as expansions. |
| Approach: | They propose a corpus-steered query expansion to promote incorporation of knowledge embedded within the corpus. |
| Outcome: | et al. analyzed corpus-based Query Expansion (CSQE) using LLMs to generate hypothetical documents that answer the query. |
Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing (2026.findings-acl)
Copied to clipboard
| Challenge: | Current methods for modifying parameters to integrate new knowledge are not accurate enough. |
| Approach: | They propose an SFT+RL framework that instills process-level faithfulness by a stage-aware Reward mechanism and a Stage-assisted Reward Mechanism. |
| Outcome: | The proposed framework instills process-level faithfulness while boosting final accuracy. |
Zero-shot Sharpness-Aware Quantization for Pre-trained Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing zero-shot quantization methods are based on overfitting problem in adversarial learning process, leading to sub-optimal performance. |
| Approach: | They propose a zero-shot sharpness-aware quantization framework for the quantization of various PLMs by optimizing a minimax problem. |
| Outcome: | The proposed framework can achieve significant performance gains on discriminative and generative PLMs. |
Revisiting Knowledge Distillation for Autoregressive Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Autoregressive language models (LMs) are expensive and memory intensive, preventing the development of industrial applications. |
| Approach: | They propose an adaptive teaching approach to improve the KD of autoregressive language models by distilling knowledge into a small student model. |
| Outcome: | The proposed method can achieve consistent and significant performance gains across all model types and sizes. |
Pre-training Cross-Modal Retrieval by Expansive Lexicon-Patch Alignment (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent large-scale vision-language pre-training relies on image-text global alignment by contrastive learning and is further boosted by fine-grained alignment in a weakly contrastive manner for cross-modal retrieval. |
| Approach: | They propose expansive lexicon-patch alignment (ELA) to align image patches with a vocabulary rather than only the words explicitly in the text for annotation-free alignment and information augmentation. |
| Outcome: | The proposed method outperforms state-of-the-art methods on cross-modal retrieval and can learn representative fine-grained information. |
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)
Copied to clipboard
Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM. |
| Approach: | They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks. |
| Outcome: | The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting. |
Rethinking Task-Specific Knowledge Distillation: Contextualized Corpus as Better Textbook (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for knowledge distillation use a two-stage paradigm: general distillation with a task-agnostic general corpus and task-specific distillation using augmented task- specific corpus. |
| Approach: | They propose a contextualized corpus that contextualizes task corpus with large-scale general corpus through relevance-based text retrieval to improve student learning. |
| Outcome: | The proposed model improves on the GLUE benchmark and shows that it is better than generalized corpus and augmented task-specific corpus. |
Iterative Document Representation Learning Towards Summarization with Polishing (D18-1)
Copied to clipboard
| Challenge: | Existing summarization methods read through document only once to generate a document representation, resulting in a sub-optimal representation. |
| Approach: | They propose an iterative model for supervised extractive text summarization which polishes the document representation on many passes through the document. |
| Outcome: | The proposed model outperforms state-of-the-art extractive systems on CNN/DailyMail and DUC2002 datasets. |
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)
Copied to clipboard
Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong
| Challenge: | Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored. |
| Approach: | They propose a survey structured around the pipeline to identify and improve MI models. |
| Outcome: | The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency. |
Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety (2025.emnlp-main)
Copied to clipboard
Chenhao Huang, Ziyu Shen, Yicong Ren, Huiyuan Zheng, Jiazheng Zhang, Mingxu Chai, Ming Zhang, Shihan Dou, Fan Mo, Jie Shi, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to align large language models with human preferences lack flexibility . static alignment preferences lack the ability to correct misaligned behaviors as they emerge . |
| Approach: | They propose a framework that enables dynamic and continuous alignment of large language models with human preferences. |
| Outcome: | The proposed framework improves safety and accuracy of a 7B model with human annotations. |
TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities (2024.emnlp-main)
Copied to clipboard
Ming Zhang, Caishuang Huang, Yilong Wu, Shichun Liu, Huiyuan Zheng, Yurui Dong, Yujiong Shen, Shihan Dou, Jun Zhao, Junjie Ye, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Current datasets cater to user-led systems and are limited to predefined specific scenarios and slots. |
| Approach: | They propose to use a Chinese dialogue dataset to train a model that authentically simulates human-computer dialogues in 30 popular life service scenarios. |
| Outcome: | The proposed model achieves a joint accuracy of 75.09% in out-of-domain evaluations . it also achieves notable abilities in slot filling and questioning . |
ADAM: Dense Retrieval Distillation with Adaptive Dark Examples (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to retrieve data from multiple encoders are too trivial for the teacher to distinguish, preventing the teacher from transferring abundant dark knowledge to the student. |
| Approach: | They propose a knowledge distillation framework that can better transfer the dark knowledge held in the teacher with adaptive dark examples. |
| Outcome: | The proposed framework can better transfer the dark knowledge held in the teacher with adaptive dark examples. |
PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts (2025.findings-acl)
Copied to clipboard
Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, but they struggle to solve strictly constrained dialogue tasks. |
| Approach: | They construct a dataset that contains 12,705 high-quality Chinese dialogue instructions from 440 flowcharts containing 5,055 process nodes. |
| Outcome: | The proposed model outperforms GPT-4o models on backward transitions and outperformed GPT-42 models on the same dataset. |
FACTrial: Factorized Clinical Contrastive Training for Scalable Patient-Trial Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to patient–trial retrieval rely on generic semantic matching and zero-shot transfer. |
| Approach: | They propose a factorized contrastive training framework that synthesizes diagnosis-aware supervision for scalable patient–trial retrieval. |
| Outcome: | Experiments show that the proposed framework improves quality and recall coverage. |
UMSE: Unified Multi-scenario Summarization Evaluation (2023.findings-acl)
Copied to clipboard
| Challenge: | Summarization quality evaluation is a non-trivial task in text summarization. |
| Approach: | They propose a unified multi-scenario summarization evaluation model that shares cross-sceenario knowledge and uses a self-supervised training paradigm to optimize the model without extra human labeling. |
| Outcome: | The proposed model can achieve comparable performance with existing methods for three evaluation scenarios. |
SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for training large language models waste computation budget on trivial steps while failing to guarantee sample quality. |
| Approach: | They propose a framework that selectively branches at critical decision states for resource-efficient exploration. |
| Outcome: | The proposed framework activates adaptive branching exploration at critical decision states to probe promising trajectories, thereby achieving precise resource allocation that prioritizes sampling quality over blind coverage. |
PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to learning sentence embeddings in unsupervised manner depend on mono-augmenting . existing approaches depend on augmenting biases and thus corrupt the quality of sentence embeds. |
| Approach: | They propose a method to augment a sentence with a semantically-close positive instance to construct contrastive pairs in unsupervised manner. |
| Outcome: | The proposed method improves performance on STS benchmarks and compares with existing methods. |
TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities (2023.acl-demo)
Copied to clipboard
Zhe Zhao, Yudong Li, Cheng Hou, Jing Zhao, Rong Tian, Weijie Liu, Yiren Chen, Ningyuan Sun, Haoyan Liu, Weiquan Mao, Han Guo, Weigang Gou, Taiqiang Wu, Tao Zhu, Wenhang Shi, Chen Chen, Shan Huang, Sihong Chen, Liqun Liu, Feifei Li, Xiaoshuai Chen, Xingwu Sun, Zhanhui Kang, Xiaoyong Du, Linlin Shen, Kimmo Yan
| Challenge: | Several pre-training models of different modalities are showing a rising trend of homogeneity in their model structures. |
| Approach: | They propose a toolkit that supports pre-training models of different modalities. |
| Outcome: | The proposed toolkit can match the performance of the original implementations on text, vision, and audio benchmarks. |
Dense Information Flow for Neural Machine Translation (N18-1)
Copied to clipboard
| Challenge: | Recent advances in deep neural networks have improved learning performance for NMT . Residual connections allow features from previous layers to be accumulated to the next layer easily. |
| Approach: | They propose a densely connected NMT architecture that can train more efficiently for NMT. |
| Outcome: | The proposed architecture improves learning performance and attention quality on multiple datasets. |
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (2023.emnlp-main)
Copied to clipboard
| Challenge: | Extensive experiments show that MEO significantly improves computational efficiency . compared to dense networks, sparsely activated networks only employ a few parameters for each input . |
| Approach: | They propose a method that merges multiple experts into one to reduce computation costs . they demonstrate that a sparse Mixture of Experts (MoE) can reduce the cost by activating a small subset of parameters for each input . |
| Outcome: | The proposed approach reduces the computational cost to that of a single expert by 83.3% compared to 82.6% in vanilla MoE. |
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. |
Reciprocal Learning of Knowledge Retriever and Response Ranker for Knowledge-Grounded Conversations (2022.coling-1)
Copied to clipboard
| Challenge: | Recent work on grounding dialogue agents with knowledge documents has sparked increased attention . hand-labeling data to that end is time-consuming and many datasets lack knowledge annotations . |
| Approach: | They propose a reciprocal learning approach to optimize a knowledge retriever and a response ranker for knowledge-grounded response retrieval without ground-truth knowledge labels. |
| Outcome: | The proposed model outperforms previous state-of-the-art methods on two public benchmarks. |
Synergistic Interplay between Search and Large Language Models for Information Retrieval (2024.acl-long)
Copied to clipboard
| Challenge: | Information retrieval (IR) is an indispensable technique for locating relevant resources from vast amounts of data. |
| Approach: | They propose a framework that facilitates information refinement through synergy between RMs and LLMs. |
| Outcome: | The proposed framework improves the performance of large-scale retrieval benchmarks on web searches and low-resource retrieval tasks. |
DP3: Differentially Private Prompt Perturbation for Multi-turn LLM Inference (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are widely used for text understanding and generation . existing methods that assume single-turn interactions break down in multi-turn settings . |
| Approach: | They propose a differentially private prompt perturbation framework for multi-turn LLM inference . DP3 constructs a perturbation mapping table to reuse perturbations for recurring tokens . |
| Outcome: | The proposed framework reduces privacy costs and degrades cross-turn semantic coherence . it also provides a context-aware utility function to maintain semantic consistency across turns . |
UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective (2025.emnlp-main)
Copied to clipboard
Jing Xiong, Jianghan Shen, Fanghua Ye, Chaofan Tao, Zhongwei Wan, Jianqiao Lu, Xun Wu, Chuanyang Zheng, Zhijiang Guo, Min Yang, Lingpeng Kong, Ngai Wong
| Challenge: | Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands. |
| Approach: | They propose an uncertainty-aware framework that leverages truncated matrix entropy to identify areas of low information content. |
| Outcome: | The proposed framework reduces the KV cache size to 4.74% of the original and achieves a 6% speedup. |
ThinkQE: Query Expansion via an Evolving Thinking Process (2025.findings-emnlp)
Copied to clipboard
| Challenge: | LLM-based methods often generate narrowly focused expansions that overlook these desiderata. |
| Approach: | They propose a test-time query expansion framework that promotes exploration and result diversity . ThinkQE encourages deeper and comprehensive semantic exploration and a corpus-interaction strategy that iteratively refines expansions . |
| Outcome: | The proposed framework outperforms prior approaches on diverse web search benchmarks. |
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models (2026.acl-long)
Copied to clipboard
Ming Zhang, Yujiong Shen, Jingyi Deng, Yuhui Wang, Huayu Sha, Kexin Tan, Qiyuan Peng, Yue Zhang, Junzhe Wang, Shichun Liu, Yueyuan Huang, Jingqi Tong, Changhao Jiang, Yilong Wu, Zhihao Zhang, Mingqi Wu, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing evaluation of Large Language Models on static benchmarks is vulnerable to data contamination and leaderboard overfitting. |
| Approach: | LLMEval-Fair framework provides a framework for dynamic evaluation of Large Language Models . evaluators use a proprietary bank of 220k graduate-level questions to analyze model data . |
| Outcome: | LLMEval-Fair provides robust and credible evaluation framework for Large Language Models . it provides a strong empirical validation for the dynamic evaluation paradigm . |
ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification (2022.acl-long)
Copied to clipboard
| Challenge: | Existing work on event-centric reasoning fails to model event-level correlations . Existing studies limit their scope to specific scenarios or overlook event- level correlations. |
| Approach: | They propose to pre-train a general Correlation-aware context-to-Event Transformer for event-centric reasoning by highlighting event-level correlations with effective training. |
| Outcome: | The proposed model is applicable to a wide range of event-centric reasoning scenarios, considering its versatility of event correlation types, application formulations, and reasoning types. |
ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models (2025.acl-long)
Copied to clipboard
Hanxing Ding, Shuchang Tao, Liang Pang, Zihao Wei, Jinyang Gao, Bolin Ding, Huawei Shen, Xueqi Cheng
| Challenge: | Existing approaches to tool learning rely on hand-crafted prompts and natural language reasoning, making multi-step planning difficult and lacking precise error diagnosis and reflection mechanisms. |
| Approach: | They propose a framework that reformulates tool learning as a code generation task. |
| Outcome: | The proposed framework achieves superior performance in task completion accuracy and execution reliability compared to existing approaches. |
Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to encode natural languages without orders are lacking. |
| Approach: | They conduct a comprehensive analysis of the ability of neural models to organize sentences from a bag of words under three typical scenarios. |
| Outcome: | The proposed models can reorder or reconstruct sentences from a bag of words under three typical scenarios. |
Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement (2025.emnlp-industry)
Copied to clipboard
Haotan Guo, Jianfei He, Jiayuan Ma, Hongbin Na, Zimu Wang, Haiyang Zhang, Qi Chen, Wei Wang, Zijing Shi, Tao Shen, Ling Chen
| Challenge: | Phonetic Cloaking Replacement (PCR) is a problem in content moderation in China. |
| Approach: | They organize PCR into a four-way surface-form taxonomy and compile PCR-ToxiCN, a dataset of 500 phonetically cloaked offensive posts gathered from the RedNote platform. |
| Outcome: | The proposed model achieves only an F1-score and zero-shot chain-of-thought prompting pushes performance even lower. |
When to Trust LLMs: Aligning Confidence with Response Quality (2024.findings-acl)
Copied to clipboard
Shuchang Tao, Liuyi Yao, Hanxing Ding, Yuexiang Xie, Qi Cao, Fei Sun, Jinyang Gao, Huawei Shen, Bolin Ding
| Challenge: | Existing methods express reliability by confidence level, but lack objective guidance . Existing approaches express reliability but lack guidance on when to trust LLMs . |
| Approach: | They propose a reward-based approach to align confidence with quality to ensure reliability . they propose 'conqORD' to help model to verbalize greater confidence for higher quality responses . |
| Outcome: | Experiments show that CONQORD significantly improves confidence and response accuracy . the proposed approach can be used to determine reliability of large language models . |
Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base (D19-1)
Copied to clipboard
| Challenge: | Recent approaches to handle large knowledge base decompose tasks into subtasks and solve them sequentially. |
| Approach: | They propose a multi-task learning framework that resolves coreference in conversations . they propose enabling shared supervisions and type-aware entity detection model . |
| Outcome: | The proposed framework improves overall F1 score from 67% to 79% on a large-scale conversational question answering dataset. |
CORE: Cooperative Training of Retriever-Reranker for Effective Dialogue Response Selection (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods to train retrieval-based dialogue systems are suboptimal . existing methods to optimize retrieval and rerank modules are sub-optimal, causing sub-optimum performance. |
| Approach: | They propose a retrieval-based dialogue system with a fast retriever and a smart response reranker that combine the best of both worlds. |
| Outcome: | The proposed method can learn from each other and evolve together . it can be used in industrial applications and has powered industrial applications. |
Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for integrating knowledge graphs into pre-trained language models have been poorly implemented. |
| Approach: | They propose a self-supervised entity masking scheme that exploits relational knowledge underlying the text. |
| Outcome: | The proposed model achieves improved performance on five benchmarks, including question answering and knowledge base completion. |
Length-Adaptive Distillation: Customizing Small Language Model for Dynamic Token Pruning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to accelerate inference speed are model compression and dynamic computation (e.g., dynamic token pruning). |
| Approach: | They propose a two-stage knowledge distillation framework that produces a customized small language model for dynamic token pruning. |
| Outcome: | The proposed framework can make the small language model more customized for dynamic token pruning and achieve better speed-performance trade-off. |
Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models encode vast amounts of knowledge but remain static once trained, making timely integration of emerging facts prohibitively expensive via full retraining. |
| Approach: | They introduce a reasoning-chain-based editing framework that steers a pretrained LLM through four structured stages to filter distractors in a single pass. |
| Outcome: | The proposed framework steers a pretrained LLM through four structured stages to filter distractors in a single pass. |
Social Norms-Grounded Machine Ethics in Complex Narrative Situation (2022.coling-1)
Copied to clipboard
| Challenge: | Recent studies focus on data-driven methods to judge the ethics of complex real-world narratives but face two major challenges: they cannot handle dilemma situations due to a lack of basic knowledge about social norms; and they focus on sparse situation-level judgment regardless of the social norm. |
| Approach: | They propose to complement a complex situation with grounded social norms by a norm-supported ethical judgment model in line with neural module networks to alleviate dilemma situations and improve norm-level explainability. |
| Outcome: | The proposed model improves state-of-the-art performance on two narrative judgment benchmarks. |
ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)
Copied to clipboard
Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo
| Challenge: | Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task. |
| Approach: | They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5. |
| Outcome: | The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers. |
Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)
Copied to clipboard
Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values. |
| Approach: | They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values . |
| Outcome: | The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets. |
On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT) however, it often fails to achieve notable gains on resource-rich NMT on par with its Random-Initialization (RI) counterpart. |
| Approach: | They propose to combine pre-training and random-initialization techniques to achieve significant improvements in NMT. |
| Outcome: | The proposed model fusion algorithm can achieve significant improvements on two resource-rich translation benchmarks. |
Leveraging Large Language Models for NLG Evaluation: Advances and Challenges (2024.emnlp-main)
Copied to clipboard
| Challenge: | introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. |
| Approach: | They propose a taxonomy for organizing existing LLM-based evaluation metrics and a structured framework to understand and compare them. |
| Outcome: | The proposed taxonomy offers a framework to understand and compare LLM-based evaluation methods. |
You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations (2026.findings-acl)
Copied to clipboard
Hongbin Na, Zimu Wang, Zhaoming Chen, Peilin Zhou, Yining Hua, Grace Ziqi Zhou, Haiyang Zhang, Tao Shen, Wei Wang, John Torous, Shaoxiong Ji, Ling Chen
| Challenge: | Psychological defenses are strategies people use to manage distress. |
| Approach: | They propose a dialogue corpus with help seeker utterances labeled for defense level and a DMRS Co-Pilot pipeline that provides evidence-based pre-annotations. |
| Outcome: | The proposed framework reduces annotation time by 24.0% in a counterbalanced study. |
Re-Reading Improves Reasoning in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Unlike thought-eliciting prompting methods, RE2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process. |
| Approach: | They introduce a simple, yet general and effective prompting method, RE2, which rereads the question as input. |
| Outcome: | The proposed method demonstrates strong generality and compatibility with most thought-eliciting prompting methods, including CoT. |
FAA: Fine-grained Attention Alignment for Cascade Document Ranking (2023.acl-long)
Copied to clipboard
| Challenge: | Contemporary document ranking methods focus on transforming documents into passages to handle long inputs, but intensive query-irrelevant content may lead to harmful distraction and high query latency. |
| Approach: | They propose a fine-grained attention alignment approach to jointly optimize a cascade document ranking model. |
| Outcome: | Experiments on MS MARCO and TREC DL show that the proposed method is effective in document ranking tasks. |
Enhancing Lexicon-Based Text Embeddings with Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have demonstrated exceptional performance on general-purpose text embedding tasks. |
| Approach: | They introduce the first lexicon-based embeddings that consolidates the vocabulary space through token embeddation clustering to handle the issue of token redundancy in LLM vocabularies. |
| Outcome: | The proposed model outperforms dense embeddings on the Massive Text Embedding Benchmark (MTEB) it also supports efficient dimension pruning without any specialized objectives like Matryoshka Representation Learning. |
O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning (2026.findings-acl)
Copied to clipboard
Haotian Luo, Haiying He, Yibo Wang, Shiwei Liu, Wei Li, Xiaochun Cao, Dacheng Tao, Naiqiang Tan, Li Shen
| Challenge: | Recent long-thought reasoning models adopt extended reasoning processes similar to how humans ponder over complex problems. |
| Approach: | They propose a model that uses RL-style fine-tuning to reduce inference overhead while maintaining accuracy. |
| Outcome: | The proposed model reduces inference overhead while maintaining accuracy. |
Meta-Task Prompting Elicits Embeddings from Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for large language modeling are based on task-related instructions or prompts. |
| Approach: | They propose a method for generating high-quality sentence embeddings from Large Language Models (LLMs) using meta-task prompts. |
| Outcome: | The proposed method produces high-quality sentences without fine-tuning . it excels on STS benchmarks and in downstream tasks, surpassing models with similar prompts . |
Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing NER-based transformer models are expensive and lack contextual dependencies, making them less reliable when handling unseen or ad-specific terms, e.g., brand names. |
| Approach: | They propose a two-stage approach to casing correction in e-commerce ad content that leverages Chain-of-Actions to enforce content policies while accurately handling ads-specific terms. |
| Outcome: | The proposed model outperforms existing NER-based models and achieves near-LLM performance at a fraction of the cost. |
Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision (2022.findings-naacl)
Copied to clipboard
| Challenge: | Distant supervision uses triple facts to label corpus for relation extraction, leading to wrong labeling and long-tail problems. |
| Approach: | They propose a model to enrich distantly-supervised sentences with entity types by injecting context-free and -related backgrounds into sentences to alleviate sentence-level wrong labeling. |
| Outcome: | The proposed model achieves state-of-the-art on benchmarks and in overall and long-tail performance. |
Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to handle wrong labeling and long-tail relations are labor-intensive and scarce training data. |
| Approach: | They propose a neural network to handle wrong labeling and long-tail relations by collaborating relation-augmented attention. |
| Outcome: | The proposed neural network improves the state-of-the-art on the NYT dataset . |
MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation (2025.findings-acl)
Copied to clipboard
Zhongwei Wan, Che Liu, Xin Wang, Chaofan Tao, Hui Shen, Jing Xiong, Rossella Arcucci, Huaxiu Yao, Mi Zhang
| Challenge: | Recent studies have focused on classifying cardiac conditions using ECG data but have overlooked ECG report generation, which is time-consuming and requires clinical expertise. |
| Approach: | They propose a Multimodal ECG Instruction Tuning framework that extends the capability of large language models (LLMs) for the task. |
| Outcome: | The proposed framework outperforms open-source LLMs and LLM backbones across two large-scale ECG datasets. |
Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to update large language models focus on single-language editing or basic multilingual editing, failing to achieve true cross-linguistic knowledge synchronization. |
| Approach: | They propose a cross-linguistic knowledge democracy edit technique to improve cross-lingual performance. |
| Outcome: | The proposed method improves cross-lingual performance while maintaining high accuracy in monolingual settings. |
Modeling Event-Pair Relations in External Knowledge Graphs for Script Reasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on graph triples with event overlap, but ignore more supportive triples . Script reasoning relies on understanding the relationship between two events . |
| Approach: | They propose a model to learn the inferential relations between events from the whole eventuality KG . they propose 'script adapter' to extend the model to infer the associated relations between an event chain and a subsequent event candidate. |
| Outcome: | The proposed model is compared with baselines using external KG or not on a script reasoning task. |
CFBench: A Comprehensive Constraints-Following Benchmark for LLMs (2025.acl-long)
Copied to clipboard
Tao Zhang, ChengLIn Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Tao Zhang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, Zenan Zhou
| Challenge: | Existing evaluations of Large Language Models (LLMs) focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user’s perspective. |
| Approach: | They propose a Chinese Comprehensive Constraints Following Benchmark for LLMs that compiles constraints from real-world instructions and constructs a systematic framework for constraint types. |
| Outcome: | The proposed framework integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment. |
Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together (N19-1)
Copied to clipboard
| Challenge: | Neural networks equipped with self-attention have parallelizable computation and the ability to capture both long-range and local dependencies. |
| Approach: | They propose a novel attention mechanism called "Multi-mask Tensorized Self-Attention" it captures pairwise and global dependencies by a compatibility function composed of dot-product and additive attentions . |
| Outcome: | The proposed model outperforms CNN-/RNN-/attention-based models on nine NLP benchmarks with compelling memory- and time-efficiency. |
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation (2025.findings-emnlp)
Copied to clipboard
Ming Zhang, Yujiong Shen, Zelin Li, Huayu Sha, Binze Hu, Yuhui Wang, Chenhao Huang, Shichun Liu, Jingqi Tong, Changhao Jiang, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current medical benchmarks have limitations in question design, data sources and evaluation methods. |
| Approach: | They propose a new benchmark covering five core medical areas . it includes 2,996 questions created from real-world electronic health records . |
| Outcome: | The proposed model covers five core medical areas and includes 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios. |
Retrieval-Augmented Retrieval: Large Language Models are Strong Zero-Shot Retriever (2024.findings-acl)
Copied to clipboard
Tao Shen, Guodong Long, Xiubo Geng, Chongyang Tao, Yibin Lei, Tianyi Zhou, Michael Blumenstein, Daxin Jiang
| Challenge: | Large-scale retrieval is indispensable in information-seeking tasks such as open-domain question answering and knowledgegrounded dialogue. |
| Approach: | They propose to use a large language model (LLM) to augment a query with its potential answers by prompting LLMs with a composition of the query and the query’s in-domain candidates. |
| Outcome: | The proposed method breaks brute-force combinations of retrievers with LLMs and lifts the performance of zero-shot retrieval to be very competitive on benchmark datasets. |
Analogical Reasoning on Chinese Morphological and Semantic Relations (P18-2)
Copied to clipboard
| Challenge: | Analogical reasoning is effective in capturing linguistic regularities. |
| Approach: | They propose to use Chinese lexical knowledge to build an analogical reasoning task using a large dataset. |
| Outcome: | The proposed dataset proves to be reliable benchmark for evaluating Chinese word embeddings. |
Extractive Medical Entity Disambiguation with Memory Mechanism and Memorized Entity Information (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods focus on local optimal while ignoring sole-mention disambiguation boosted by richer context from other mentions’ disambiguating processes. |
| Approach: | They propose an approach to extracting medical entity disambiguation using memory mechanism and memorized entity information (M3E) they use a memory mechanism module that performs memory caching, retrieval, fusion and cross-network residual to aid the disambiguations of remaining mentions. |
| Outcome: | The proposed method outperforms state-of-the-art methods on two benchmark datasets. |
Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Aspect-level sentiment classification (ALSC) is a practical setting in aspect-based sentiment analysis due to no opinion term labeling needed, but it fails to interpret why a sentiment polarity is derived for the aspect. |
| Approach: | They propose a span-based anti-bias aspect representation learning framework that eliminates the sentiment bias in the aspect embedding by adversarial learning against aspects’ prior sentiment. |
| Outcome: | The proposed framework achieves state-of-the-art performance on five benchmarks, with the capability of unsupervised opinion extraction. |
ATLAS: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning (2026.findings-acl)
Copied to clipboard
Jinyang Wu, Guocheng Zhai, Ruihan Jin, Jiahao Yuan, Yuhao Shen, Shuai Zhang, Zhengqi Wen, Jianhua Tao
| Challenge: | Existing approaches to optimize large language models with external tools are limited. |
| Approach: | They propose a dual-path framework for dynamic tool usage in cross-domain complex reasoning . they exploit empirical priors for domain-specific alignment and RL-based multi-step routing . |
| Outcome: | The proposed framework outperforms closed-source models and existing methods on in-distribution and out-of-distortion tasks. |
CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing methods to improve pre-trained language models for many-class classification suffer from verbalizer ambiguity . a significant disparity exists between the pre-training and fine-tuning stages of the model . |
| Approach: | They propose a method to tune pre-trained language models to a broad spectrum of tasks . they use an instance-dependent soft prefix to complement language verbalizers in many-class classification . |
| Outcome: | The proposed method outperforms baselines on many-class datasets. |
Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to solve multilingual question answering over knowledge graph (KGQA) use of bilingual lexicon induction to map training questions into those in target language circumvents language inconsistency . |
| Approach: | They propose to use bilingual lexicon induction to map training questions in source and target languages as augmented training data to minimize syntax-disorder. |
| Outcome: | The proposed model narrows the gap in zero-shot cross-lingual transfer between source and target languages. |
Towards Robust Ranker for Text Retrieval (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for text retrieval are based on a 'retrieval & rerank' pipeline, which uses a fast retriever to fetch a set of top document candidates, while a robust ranker is based upon a weak negative mining during contrastive learning. |
| Approach: | They propose a multi-adversarial training strategy that leverages multiple retrievers as generators to challenge a ranker. |
| Outcome: | The proposed model outperforms the existing de facto ranker training paradigms on the passage retrieval benchmarks using BM25-reranking, full-ranking and retriever distillation. |
RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches for knowledge graph embedding have limitations in complex vector space . embeddability of one-to-many relations is not explicitly alleviated . |
| Approach: | They propose a relation-adaptive translating embedding function that can be extended to complex vector space. |
| Outcome: | The proposed translation function improves expressive power and alleviates embedding ambiguity problem. |
Improving Text Generation with Student-Forcing Optimal Transport (2020.emnlp-main)
Copied to clipboard
Jianqiao Li, Chunyuan Li, Guoyin Wang, Hao Fu, Yuhchen Lin, Liqun Chen, Yizhe Zhang, Chenyang Tao, Ruiyi Zhang, Wenlin Wang, Dinghan Shen, Qian Yang, Lawrence Carin
| Challenge: | Maximum likelihood estimation (MLE) is used to train models, but during testing, the model is conditioned on previously generated tokens, resulting in exposure bias. |
| Approach: | They propose to use optimal transport to match the sequences generated in MLE and test modes to reduce exposure bias. |
| Outcome: | The proposed method is validated on machine translation, text summarization, and text generation tasks. |
Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results prove that language models can learn from human feedback better, irrespective of sequence length . emergence of length bias often induces the model to favor longer outputs . |
| Approach: | They propose to separate reward modeling from the influence of sequence length by using the Product-of-Experts technique. |
| Outcome: | The proposed approach shows that language models perform better regardless of sequence length . the main expert is focused on understanding human intents, while the biased expert targets the identification and capture of length bias. |
Improving Textual Network Embedding with Global Attention via Optimal Transport (P19-1)
Copied to clipboard
Liqun Chen, Guoyin Wang, Chenyang Tao, Dinghan Shen, Pengyu Cheng, Xinyuan Zhang, Wenlin Wang, Yizhe Zhang, Lawrence Carin
| Challenge: | Existing methods for learning textual network embeddings are noisy and sparse. |
| Approach: | They propose to use text-based attention parsing to learn context-aware network embeddings. |
| Outcome: | The proposed model outperforms state-of-the-art methods in a number of domains. |
Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)
Copied to clipboard
Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations. |
| Approach: | They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference. |
| Outcome: | The proposed method significantly mitigates object hallucinations across various model architectures. |
STA-CoT: Structured Target-Centric Agentic Chain-of-Thought for Consistent Multi-Image Geological Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Reliable multi-image geological reasoning is essential for automating expert tasks in remote-sensing mineral exploration. |
| Approach: | They propose a framework that orchestrates planning, execution, and verification agents to decompose, ground, and iteratively refine reasoning steps over geological and hyperspectral image sets. |
| Outcome: | The proposed framework decomposes, ground, and iteratively refines reasoning steps over geological and hyperspectral image sets. |
Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pretrained language models suffer from poor generalization . however, they add a perturbation to each model parameter equally, which is sub-optimal . |
| Approach: | They propose a sharpness-aware minimization optimization procedure that introduces a Fisher mask to improve the efficiency of SAM. |
| Outcome: | The proposed method outperforms the vanilla sharpness-aware minimization method on GLUE and SuperGLUE benchmarks. |
Towards Making the Most of ChatGPT for Machine Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Prior studies have shown that ChatGPT achieves comparable results to commercial systems for high-resource languages, but lags behind in complex tasks, e.g., low-resourced and distant-language-pairs translation. |
| Approach: | They propose task-specific prompts and domain-specific prompts which are based on task information and domain information and a task-specific prompt. |
| Outcome: | The proposed prompts improve the performance of ChatGPT in complex tasks and generate hallucinations for non-English-centric tasks. |
Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis (2025.emnlp-main)
Copied to clipboard
Hanxi Guo, Siyuan Cheng, Xiaolong Jin, Zhuo Zhang, Guangyu Shen, Kaiyuan Zhang, Shengwei An, Guanhong Tao, Xiangyu Zhang
| Challenge: | Existing methods to identify the origin of AI-generated texts fail to identify origin due to the high similarity of different LLMs. |
| Approach: | They propose a black-box AI-generated text origin detection method which accurately predicts the origin of an input text by extracting distinct context inference patterns. |
| Outcome: | The proposed method outperforms 10 state-of-the-art baselines and achieves a 25% increase in AUC score on average across natural language and code datasets. |
UniEvent: Unified Generative Model with Multi-Dimensional Prefix for Zero-Shot Event-Relational Reasoning (2023.acl-long)
Copied to clipboard
| Challenge: | Reasoning about events and their relations is an indispensable ability to fulfill various event-centric or common-sense reasoning tasks. |
| Approach: | They propose a multi-task learning framework that organizes event relational reasoning tasks into a coordinate system with multiple axes, representing inter-event relations and reasoning formulations. |
| Outcome: | The proposed framework achieves state-of-the-art or competitive performance on zero-shot and supervised reasoning tasks. |
Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training (2026.acl-long)
Copied to clipboard
Changhao Jiang, Ming Zhang, Yifei Cao, Junjie Ye, Xiaoran Fan, Shihan Dou, Zhiheng Xi, Jiajun Sun, Yi Dong, Yujiong Shen, Jingqi Tong, Baoyu Fan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods to predict performance of large language models are lacking . authors propose a size-dependent mutual information predictor for closed-book question answering accuracy . |
| Approach: | They propose a size-dependent mutual information predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering accuracy. |
| Outcome: | The proposed method outperforms baseline models and achieves R2 > 0.7 in predicting QA accuracy without additional training. |