Papers by Yang Tang
Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs). |
| Approach: | They propose a framework that leverages an LLM to decompose questions into searchable triplets with placeholders. |
| Outcome: | Empirical results show that T2RAG outperforms state-of-the-art multi-round and Graph RAG methods while reducing retrieval costs by up to 45%. |
TURING: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface (2021.acl-demo)
Copied to clipboard
Peng Xu, Wenjie Zi, Hamidreza Shahidi, Ákos Kádár, Keyi Tang, Wei Yang, Jawad Ateeq, Harsh Barot, Meidan Alon, Yanshuai Cao
| Challenge: | Existing text-to-SQL semantic parsers cannot achieve high accuracy in cross-database setting . TURING is a NLDB system that can be used to democratize data-driven insights for non-technical users . |
| Approach: | They propose a TURING system that provides high-precision natural language explanations of SQL queries in a beam. |
| Outcome: | The proposed system achieves 75.1% execution accuracy and 78.3% top-5 beam execution accuracy on the Spider validation set. |
Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models (2025.emnlp-main)
Copied to clipboard
Qihang Ma, Shengyu Li, Jie Tang, Dingkang Yang, null Chenshaodong, Yingyi Zhang, Chao Feng, Ran Jiao
| Challenge: | Multi-modal keyphrase prediction (MMKP) aims to produce concise, informative phrases that capture the essence of cross-modal inputs. |
| Approach: | They propose to use vision-language models to generate conclusive phrases using multiple modalities of input information. |
| Outcome: | The proposed methods outperform existing methods on absence and unseen scenarios and overestimate model capability due to overlap in training tests. |
LLMs as Lab Engineers: A Benchmark for Analytical Method Lifecycle Management (2026.findings-acl)
Copied to clipboard
Xiaoyi Chen, Mahsa Monshizadeh, Chaoqi Zhang, Jianjun Lang, Yang Wu, Genevieve Mortensen, Xiaozhong Liu, Haixu Tang
| Challenge: | General-purpose commercial models outperform domain-specialized ones, while RAG and reasoning significantly improve performance. |
| Approach: | They propose a benchmark to evaluate LLMs' capabilities in analytical chemistry scenarios. |
| Outcome: | The proposed framework outperforms existing benchmarks focused on factual knowledge and provides practical guidance for analytical chemistry challenges. |
GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs (2026.acl-long)
Copied to clipboard
Weidong Tang, Jierui Li, Yueling Hou, Zihan Mei, Can Zhang, Xinyan Wan, Zhiyuan Liang, Pengfei Zhou, Yang You, Wangbo Zhao
| Challenge: | Existing models for general intelligence fail to model how mental states interact and crystallize into group-level outcomes. |
| Approach: | They propose a multimodal benchmark for group-level Theory of Mind (ToM) to probe nonlinear collective behavior. |
| Outcome: | The proposed model performs significantly below human levels, exposing blind spots in modeling social structures and nonlinear collective behavior. |
Optimizing Deeper Transformers on Small Datasets (2021.acl-long)
Copied to clipboard
Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, Jackie Chi Kit Cheung, Simon J.D. Prince, Yanshuai Cao
| Challenge: | a common belief that training deep transformers from scratch requires large datasets is wrong . however, with proper initialization and optimization, the benefits of very deep transformer can carry over to challenging tasks with small datasets. |
| Approach: | They train 48 layers of transformers from pre-trained RoBERTa and 24 relation-aware layers from scratch. |
| Outcome: | The proposed scheme achieves state-of-the-art performance on a text-to-sql parsing benchmark . it uses 24 fine-tuned layers from pre-trained RoBERTa and 24 relation-aware layers from scratch . |
RoadMapper: A Multi-Agent System for Roadmap Generation of Solving Complex Research Problems (2026.findings-acl)
Copied to clipboard
Jiacheng Liu, Zichen Tang, Zhongjun Yang, Xinyi Hu, Xueyuan Lin, Linwei Jia, Ruofei Bai, Rongjin Li, Shiyao Peng, Haocheng Gao, Haihong E
| Challenge: | Existing tools to generate structured content for research tasks are limited in their ability to generate high-quality roadmaps. |
| Approach: | They propose a benchmark to evaluate the ability of large language models (LLMs) to generate high-quality roadmaps for solving complex research problems. |
| Outcome: | The proposed system can improve LLMs’ ability for roadmap generation while saving 84% of the time required by human experts. |
Enhancing Self-Attention with Knowledge-Assisted Attention Maps (2022.naacl-main)
Copied to clipboard
Jiangang Bai, Yujing Wang, Hong Sun, Ruonan Wu, Tianmeng Yang, Pengfei Tang, Defu Cao, Mingliang Zhang1, Yunhai Tong, Yaming Yang, Jing Bai, Ruofei Zhang, Hao Sun, Wei Shen
| Challenge: | Existing works of knowledge infusion depend on multi-task learning frameworks, which are inefficient and require large-scale retraining when new knowledge is considered. |
| Approach: | They propose a method which integrates knowledge-generated attention maps into the self-attention mechanism and integrates it into the model. |
| Outcome: | The proposed model outperforms existing methods on academic datasets and industry-scale ad relevance applications. |
MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills (2026.eacl-long)
Copied to clipboard
Zonghai Yao, Zihao Zhang, Chaolong Tang, Xingyu Bian, Youxia Zhao, Zhichao Yang, Junda Wang, Huixue Zhou, Won Seok Jang, Feiyun Ouyang, Hong Yu
| Challenge: | Current clinical LLM benchmarks fail to evaluate advanced clinical skills in AI and large language models (LLMs). |
| Approach: | They propose a framework to evaluate large language models (LLMs) using two instruction-following tasks designed to reflect real clinical scenarios. |
| Outcome: | The proposed framework evaluates LLMs through two instruction-following tasks designed to reflect real clinical scenarios. |
From Charts to Code: A Hierarchical Benchmark for Multimodal Models (2026.acl-long)
Copied to clipboard
Jiahao Tang, Henry Hengyuan Zhao, Lijian Wu, Zijian Zhang, Yifei Tao, Dongxing Mao, Yang Wan, Jingru Tan, Min Zeng, Min Li, Alex Jinpeng Wang
| Challenge: | Chart2Code is a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models. |
| Approach: | They introduce Chart2Code, a new benchmark for evaluating the natural language to chart code generation capabilities of large multimodal models. |
| Outcome: | The proposed benchmark is the first to scale task complexity while capturing diverse scenarios. |
FinEntity: Entity-level Sentiment Classification for Financial Texts (2023.emnlp-main)
Copied to clipboard
| Challenge: | FinEntity annotates financial entity spans and their sentiment (positive, neutral, and negative) in financial news. |
| Approach: | They introduce an entity-level sentiment classification dataset called FinEntity that annotates financial entity spans and their sentiment in financial news. |
| Outcome: | The proposed dataset annotates financial entity spans and their sentiment (positive, neutral, and negative) in financial news. |
UnCo: Uncertainty-Driven Collaborative Framework of Large and Small Models for Grounded Multimodal NER (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to identify unseen multimodal entities struggle with limited knowledge and generalization. |
| Approach: | They propose a framework that leverages the strengths of small fine-tuned models and MLLMs to generate unambiguous predictions. |
| Outcome: | Extensive experiments show that the proposed framework retains the in-domain knowledge of small models while utilizing the capabilities of MLLMs to handle unseen entities. |
Defending against Indirect Prompt Injection by Instruction Detection (2025.findings-emnlp)
Copied to clipboard
Tongyu Wen, Chenglong Wang, Xiyuan Yang, Haoyu Tang, Yueqi Xie, Lingjuan Lyu, Zhicheng Dou, Fangzhao Wu
| Challenge: | Indirect Prompt Injection attacks can be exploited by LLMs that are embedded with external data. |
| Approach: | They propose a detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks. |
| Outcome: | The proposed approach reduces the success rate of attacks to 0.03% on the BIPIA benchmark. |
Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Haonan He, Yuchen Ren, Yining Tang, Ziyang Xu, Junxian Li, Minghao Yang, Di Zhang, Yuan Dong, Tao Chen, Shufei Zhang, Yuqiang Li, Nanqing Dong, Wanli Ouyang, Dongzhan Zhou, Peng Ye
| Challenge: | Biology-Instructions is the first large-scale instruction-tuning dataset for multi-omics biological sequences. |
| Approach: | They propose a large-scale instruction-tuning dataset for multi-omics biological sequences . they propose 'chatMultiOmics' to overcome limitations of current LLMs on multi-ome tasks . |
| Outcome: | The proposed dataset bridges LLMs and complex biological sequence-related tasks while maintaining conversational fluency. |
OptiCo: Adaptive Distributed Training Optimization via Collaborative Agent Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing distributed training frameworks are plagued by over-reliance on prior profiling and poor generalization across models/hardware. |
| Approach: | They propose a model-driven multi-agent framework that leverages Large Language Models to enable automatic and explainable distributed training strategy configuration. |
| Outcome: | The proposed framework outperforms expert-designed training strategies within 20 iterations. |
DrAgent: Empowering Large Language Models as Medical Agents for Multi-hop Medical Reasoning (2025.findings-emnlp)
Copied to clipboard
Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xin Liu, Zhengyang Wang, Xianfeng Tang, Shiyang Li, Xiang He, Ruijie Wang, Bing Yin, Xiao Gu, Lei Clifton, David A. Clifton
| Challenge: | commercial LLMs can be difficult to use in real-world clinical decision-making . a lightweight LLM can be used to collaborate with diverse clinical tools . |
| Approach: | They propose a lightweight LLM that can be used to build medical LLMs as agents . they use recursive curriculum learning to optimize the LLM in an easy-to-hard progression . |
| Outcome: | The proposed approach outperforms human experts in medical examinations on diverse datasets. |
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval (2024.emnlp-industry)
Copied to clipboard
Xin Zhang, Yanzhao Zhang, Dingkun Long, Wen Xie, Ziqi Dai, Jialong Tang, Huan Lin, Baosong Yang, Pengjun Xie, Fei Huang, Meishan Zhang, Wenjie Li, Min Zhang
| Challenge: | Existing models for text retrieval are based on a multi-stage process that involves retrieving documents from a large corpus. |
| Approach: | They propose to build a multilingual text representation model and a cross-encoder reranker from scratch for text retrieval. |
| Outcome: | The proposed models outperform the state-of-the-art models on long-context retrieval benchmarks. |
LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)
Copied to clipboard
Jian Yang, Wei Zhang, Shuyue Guo, Yizhi LI, Linzheng Chai, Zhengmao Ye, Shukai Liu, Yuyang Song, Jiajun Wu, Che Liu, Tianyu Zheng, Siwei Wu, Leo L, Xudong Ma, Chuan Hao, Ran Tao, Yan Xing, Jianzhou Wang, Mingjie Tang, Aishan Liu, Zhoujun Li, Xianglong Liu, Weifeng Lv, Bryan Dai
| Challenge: | Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge. |
| Approach: | They propose a recurrent inductive bias that aligns with the recursive nature of programming logic. |
| Outcome: | The proposed model achieves comparable performance to standard dense models with more parameters. |
Effective Distillation of Table-based Reasoning Ability from LLMs (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing work on table-based reasoning distillation has focused on smaller models with limited performance. |
| Approach: | They propose a table-based reasoning distillation approach to distill LLMs into smaller models . their results show that a 220 million parameter model fine-tuned using distilled data improves performance . |
| Outcome: | The proposed model improves on a scientific table-to-text generation dataset and surpasses specific LLMs. |
Understanding GUI Agent Localization Biases through Logit Sharpness (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal large language models often exhibit hallucinations that compromise reliability . despite promising performance, these models often display systematic localization errors . |
| Approach: | They propose a framework that categorizes model predictions into four distinct types . they propose metric that evaluates alignment between semantic continuity and logits distribution . |
| Outcome: | The proposed framework categorizes model predictions into four different types . it reveals nuanced failure modes beyond traditional accuracy metrics . |
SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale (2022.emnlp-industry)
Copied to clipboard
Raphael Tang, Karun Kumar, Gefei Yang, Akshat Pandey, Yajie Mao, Vladislav Belyaev, Madhuri Emmadi, Craig Murray, Ferhan Ture, Jimmy Lin
| Challenge: | End-to-end automatic speech recognition systems require thousands of hours of manual annotation and heavyweight computation to perform inference. |
| Approach: | They propose to use a third-party ASR system as a weak supervision source and labeling functions derived from implicit user feedback to reduce human labor. |
| Outcome: | The proposed system improves word-error rate and speed up 600% over third-party ASR. |
Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)
Copied to clipboard
Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu
| Challenge: | Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature. |
| Approach: | They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management. |
| Outcome: | The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench. |
Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models (2026.findings-acl)
Copied to clipboard
Hoang Phan, Xianjun Yang, Yuanshun Yao, Jingyu Zhang, Shengjie Bi, Xiaocheng Tang, Madian Khabsa, Lijuan Liu, Deren Lei
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning . however, the recipe introduces a significant risk of capability regression, where models forget foundational skills after prolonged training without employing regularization strategies. |
| Approach: | They propose a replay strategy with dynamic objective reweighting for general knowledge preservation using short-horizon signals of convergence and instability. |
| Outcome: | The proposed method preserves general capabilities and improves reasoning . it can be applied to existing RLVR pipelines without training additional models or tuning . |
Evaluating and Aligning Human Economic Risk Preferences in LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly used in decision-making scenarios that involve risk assessment, yet their alignment with human economic rationality remains unclear. |
| Approach: | They propose an evaluation metric called Risk Disparity Score (RDS) and assess whether LLM-generated responses reflect appropriate levels of risk aversion or risk-seeking behavior based on individual’s persona. |
| Outcome: | The proposed evaluation metric assesses whether LLM-generated responses reflect appropriate levels of risk aversion or risk-seeking behavior based on individual’s persona. |
TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition (2025.acl-long)
Copied to clipboard
Tianwei Lin, Jiang Liu, Wenqiao Zhang, Yang Dai, Haoyuan Li, Zhelun Yu, Wanggui He, Juncheng Li, Jiannan Guo, Hao Jiang, Siliang Tang, Yueting Zhuang
| Challenge: | Existing methods for fine-tuning are resource-efficient, but performance often falls short . a new approach, TeamLoRA, integrates collaborative and competitive modules to improve performance. |
| Approach: | They propose to introduce task-specific LoRA as domain experts to improve learning efficiency . teamLoRA integrates collaborative and competition modules to improve model learning . |
| Outcome: | Experiments show that TeamLoRA improves performance in multi-task learning . teamLorea integrates collaborative and competitive modules to improve performance . |
Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for extending the maximum context lengths of language models are lacking a strong baseline for in-context few-shot classification and on more challenging Chain-of-Thought reasoning, such as HotpotQA, deteriorate question miscomprehension and false inference. |
| Approach: | They propose to harness window-wise attention and positional embedding techniques to extend the maximum context lengths of language models. |
| Outcome: | The proposed method is able to extend the maximum context lengths of language models, e.g., 2048 for LLaMA, by harnessing window-wise attention and positional embedding techniques. |
Parameter-Efficient Tuning Makes a Good Classification Head (2022.emnlp-main)
Copied to clipboard
| Challenge: | In recent years, pretrained models revolutionized the paradigm of natural language understanding . but the final-layer output of the backbone, i.e. the input of the classification head, will change greatly during finetuning . |
| Approach: | They propose to append a randomly initialized classification head after the pretrained backbone and finetune the whole model. |
| Outcome: | The proposed classification head can be replaced with the randomly initialized heads for a stable performance gain. |
GLM: General Language Model Pretraining with Autoregressive Blank Infilling (2022.acl-long)
Copied to clipboard
| Challenge: | Existing pretraining frameworks do not perform well for all tasks of three main categories, such as natural language understanding (NLU), unconditional generation, and conditional generation. |
| Approach: | They propose a general language model based on autoregressive blank infilling to address this challenge. |
| Outcome: | The proposed model outperforms BERT, T5, and GPT on a wide range of tasks across NLU, conditional and unconditional generation tasks. |
Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation metrics struggle to evaluate adversarial negative examples . existing metrics struggle in handling adversarials, resulting in low correlations with human judgments. |
| Approach: | They propose a framework that integrates AMR and domain-specific language models for automatic open-domain dialogue evaluation. |
| Outcome: | The proposed evaluation framework achieves strong correlations with human judgments across multiple datasets. |
Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, including instruction following, mathematical problem solving, and coding generation. |
| Approach: | They propose a method that truncates both preferred and dispreferred responses to match the shorter one’s length. |
| Outcome: | The proposed approach improves over standard implementations and achieves 11.8 points in AlpacaEval 2 and overall improvements across downstream tasks. |
Asking Clarification Questions in Knowledge-Based Question Answering (D19-1)
Copied to clipboard
| Challenge: | Existing clarification datasets with limited annotated examples do not address ambiguous phenomena. |
| Approach: | They propose a dataset that allows users to ask clarification questions using open-domain examples. |
| Outcome: | The proposed model achieves better performance than strong baselines and provides new challenges. |
RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotations (2025.findings-acl)
Copied to clipboard
| Challenge: | Lack of human preference labels remains a significant bottleneck when applying RLHF to a downstream domain. |
| Approach: | They propose a method that leverages human priors encoded in Knowledge Graphs (KGs) to derive RL rewards in the absence of manual annotations. |
| Outcome: | Experiments on three public and one private medical dialogue datasets show that the proposed method outperforms the competitive RLAIF in improving LLM diagnostic accuracy. |
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining (2026.acl-long)
Copied to clipboard
Jiandong Shao, Raphael Tang, Crystina Zhang, Karin Sevegnani, Pontus Stenetorp, Jianfei Yang, Yao Lu
| Challenge: | Existing research suggests that multilingual large language models can achieve impressive cross-lingual understanding despite largely monolingual pretraining. |
| Approach: | They compare a monolingual-only corpus with a standard web corpus that removes all multilingual documents and then retrain the models from scratch under controlled conditions. |
| Outcome: | The results show that removing bilingual data causes translation performance to drop 56% in BLEU, whereas code-switching contributes minimally. |
Revealing the Numeracy Gap: An Empirical Investigation of Text Embedding Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Text embedding models are widely used in natural language processing but are often benchmarked on tasks that do not require understanding nuanced numerical information in text. |
| Approach: | They evaluate 13 widely used text embedding models and find they struggle to capture numerical details accurately. |
| Outcome: | The proposed models struggle to capture nuanced numerical details accurately, despite being benchmarked on tasks that do not require understanding nuance. |
FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging (2025.acl-long)
Copied to clipboard
Zichen Tang, Haihong E, Ziyan Ma, Haoyang He, Jiacheng Liu, Zhongjun Yang, Zihua Rong, Rongjin Li, Kun Ji, Qing Huang, Xinyang Hu, Yang Liu, Qianhe Zheng
| Challenge: | Compared to existing benchmarks, FinanceReasoning provides three key advancements: (1) credibility; (2) comprehensiveness; (3) numerical precision; (4) complexity; (5) complexity; and (6) complexity. |
| Approach: | They propose a benchmark to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems. |
| Outcome: | The proposed benchmark exceeds existing benchmarks in 67.8% of financial concepts and formulas and is credible, comprehensive, and challenging. |
HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for medical vision-language models overlook modality misalignment . HSCR generates high-quality preference data with higher sampling probability . |
| Approach: | They propose a hierarchical self-contrastive reward approach that addresses two challenges in alignment . they leverage the inherent capability of Med-VLMs to generate dispreferred responses . |
| Outcome: | The proposed approach improves accuracy and trustworthiness of medical vision-label models with 2,000 training entries. |
Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LLM-based agents lack inherent spatial awareness, relying on web search or text matching while hallucinating spatial relationships. |
| Approach: | They propose a spatial-based agent that can perform real-world geospatial computations . they use natural-language questions to parse into executable workflows based on geoFlow Graphs - directed acyclic graphs with nodes corresponding to spatial concepts and edges representing transformations. |
| Outcome: | The proposed agent outperforms existing baselines on MapEval-API and MapQA benchmarks while producing interpretable and executable geospatial workflows. |
Beyond Guilt: Legal Judgment Prediction with Trichotomous Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current legal large language models lack trichotomous reasoning capabilities due to the absence of an appropriate benchmark dataset. |
| Approach: | They propose a benchmark dataset for Legal Judgment Prediction with Innocent Verdicts that incorporates trichotomous dogmatics into zero-shot prompting and fine-tuning. |
| Outcome: | The proposed dataset extends three widely-used legal datasets through LLM-based augmentation and manual verification. |
RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing (2025.findings-emnlp)
Copied to clipboard
Hao Xiang, Tianyi Tang, Yang Su, Bowen Yu, An Yang, Fei Huang, Yichang Zhang, Yaojie Lu, Hongyu Lin, Xianpei Han, Jingren Zhou, Junyang Lin, Le Sun
| Challenge: | Existing benchmarks focus on character-centric approach and fail to reflect real-world applications. |
| Approach: | RMTBench is a user-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds. |
| Outcome: | RMTBench features 80 diverse characters and over 8,000 dialogue rounds. |
Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detecting pre-training data in large language models rely on superficial features like prediction confidence and loss, resulting in mediocre performance. |
| Approach: | They propose a new algorithm to analyze neuron activation patterns between training and non-training data in large language models to improve their performance. |
| Outcome: | The proposed algorithm outperforms existing methods across three benchmarks and multiple LLMs. |
FinMTEB: Finance Massive Text Embedding Benchmark (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing text embedding benchmarks for financial domains are inadequately addressing the nuanced requirements of specialized domains like finance. |
| Approach: | They propose a finance-adapted embedding model that outperforms general-purpose models . they also introduce a new model, Fin-E5, which is also open-sourced . |
| Outcome: | The proposed framework outperforms general-purpose models on financial embedding tasks. |
TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization (2024.naacl-long)
Copied to clipboard
Liyan Tang, Igor Shalyminov, Amy Wong, Jon Burnsky, Jake Vincent, Yu’an Yang, Siffi Singh, Song Feng, Hwanjun Song, Hang Su, Lijia Sun, Yi Zhang, Saab Mansour, Kathleen McKeown
| Challenge: | Existing LLMs hallucinate significant amounts of factual errors in the dialogue domain, regardless of the model’s size. |
| Approach: | They propose to evaluate topic-focused dialogue summarization by using large language models (LLMs) they use human annotations to evaluate factual consistency and explain factually inconsistent sentences. |
| Outcome: | The proposed evaluation benchmark on topic-focused dialogue summarization shows that existing LLMs hallucinate significant amounts of factual errors regardless of the model’s size. |
PlotGen-Bench: Evaluating VLMs on Generating Visualization Code from Diverse Plots across Multiple Libraries (2026.findings-acl)
Copied to clipboard
| Challenge: | PlotGen-Bench evaluates vision-language models' ability to generate executable visualization code from plots under realistic and complex visualization requirements. |
| Approach: | They propose a benchmark to evaluate plot-to-code generation in vision-language models . they use Matplot, Matplos, Mat3D, Mat4D, and Mat4E to evaluate their performance . |
| Outcome: | The proposed benchmark covers 9 major categories, 30 subcategories, and 3 core tasks . it covers 2D, 3D and animated plots across 5 widely used visualization libraries. |
RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning (2025.emnlp-industry)
Copied to clipboard
Deyi Ji, Yuekui Yang, Liqun Liu, Peng Shu, Haiyang Wu, Shaogang Tang, Xudong Chen, Shaoping Ma, Tianrun Chen, Lanyun Zhu
| Challenge: | Recent advances in large language models have improved the detection of non-compliant content, but critical gaps persist in fine-grained understanding, explainability, and generalization. |
| Approach: | They propose a framework that combines active reinforcement learning, fine-grained violation understanding and progressive multi-stage training. |
| Outcome: | The proposed framework outperforms general-purpose LLMs and specialized models in fine-grained violation understanding, explainability, and generalization. |
A Boundary Offset Prediction Network for Named Entity Recognition (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a fundamental task in natural language processing . span-based methods assign entity types to text spans, resulting in imbalanced sample space . |
| Approach: | They propose a method that predicts boundary offsets between candidate and nearest spans . the method integrates entity type and span representations to generate type-aware boundary offset . |
| Outcome: | The proposed method outperforms existing methods on eight widely-used NER datasets. |
“Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors (2023.findings-acl)
Copied to clipboard
| Challenge: | Text classification is one of the most fundamental tasks in natural language processing (NLP), but deep neural networks are data-hungry and expensive to train. |
| Approach: | They propose a non-parametric alternative to DNNs that uses a compressor like gzip and a k-nearest-neighbor classifier to achieve competitive results. |
| Outcome: | The proposed method outperforms BERT on all five OOD datasets and outperformed other methods on the few-shot setting. |
CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention (2025.acl-long)
Copied to clipboard
Zekai Ye, Qiming Li, Xiaocheng Feng, Libo Qin, Yichong Huang, Baohang Li, Kui Jiang, Yang Xiang, Zhirui Zhang, Yunfei Lu, Duyu Tang, Dandan Tu, Bing Qin
| Challenge: | Large Vision-Language Models (LVLMs) have impressive multimodal abilities but remain prone to multilingual object hallucination. |
| Approach: | They propose a cross-lingual attention intervention method to mitigate multilingual object hallucination in LVLMs by aligning attention patterns. |
| Outcome: | The proposed method improves 13.56% (up to 30%) on the POPE and 21.75% on the hallucination subsets across languages. |
Multimodal Invariant Sentiment Representation Learning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multimodal sensing ignore significant sentiment distribution imbalances and cross-modal sentiment conflicts, hindering performance improvement. |
| Approach: | They propose a method to learn stable multimodal invariant sentiment representations by incorporating distributional discrepancies and sentiment conflicts into the model training. |
| Outcome: | The proposed method improves MSA performance and achieves new state-of-the-art. |
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. |
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. |
CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Cultural competence is defined as the ability to understand and adapt to multicultural contexts. |
| Approach: | They propose a framework that uses a hierarchical multilingual taxonomy and a Retrieval-Augmented Generation to synthesize culturally relevant question-answer pairs. |
| Outcome: | The proposed framework contains a hierarchical multilingual taxonomy covering 12 primary and 130 secondary topics and a Retrieval-Augmented Generation (RAG)-based methodology leveraging factual knowledge to synthesize culturally relevant question-answer pairs. |
FaithLM: Towards Faithful Explanations for Large Language Models (2026.eacl-long)
Copied to clipboard
Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Ruixiang Tang, Shaochen Zhong, Fan Yang, Andrew Wen, Mengnan Du, Xuanting Cai, Vladimir Braverman, Xia Hu
| Challenge: | Large language models (LLMs) produce natural language explanations, but they lack faithfulness and do not reflect the evidence the model uses to decide. |
| Approach: | They propose a model-agnostic framework that evaluates and improves the faithfulness of LLM explanations without token masking or task-specific heuristics. |
| Outcome: | The proposed framework improves faithfulness of large language models without masking or heuristics. |
Incomplete Utterance Rewriting by A Two-Phase Locate-and-Fill Regime (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing models with incomplete utterances have too large search space, resulting in poor quality of rewriting results. |
| Approach: | They propose a 2-phase rewriting framework which predicts empty slots in the utterance that need to be completed and generates the part to be filled into each position. |
| Outcome: | The proposed framework achieves state-of-the-art results on several public rewriting datasets. |
A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese (2026.tacl-1)
Copied to clipboard
Yikang Liu, Yeting Shen, Hongao Zhu, Lilong Xu, Zhiheng Qian, Siyuan Song, Kejia Zhang, Jialong Tang, Pei Zhang, Baosong Yang, Rui Wang, Hai Hu
| Challenge: | Using sub-linear length normalized log-probabilities (SLLN-LP), we find unequal lengths of sentences in minimal pairs difficult for LMs even up to 32B parameters. |
| Approach: | They propose to use ZhoBLiMP as a linguistic minimal pair benchmark for Chinese language models to mitigate biases. |
| Outcome: | The proposed metric mitigates biases in Chinese language models with over 100 paradigms . Anaphor, Quantifiers, and Ellipsis are difficult for LMs even up to 32B parameters . |
SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to evaluate open domain dialogues have a one-to-many problem . existing approaches lack commonsense reasoning biases and perform poorly in domain-specific scenarios. |
| Approach: | They propose a framework that leverages both a small, specialised model and LLMs for the evaluation of open-domain dialogues. |
| Outcome: | The proposed framework achieves state-of-the-art performance in both classification and evaluation tasks and exhibits better correlation with human judgements. |
Think Outside the Policy: In-Context Steered Policy Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing Reinforcement Learning from Verifiable Rewards (RLVR) methods exhibit limited exploration due to reliance on on-policy rollouts which are limited to the current policy’s distribution, resulting in narrow trajectory diversity. |
| Approach: | They propose a framework that leverages the in-context learning capability of Large Reasoning Models to provide expert guidance using existing datasets. |
| Outcome: | The proposed framework improves RLVR performance and training stability on mathematical reasoning benchmarks. |
Tuning Less, Prompting More: In-Context Preference Learning Pipeline for Natural Language Transformation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to natural language transformation (NLT) tasks face significant challenges, such as the computational costs of leveraging large pre-trained models and the limited generalization ability of fine-tuned smaller models. |
| Approach: | They propose a framework that combines prompting with fine-tuning to enhance smaller models by integrating In-Context Examples from retrieval. |
| Outcome: | The proposed framework outperforms existing methods across MT and TST tasks. |
ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition (2026.findings-acl)
Copied to clipboard
Yujie Liu, Zonglin Yang, Tong Xie, Jinjie Ni, Ben Gao, Yuqiang Li, Shixiang Tang, Wanli Ouyang, Erik Cambria, Dongzhan Zhou
| Challenge: | Large language models have shown potential in assisting scientific research, yet their ability to discover high-quality research hypotheses remains unexamined due to the lack of a dedicated benchmark. |
| Approach: | They propose a benchmark for evaluating large language models on a sufficient set of scientific discovery sub-tasks. |
| Outcome: | The proposed framework extracts critical components from papers across 12 disciplines with expert validation confirming its accuracy. |
Language Constrained Multimodal Hyper Adapter For Many-to-Many Multimodal Summarization (2025.acl-long)
Copied to clipboard
| Challenge: | Existing models that share parameters neglect the language-specific knowledge learning. |
| Approach: | They propose a language-constrained multimodal hyper adapter for multimodal summarization that integrates language-specific adapters into multilingual pre-trained backbones. |
| Outcome: | The proposed model can generate summaries based on multimodal documents such as text and visuals, allowing people to quickly locate key information from the vast multimedia con. |
What the DAAM: Interpreting Stable Diffusion Using Cross Attention (2023.acl-long)
Copied to clipboard
Raphael Tang, Linqing Liu, Akshat Pandey, Zhiying Jiang, Gefei Yang, Karun Kumar, Pontus Stenetorp, Jimmy Lin, Ferhan Ture
| Challenge: | a new text-image attribution analysis model for text-to-image generation is understudied due to ethical constraints . corporators have restricted the general public from using the models and their weights . |
| Approach: | They perform a text-image attribution analysis on Stable Diffusion, a recently open-sourced model. |
| Outcome: | The proposed method achieves a competitive 58.8-64.8 mIoU on noun segmentation and fair to good mean opinion scores on all parts of speech rated by humans . it also achieves good attribution quality on all part of speech, rated in humans - and the first to interpret large diffusion models from a visuolinguistic perspective. |
Are Large Language Models (LLMs) Good Social Predictors? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies suggest that Large Language Models can generate human-like responses, but it is unclear how well they work and where the plausible predictions derive from. |
| Approach: | They propose to use LLMs to generate human-like responses by mutability and accessibility of social inputs to perform a social prediction task. |
| Outcome: | The proposed model performs well in three realistic settings and a novel social prediction task. |
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. |
Specialization through Collaboration: Understanding Expert Interaction in Mixture-of-Expert Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) based large language models are popular for multitasking . however, whether each expert can specialize to a task remains unclear . |
| Approach: | They propose to use a dictionary learning approach to analyze expert collaboration mechanisms in MoE LLMs. |
| Outcome: | The proposed model outperforms existing methods by 2.5% while enabling 50% expert reduction. |
LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing (2026.findings-acl)
Copied to clipboard
Hao Li, Yiqun Zhang, Zhaoyan Guo, Chenxu Wang, Shengji Tang, Qiaosheng Zhang, Yang Chen, Biqing Qi, Peng Ye, Lei Bai, Zhen Wang, Shuyue Hu
| Challenge: | Large language model (LLM) routing assigns each query to the best suitable model from an ensemble. |
| Approach: | They introduce a large-scale benchmark and unified framework for LLM routing . they find that many routing methods exhibit similar performance under unified evaluation . |
| Outcome: | The proposed benchmark provides comprehensive metrics for both performance-oriented and performance-cost trade-off routing. |
Incorporating Contextual and Syntactic Structures Improves Semantic Similarity Modeling (D19-1)
Copied to clipboard
| Challenge: | Semantic similarity modeling is central to many NLP problems such as question answering. |
| Approach: | They propose a pairwise word interaction model with syntactic structure priors to explore their effectiveness. |
| Outcome: | Extensive evaluations on eight benchmark datasets show that incorporating structural information improves over strong baselines. |
DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation (2025.findings-acl)
Copied to clipboard
Xinglin Lyu, Wei Tang, Yuang Li, Xiaofeng Zhao, Ming Zhu, Junhui Li, Yunfei Lu, Min Zhang, Daimeng Wei, Hao Yang, Min Zhang
| Challenge: | Document-level context is crucial for speech translation due to noise from ASR . incorporating document-level contextual information into ST remains a challenge . |
| Approach: | They develop an online framework that integrates document-level context into machine translation . they use document-based modules to integrate document- level context into ST . |
| Outcome: | The proposed framework outperforms baselines in sentence and discourse metrics . it can correct ASR transcription errors and improve translation performance . |
FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding (2022.acl-long)
Copied to clipboard
Yanan Zheng, Jing Zhou, Yujie Qian, Ming Ding, Chonghua Liao, Li Jian, Ruslan Salakhutdinov, Jie Tang, Sebastian Ruder, Zhilin Yang
| Challenge: | Existing evaluation protocols for few-shot natural language understanding (NLU) tasks are inconsistent and hinder fair comparison and measuring progress. |
| Approach: | They propose an evaluation framework that improves previous evaluation procedures in three key aspects, i.e., test performance, dev-test correlation, and stability. |
| Outcome: | The proposed framework improves evaluation procedures in three key aspects, i.e., performance, dev-test correlation, and stability. |
REG: Retrieval via Emotion Similarity for Guiding Empathetic Dialogue Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Empathy relies on the cognitive capacity to relate to similar past experiences. Existing methods prioritize semantic similarity over emotion characteristics, leading to unempathetic responses. |
| Approach: | They propose a framework that integrates four Emotion Attributes into the retrieval process to ensure explicit emotional alignment. |
| Outcome: | Empirical results show that REG significantly outperforms baselines, offering a robust solution for empathetic generation. |
Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference (2025.coling-main)
Copied to clipboard
Lanrui Wang, Jiangnan Li, Chenxu Yang, Zheng Lin, Hongyin Tang, Huan Liu, Yanan Cao, Jingang Wang, Weiping Wang
| Challenge: | Recent studies have focused on integrating commonsense knowledge into chatbots to enhance their ability to understand and generate dialogue responses. |
| Approach: | They propose a framework that integrates commonsense knowledge into chatbots to enable them to elicit more empathetic responses. |
| Outcome: | The proposed framework enables LLMs to uncover the implicit requirements of the conversation, aiming to elicit more empathetic responses. |
Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt Collection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models that assume users to be static, rational agents with fixed preferences fail to capture rich behavioral heterogeneity in real-world debt collection scenarios. |
| Approach: | They propose a public persona-enriched debt collection benchmark that highlights behavioral heterogeneity in negotiation. |
| Outcome: | The proposed benchmark outperforms existing models in realistic scenarios using 16 state-of-the-art LLMs. |
VIRT: Improving Representation-based Text Matching via Virtual Interaction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that representation-based text matching methods suffer from performance degradation due to the lack of interactions between the pair of texts. |
| Approach: | They propose a virtual interaction mechanism that enables deep interaction between texts . they propose 'inteRacTion mechanism' that can be integrated into existing methods as plugins . |
| Outcome: | The proposed method outperforms state-of-the-art models on six text matching benchmarks. |
TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal in-context learning (ICL) is a key mechanism for harnessing the capabilities of large vision–language models. |
| Approach: | They propose a transformer-based model with task-aware attention that dynamically configures ICL sequences. |
| Outcome: | Experiments on five LVLMs and nine datasets show that TACO surpasses baselines across diverse ICL tasks. |
Grammar-Based Patches Generation for Automated Program Repair (2021.findings-acl)
Copied to clipboard
| Challenge: | Automated program repair (APR) aims to find an automatic solution to program language bugs without human intervention. |
| Approach: | They propose a grammar-based rule-rule model which regards the repair process as the transformation of grammar rules and employs a tree-based self-attention approach to guarantee grammar correctness. |
| Outcome: | The proposed model outperforms the state-of-the-art models on a Java dataset in terms of generated code accuracy. |
SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains (2025.naacl-long)
Copied to clipboard
Ran Xu, Hui Liu, Sreyashi Nag, Zhenwei Dai, Yaochen Xie, Xianfeng Tang, Chen Luo, Yang Li, Joyce C. Ho, Carl Yang, Qi He
| Challenge: | Retrieval-augmented generation (RAG) enhances the question answering abilities of large language models (LLMs) however, adapting general-purpose RAG systems to specialized fields poses unique challenges due to distribution shifts and limited access to domain-specific data. |
| Approach: | They propose a method that equips large language models with joint capabilities of question answering and question generation for domain adaptation. |
| Outcome: | Experiments on 11 datasets across three different domains verify the efficacy of SimRAG over baselines by 1.2%–8.6%. |
NOTA: Multimodal Music Notation Understanding for Visual Large Language Model (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing general-domain visual language models lack ability of music notation understanding . Symbolic music is represented in two distinct forms: auditory music and symbolic music . |
| Approach: | They propose to train a multimodal music notation model using a large-scale dataset . they use cross-modal alignment to train the model for music notations analysis . |
| Outcome: | The proposed model improves on music understanding by training with a multimodal music notation model. |
MSCFFN: A New FFN with Multi-Space Cross to Accelerate Transformer (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models to reduce computation complexity are limited in some areas . a new structure to reduce the computation complexity is proposed to accelerate Transformers . |
| Approach: | They propose a new feed forward network structure which splits matrix space to smaller space to reduce computation complexity. |
| Outcome: | The proposed model can achieve a faster speed and better accuracy on the long-range arena benchmark. |
MultiAgentBench : Evaluating the Collaboration and Competition of LLM agents (2025.acl-long)
Copied to clipboard
Kunlun Zhu, Hongyi Du, Zhaochen Hong, Xiaocheng Yang, Shuyi Guo, Zhe Wang, Zhenhailong Wang, Cheng Qian, Robert Tang, Heng Ji, Jiaxuan You
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition. |
| Approach: | They propose a benchmark to evaluate LLM-based multi-agent systems across diverse, interactive scenarios. |
| Outcome: | The proposed framework measures task completion and quality of collaboration and competition using novel, milestone-based key performance indicators. |
Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to RLVR train LMs based on their own on-policy responses and are constrained by the initial capability of LM. |
| Approach: | They propose an approach that hints LMs with their self-made mistakes without external guidance. |
| Outcome: | The proposed approach outperforms the normal group relative policy optimization and requires no external guidance. |
Cognitive Graph for Multi-Hop Reading Comprehension at Scale (P19-1)
Copied to clipboard
| Challenge: | a new framework for multi-hop reading comprehension question answering is needed to cross the chasm of reading comprehension between machine and human. |
| Approach: | They propose a CogQA framework for multi-hop reading comprehension question answering in web-scale documents that builds a cognitive graph in an iterative process by coordinating an implicit extraction module and an explicit reasoning module. |
| Outcome: | The proposed framework outperforms the best competitor in the hotpotQA dataset in F1 . it provides explainable reasoning paths and accurate answers, while giving accurate answers . |
KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Recent work shows that decoder-only LLMs can serve as strong embedding backbones when fine-tuned with contrastive objectives. |
| Approach: | They propose a framework that activates the latent representation power of frozen LLMs by rerouting the final token's KV states as a prepended prefix. |
| Outcome: | The proposed framework outperforms existing training-free baselines by 10% on MTEB and maintains robust performance on sequences up to 4,096 tokens. |
Enhancing Learning-Based Binary Code Similarity Detection Model through Adversarial Training with Multiple Function Variants (2024.findings-emnlp)
Copied to clipboard
Lichen Jia, Chenggang Wu, Bowen Tang, Peihua Zhang, Zihan Jiang, Yang Yang, Ning Liu, Jingfeng Zhang, Zhe Wang
| Challenge: | Existing Learning-Based Binary Code Similarity Detection (LB-BCSD) methods exhibit lower accuracy in recognizing functions with the same functionality but different implementations. |
| Approach: | They propose a gradient-guided adversarial attack method based on critical code called FuncFooler which perturbs critical code to generate multiple variants of the same function. |
| Outcome: | The proposed method increases the accuracy of the current Learning-Based Binary Code Similarity Detection (LB-BCSD) model by 5%-7%. |
Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)
Copied to clipboard
Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang
| Challenge: | Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking. |
| Approach: | They propose an iterative adversarial training method that incorporates three key innovations to address these challenges. |
| Outcome: | Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%. |
Aligning Language Models with Real-time Knowledge Editing (2026.acl-long)
Copied to clipboard
| Challenge: | Mainstream knowledge editing methods are static and fail to keep pace with the evolving real-world knowledge. |
| Approach: | They propose a new paradigm for knowledge editing that integrates edit augmentation and self-adaptive post-alignment inference into CRAFT to improve edit success. |
| Outcome: | The proposed method shows significant performance gain on CRAFT and traditional datasets compared to existing methods. |
TrustAgent: Towards Safe and Trustworthy LLM-based Agents (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing LLMs are primarily used for simple text-related tasks, but LLM-based agents can undertake more complex tasks that require planning and interaction with the physical world and humans. |
| Approach: | They propose an Agent-Constitution-based agent framework with a particular focus on improving the LLM-based agents' safety. |
| Outcome: | The proposed framework can enhance an LLM agent’s safety across multiple domains by identifying and mitigating potential dangers during the planning process. |
EARA: Improving Biomedical Semantic Textual Similarity with Entity-Aligned Attention and Retrieval Augmentation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to measure semantic similarity between biomedical texts are inefficient due to too many biomedically-related entities. |
| Approach: | They propose an entity-aligned, attention-based and retrieval-augmented PLM that aligns the same type of fine-grained entity information in each sentence pair with an entity alignment matrix with an auxiliary loss. |
| Outcome: | The proposed model can achieve state-of-the-art on both in-domain and out-of domain datasets. |
RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completion (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models have strong reasoning, coding, and generation capabilities, but retrieval-augmented generation remains difficult under fixed context budgets. |
| Approach: | They propose a coalition-aware context filtering framework supervised by Shapley-style marginal contributions that captures sign effects via teacher-forced probing and computes exact Shaply values for small retrieval sets. |
| Outcome: | Experiments show that RepoShapley improves completion quality while reducing harmful context and unnecessary retrieval. |
Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition (2026.findings-acl)
Copied to clipboard
| Challenge: | Cloud-hosted Large Language Models (LLMs) offer unmatched reasoning capabilities and dynamic knowledge, yet submitting raw queries to these services can expose sensitive user intent. |
| Approach: | They propose a framework that formulates the trade-off between knowledge utility and privacy as a strategic game. |
| Outcome: | The proposed framework reduces intent leakage while maintaining high-fidelity answer quality. |
Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark (2024.emnlp-main)
Copied to clipboard
Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xianfeng Tang, Chen Luo, Ming Zeng, Haoming Jiang, Yifan Gao, Priyanka Nigam, Sreyashi Nag, Bing Yin, Yining Hua, Xuan Zhou, Omid Rohanian, Anshul Thakur, Lei Clifton, David Clifton
| Challenge: | Existing studies focus on evaluating large language models in close-ended QA tasks, but many clinical decisions involve answering open-ended questions without pre-set options. |
| Approach: | They construct a benchmark to better understand large language models in the clinic . they use existing datasets to evaluate LLMs in clinical situations . |
| Outcome: | The proposed model outperforms human experts in multiple medical tasks. |
Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets (2026.acl-long)
Copied to clipboard
| Challenge: | Existing mitigation strategies focus on reactively addressing jailbreak incidents after safety guardrails have been compromised. |
| Approach: | They investigate the degradation of safety guardrails through the lens of representation similarity between upstream alignment datasets and downstream fine-tuning tasks. |
| Outcome: | The proposed model reduces harmfulness score by 10.33% when compared to baseline models. |
DataSciBench: An LLM Agent Benchmark for Data Science (2026.findings-acl)
Copied to clipboard
Dan Zhang, Sining Zhoubian, Min Cai, Fengzu Li, Lekang Yang, Wei Wang, Tianjiao Dong, Ziniu Hu, Jie Tang, Yisong Yue
| Challenge: | Existing benchmarks focus on single task, simple evaluation metrics, and readily available ground truth (GT) DataSciBench is built on curated, natural, and challenging prompts with complex evaluation criteria and uncertain GT. |
| Approach: | They propose a benchmark for evaluating Large Language Models in data science that integrates LLM-based self-consistency and human verification to ensure accuracy. |
| Outcome: | The proposed framework outperforms open-source models in all metrics and offers rigorous insights into LLM strengths and weaknesses. |
KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing to retrieve knowledge strictly necessary for answer generation. |
| Approach: | They propose a retrieval-filtering-summarization pipeline that enhances QA coverage by retrieving a broader subgraph likely to contain relevant information. |
| Outcome: | The proposed pipeline surpasses state-of-the-art solutions by about 7% in quality and exceeds GPT-4o (Tool) by 10-21%. |
E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models (2024.findings-acl)
Copied to clipboard
Jinchang Hou, Chang Ao, Haihong Wu, Xiangtao Kong, Zhigang Zheng, Daijia Tang, Chengming Li, Xiping Hu, Ruifeng Xu, Shiwen Ni, Min Yang
| Challenge: | despite the rapid development of Large Language Models, there is no dedicated benchmark for evaluating LLMs in Chinese K-12 education. |
| Approach: | They propose to develop a benchmark specifically tailored for Chinese K-12 education. |
| Outcome: | EVAL is the first evaluation benchmark specifically tailored for Chinese K-12 education. |
Conan-Embedding-v2: Training an LLM from Scratch for Text Embeddings (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies use LoRA to fine-tune existing LLMs, but this is limited by the data and training gap between them and embedding models. |
| Approach: | They propose a new 1.4B-parameter LLM trained from scratch and fine-tuned as a text embedder that integrates embeddings across different languages. |
| Outcome: | The proposed model improves performance on the Massive Text Embedding Benchmark (MTEB) and Chinese MTEB (May 19, 2025). |
Audio-centric Video Understanding Benchmark without Text Shortcut (2025.emnlp-main)
Copied to clipboard
Yudong Yang, Jimin Zhuang, Guangzhi Sun, Changli Tang, Yixuan Li, Peihan Li, Yifan Jiang, Wei Li, Zejun Ma, Chao Zhang
| Challenge: | Recent advances in multimodal large language models (MLLMs) focus on visual abilities, but audio is essential for video understanding. |
| Approach: | They propose an audio-centric video understanding benchmark to evaluate video comprehension capabilities of multimodal LLMs with a particular focus on auditory information. |
| Outcome: | The proposed video understanding benchmarks evaluate video comprehension capabilities of multimodal models with a particular focus on auditory information. |
Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study (2025.coling-main)
Copied to clipboard
Bowen Li, Wenhan Wu, Ziwei Tang, Lin Shi, John Yang, Jinyang Li, Shunyu Yao, Chen Qian, Binyuan Hui, Qicheng Zhang, Zhiyin Yu, He Du, Ping Yang, Dahua Lin, Chao Peng, Kai Chen
| Challenge: | Existing benchmarks focused on simplified or isolated aspects of coding, ignoring the full spectrum of programming challenges. |
| Approach: | They propose a case study that examines the performance of large language models across the entire software development lifecycle with four programming languages, multiple domains, and carefully designed and verified metrics for each task. |
| Outcome: | The proposed model performs across the entire software development lifecycle, including design, environment setup, implementation, acceptance testing, and unit testing. |
Referral Augmentation for Zero-Shot Information Retrieval (2024.findings-acl)
Copied to clipboard
| Challenge: | Referral-augmented retrieval improves zero-shot document retrieval in a variety of tasks . prior work shows sparse models struggle to reconcile with dense models . |
| Approach: | They propose a technique that concatenates document indices with referrals from other documents that cite or link to the given document. |
| Outcome: | The proposed technique outperforms generative text expansion techniques on structured tasks and improves on ACL paper retrieval. |
From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement (2025.emnlp-main)
Copied to clipboard
| Challenge: | Chain-of-Thought reasoning introduces significant inference latency due to its verbosity. |
| Approach: | They propose a framework that leverages token elasticity phenomenon to progressively compress CoTs via multiround refinement. |
| Outcome: | The proposed method achieves an average accuracy improvement of 5.6% over state-of-the-art baselines while reducing CoT length by an average of 47 tokens and significantly lowering latency. |
Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on rationale quality underestimates the importance of CoT distillation, focusing primarily on data quantity, which may result in transferring noisy or incorrect information to the student model. |
| Approach: | They propose a method which can discern and select high quality rationales for distillation and a Rationale Difficulty metric to measure the ability of the student model to generate the correct answer under a given rationale. |
| Outcome: | The proposed method achieves 4.6% accuracy improvement over baseline data on seven datasets over three tasks, controlling accuracy, diversity, and difficulty. |
HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level (2023.acl-long)
Copied to clipboard
Haoran Luo, Haihong E, Yuhao Yang, Yikai Guo, Mingzhi Sun, Tianyu Yao, Zichen Tang, Kaiyang Wan, Meina Song, Wei Lin
| Challenge: | Existing research on HKGs rarely models the graphical and sequential structure of HKG, limiting their representation. |
| Approach: | They propose a Hierarchical Attention model for HKG Embedding that includes global-level and local-level attention to model the graphical structure of HKGs. |
| Outcome: | The proposed model achieves state-of-the-art performance on HKG standard datasets and addresses the issue of HKG multi-position prediction for the first time. |
Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering (2026.acl-long)
Copied to clipboard
Shuliang Liu, Songbo Yang, Dong Fang, Sihang Jia, Yuqi Tang, Lingfeng Su, Ruoshui Peng, Yibo Yan, Xin Zou, Xuming Hu
| Challenge: | Existing approaches to overcome object hallucination are limited . Existing mitigations include costly retraining and a training-free inference framework . |
| Approach: | They propose a training-free inference framework that simulates a metacognitive self-correction process. |
| Outcome: | The proposed framework reduces object hallucination rates by 12.67% on MMHal-Bench and improves accuracy by 5.8% on POPE. |
GraphAgent: Agentic Graph Language Assistant (2025.emnlp-main)
Copied to clipboard
| Challenge: | Real-world data combines structured and unstructured formats, capturing explicit relationships and implicit semantic interdependencies. |
| Approach: | They propose GraphAgent, an automated agent pipeline addressing both explicit and implicit graph-enhanced semantic dependencies for predictive and generative tasks. |
| Outcome: | Extensive experiments on diverse datasets validate GraphAgent’s effectiveness in graph-related predictive and text generative tasks. |
Proxy-Driven Robust Multimodal Sentiment Analysis with Incomplete Data (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on optimizing model structures to handle uncertain missingness, but models still face challenges when dealing with uncertain missing data. |
| Approach: | They propose a data-centric robust multimodal sentiment analysis method, Proxy-Driven Robust Multimodal Fusion, which maps unimodal data to the latent space of Gaussian distributions to capture core features and structure. |
| Outcome: | The proposed method outperforms existing models in noise resistance and achieves state-of-the-art performance on multiple benchmark datasets. |
The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks to evaluate LLMs' capabilities are inadequate for assessing their musical capabilities. |
| Approach: | They propose to use a large-scale music benchmark specifically designed to evaluate the music-related capabilities of large language models (LLMs). |
| Outcome: | The proposed framework evaluates 16 large language models in the domain of music. |
OASIS: Mitigating Harmful Fine-tuning Attacks on LLMs via Orthogonal and Adaptive Safety Alignment Strategy (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to decouple safety enforcement from harmful feature acquisition rely on perturbation directions that conflict with harmful gradients . harmful fine-tuning attacks pose a significant challenge for service providers aiming to uphold rigorous safety standards. |
| Approach: | They propose an orthogonal and ad hoc safety alignment strategy to decouple safety enforcement from harmful feature acquisition. |
| Outcome: | Experiments on four large language models show that OASIS reduces the Harmful Score by 60% compared to baselines while maintaining stable task utility. |
Exploring the Relationship between In-Context Learning and Instruction Tuning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | In-Context Learning (ICL) and Instruction Tuning (IT) are two primary paradigms of adopting Large Language Models (LLMs) to downstream applications, but they are significantly different. |
| Approach: | They examine how the hidden states of Large Language Models change in these two paradigms by examining how they differ in implementation. |
| Outcome: | The proposed model changes the hidden states of LLMs as if its accompanying demonstrations were used to instructionally tune the model. |
Multilingual Knowledge Graph Completion with Language-Sensitive Multi-Graph Attention (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to multilingual knowledge graph completion have two drawbacks: alignment dependency and training inefficiency. |
| Approach: | They propose a multilingual knowledge graph completion framework with language-sensitive multi-graph attention to predict missing links on all given KGs. |
| Outcome: | The proposed model improves on the DBP-5L and E-PKG datasets. |
SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods focus on single-step reasoning, ignoring logical dependencies between steps. |
| Approach: | They propose a method that maximizes a structure-based return to facilitate structured reasoning and explanation. |
| Outcome: | The proposed method outperforms state-of-the-art methods on EntailmentBank and STREET benchmarks. |
Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering (2025.findings-acl)
Copied to clipboard
Zheng Chu, Huiming Fan, Jingchang Chen, Qianyu Wang, Mingda Yang, Jiafeng Liang, Zhongjie Wang, Hao Li, Guo Tang, Ming Liu, Bing Qin
| Challenge: | Large language models (LLMs) have demonstrated remarkable reasoning capabilities, but they still face challenges in knowledge-intensive multi-hop reasoning. |
| Approach: | They propose a method that uses self-critique feedback to guide iterative reasoning by enabling iteration and self-evaluation of its intermediate reasoning steps. |
| Outcome: | The proposed method surpasses the previous SOTA by 8.6% on three multi-hop reasoning datasets. |
Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese (2025.emnlp-main)
Copied to clipboard
Yikang Liu, Wanyang Zhang, Yiming Wang, Jialong Tang, Pei Zhang, Baosong Yang, Fei Huang, Rui Wang, Hai Hu
| Challenge: | Translationese is a linguistic property that is often introduced in the translation process that is different from those of original texts. |
| Approach: | They propose to use synthesized translations and translations in the wild to evaluate T-index's generalizability in cross-domain settings and its validity against human judgments. |
| Outcome: | The proposed measure can generalize to unseen genres, authors, and language pairs. |
SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training (2024.acl-long)
Copied to clipboard
| Challenge: | Current methods focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication. |
| Approach: | They propose a method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness. |
| Outcome: | The proposed method significantly improves training efficiency on deduplicated datasets and improves downstream accuracy by 1.77%. |
When 20 Agents Fail to Sort: The Distributed Sorting Benchmark for Scalable Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
| Challenge: | MAS-BENCH isolates coordination under explicit communication constraints . CAMOC significantly improves coordination success and efficiency across backends . |
| Approach: | They propose a distributed-sorting benchmark that isolates coordination under explicit communication constraints. |
| Outcome: | MAS-BENCH improves coordination success and efficiency across backends . CAMOC significantly improves efficiency under shared-state interaction . |
FLARE: Task-Agnostic Embedding Model Evaluation via Normalizing Flows (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods based on kernel estimators or Gaussian mixtures fail to model high-dimensional distributions effectively, resulting in unstable rankings. |
| Approach: | They propose a method which uses normalizing flows to estimate information sufficiency in high-dimensional spaces by learning invertible transformations. |
| Outcome: | Experiments on 11 datasets show that FLARE achieves a strong Spearman’s (up to 0.90) with supervised benchmarks, remaining robust even for high-dimensional embeddings (d 3,584). |
Text2Mem: A Unified Memory Operation Language for Memory Operating System (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing memory frameworks lack a formal, executable specification for memory control. |
| Approach: | They propose a unified memory operation language that standardizes translation of natural-language instructions into reliable execution. |
| Outcome: | The proposed language standardizes translation of natural-language instructions into reliable execution. |
DaNet: Dual-Aware Enhanced Alignment Network for Multimodal Aspect-Based Sentiment Analysis (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods assume a direct alignment between images and aspects, matching the entire image with a corresponding aspect. Existing algorithms assume 'direct alignment' between images, introducing noise. |
| Approach: | They propose a Dual-Aware Enhanced Alignment Network (DaNet) that can enhance fine-grained multimodal aspect-image alignment and denoising. |
| Outcome: | The proposed system outperforms existing methods in three subtasks and is available on https://github.com/***/DaNet. |
DenseSSM: State Space Models with Dense Hidden Connection for Efficient Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) face excessive computational and memory requirements due to the commonly used Transformer architecture. |
| Approach: | They propose a method to enhance the flow of hidden information between layers in large language models by selectively integrating shallow-layer hidden states into deeper layers. |
| Outcome: | The proposed method maintains parallelizability and inference efficiency of SSMs while significantly boosting performance on public benchmarks. |
Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent work on Chain-of-Thought prompting imposes substantial computational overhead . lack of supervision obscures the analyzability of the latent reasoning chain. |
| Approach: | They propose a framework to render latent reasoning chain into images, making latent rationale explicit and traceable. |
| Outcome: | The proposed framework achieves 3-4 token compression and substantial inference acceleration compared to explicit CoT prompting. |
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios (2025.findings-acl)
Copied to clipboard
Xiaokang Zhang, Sijia Luo, Bohan Zhang, Zeyao Ma, Jing Zhang, Yang Li, Guanlin Li, Zijun Yao, Kangli Xu, Jinchang Zhou, Daniel Zhang-Li, Jifan Yu, Shu Zhao, Juanzi Li, Jie Tang
| Challenge: | TableLLM is a robust large language model capable of handling tabular data manipulation tasks. |
| Approach: | They propose a distant supervision method for training which includes a reasoning process extension strategy and a cross-way validation strategy. |
| Outcome: | The proposed model has 8 billion parameters and is capable of handling tabular data tasks. |
AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)
Copied to clipboard
Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E
| Challenge: | AEGIS examines whether current models can effectively audit AI-generated images in academic papers. |
| Approach: | They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics. |
| Outcome: | AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis. |
Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework (2025.findings-emnlp)
Copied to clipboard
Bohao Yang, Dong Liu, Chenghao Xiao, Kun Zhao, Chen Tang, Chao Li, Lin Yuan, Yang Guang, Chenghua Lin
| Challenge: | Large Language Models (LLMs) are capable of generating human-like text, but the potential for freely customisable characters remains underexplored. |
| Approach: | They propose a framework which employs Large Language Models to create freely customisable characters through personalised characteristic feature injection. |
| Outcome: | The proposed framework provides valuable insights for developing more accurate and customisable human simulacra. |
Towards Knowledge-Based Recommender Dialog System (D19-1)
Copied to clipboard
| Challenge: | Existing frameworks that only provide information about user preferences can be inaccurate in e-commerce recommender systems. |
| Approach: | They propose a framework which integrates the recommender system and dialog generation system by introducing information about users’ preferences. |
| Outcome: | The proposed framework can achieve better performance in both dialog generation and recommendation compared with baselines. |
ChatMatch: Evaluating Chatbots by Autonomous Chat Tournaments (2022.acl-long)
Copied to clipboard
| Challenge: | Existing automated evaluation systems of chatbots rely on static chat scripts as ground truth, which is hard to obtain. |
| Approach: | They propose an interactive chatbot evaluation framework that allows chatbots to compete with each other like in a sports tournament. |
| Outcome: | The proposed framework can rank chatbots independently from their model architectures and domains . existing evaluation systems rely on static chat scripts as ground truth . |
Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning (2026.acl-long)
Copied to clipboard
Junpeng Ding, Zichen Tang, Haihong E, Mengyuan Ji, Yang Liu, Haolin Tian, Haiyang Sun, Pengqi Sun, Yang Xu, Yichen Liu, Haocheng Gao, Zijie Xi, Ruomeng Jiang, Peizhi Zhao, Rongjin Li, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Jintong Chen, Siying Lin
| Challenge: | Xu and Peng, 2025) . . SPUR is a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images. |
| Approach: | They propose to use 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images to evaluate the visual perception of multimodal large language models (MLLMs) . they also propose to utilize cross-panel relation understanding to evaluate MLLM’s ability to decipher intricate cross-panel relations. |
| Outcome: | The proposed model is based on 4,264 question-answering pairs derived from 1,084 expert-curated images. |
CharacterGLM: Customizing Social Characters with Large Language Models (2024.emnlp-industry)
Copied to clipboard
Jinfeng Zhou, Zhuang Chen, Dazhen Wan, Bosi Wen, Yi Song, Jifan Yu, Yongkang Huang, Pei Ke, Guanqun Bi, Libiao Peng, JiaMing Yang, Xiyao Xiao, Sahand Sabour, Xiaohan Zhang, Wenjing Hou, Yijia Zhang, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang
| Challenge: | Character-based dialogue systems (CharacterDial) allow users to customize social characters for social interactions. |
| Approach: | They will collect a large-scale Chinese corpus of characters with diverse categories and behaviors and develop CharacterGLM models to address these challenges. |
| Outcome: | Experiments show that CharacterGLM outperforms most popular open- and closed-source LLMs and performs comparable to GPT-4. |
Compare to The Knowledge: Graph Neural Fake News Detection with External Knowledge (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fake news detection rely on linguistic and semantic features from news content and do not exploit external knowledge. |
| Approach: | They propose a graph neural model which compares news to knowledge base through entities for fake news detection. |
| Outcome: | The proposed model significantly outperforms state-of-the-art methods on two benchmark datasets. |
Human-Agent Collaborative Paper-to-Page Crafting (2026.findings-acl)
Copied to clipboard
Qianli Ma, Siyu Wang, Chen Yilin, Yinhao Tang, Yixiang Yang, Chang Guo, Bingjie Gao, Zhening Xing, Yanan Sun, Zhipeng Zhang
| Challenge: | Existing approaches to create project pages from academic papers have focused on static slides and posters, but the dynamic nature of webpages remains an unaddressed challenge. |
| Approach: | They propose a novel multi-agent system that deconstructs paper-to-page creation into a coarse-to fine pipeline from narrative planning to multimodal content generation and interactive rendering. |
| Outcome: | The proposed system generates high-quality, visually appealing pages in under 15 minutes for less than $0.1 . |
Learning to Correct Noisy Labels for Fine-Grained Entity Typing via Co-Prediction Prompt Tuning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that noise correction in fine-grained entity typing improves quality of training samples. |
| Approach: | They propose a method that leverages multiple prediction results to correct noisy labels . they integrate prediction results and utilize a differentiated margin to identify inaccurate labels a . |
| Outcome: | The proposed model improves quality of training samples annotated using distant supervision, ChatGPT, and crowdsourcing. |
Towards Scalable Lightweight GUI Agents via Multi-role Orchestration (2026.findings-acl)
Copied to clipboard
Ziwei Wang, Junjie Zheng, Leyang Yang, Sheng Zhou, Xiaoxuan Tang, Fang Zhouhua, Zhiwei Liu, Dajun Chen, Yong Li, Jiajun Bu
| Challenge: | Advanced GUI agents suffer from prohibitive deployment costs on resource-constrained devices. |
| Approach: | They propose a lightweight GUI agent with GUI-specific knowledge and task scalability . LAMO-3B supports monolithic execution and MAS-style orchestration . |
| Outcome: | The proposed GUI agent LAMO-3B supports monolithic execution and MAS-style orchestration. |
OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)
Copied to clipboard
He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou
| Challenge: | a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say . |
| Approach: | They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible . |
| Outcome: | The proposed framework achieves state-of-the-art performance among open-source projects. |
Learning Dynamic Context Augmentation for Global Entity Linking (D19-1)
Copied to clipboard
Xiyuan Yang, Xiaotao Gu, Sheng Lin, Siliang Tang, Yueting Zhuang, Fei Wu, Zhigang Chen, Guoping Hu, Xiang Ren
| Challenge: | Existing collective entity linking methods are expensive and often lack local context information. |
| Approach: | They propose a dynamic context-augmented inference model that can be used to make collective inference. |
| Outcome: | The proposed model can cope with different local EL models with different learning settings, base models, decision orders and attention mechanisms. |
Chain of Attack: Hide Your Intention through Multi-Turn Interrogation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing jailbreak attacks focus on single-turn dialogue scenarios, leaving vulnerabilities in multi-turn contexts inadequately explored. |
| Approach: | They propose an optimal interrogation principle to conceal the jailbreak intent and introduce a multi-turn attack chain generation strategy called CoA. |
| Outcome: | The proposed method shows that black-box LLMs exhibit insufficient resistance under multi-turn interrogation, with more advantages (ASR, 83% vs 64%) |
Learning Compressed Sentence Representations for On-Device Text Processing (P19-1)
Copied to clipboard
Dinghan Shen, Pengyu Cheng, Dhanasekar Sundararaman, Xinyuan Zhang, Qian Yang, Meng Tang, Asli Celikyilmaz, Lawrence Carin
| Challenge: | Existing methods for learning sentence embeddings assume they are continuous and real-valued. |
| Approach: | They propose four different strategies to transform continuous and generic sentence embeddings into a binarized form while preserving their rich semantic information. |
| Outcome: | The proposed methods reduce storage requirements by over 98% and improve performance on downstream tasks. |
P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks (2022.acl-short)
Copied to clipboard
| Challenge: | Existing methods of prompt tuning cannot handle hard sequence labeling tasks. |
| Approach: | They propose to optimize prompt tuning to tune continuous prompts with a frozen language model. |
| Outcome: | The proposed method matches finetuning with prompt tuning while having only 0.1%-3% tuned parameters. |
High-Quality Dialogue Diversification by Intermittent Short Extension Ensembles (2021.findings-acl)
Copied to clipboard
| Challenge: | Many task-oriented dialogue systems use deep reinforcement learning (DRL) to learn policies that respond to the user appropriately and complete the tasks successfully. |
| Approach: | They propose a method to diversify dialogues using a set of user models by constraining the intensity to interact with diverse user models. |
| Outcome: | The proposed method improves the performance of several state-of-the-art DRL dialogue agents trained in simulators. |
Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning (2025.findings-acl)
Copied to clipboard
Haoyu Han, Yaochen Xie, Hui Liu, Xianfeng Tang, Sreyashi Nag, William Headden, Yang Li, Chen Luo, Shuiwang Ji, Qi He, Jiliang Tang
| Challenge: | Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks, however, they still face challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences. |
| Approach: | They propose to construct explicit graphs from context and leverage them to enhance LLM reasoning performance on reasoning tasks. |
| Outcome: | Extensive experiments show that the proposed method improves both logical reasoning and multi-hop question answering tasks. |
Safe-FedLLM: Delving into the Safety of Federated Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing work on federated learning for large language models (FL) addresses privacy and data-silo issues in the training of large language model training. |
| Approach: | They propose a probe-based defense framework for FedLLM that constructs defenses across three levels: Step-Level, Client-Level and Shadow-Level. |
| Outcome: | The proposed framework improves FedLLM's robustness against malicious clients while maintaining competitive performance on benign data. |
Neural-DINF: A Neural Network based Framework for Measuring Document Influence (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to measure scholarly impact of documents without citations only consider word frequency change. |
| Approach: | They propose a neural network framework that measures document influence without citations by using word frequency changes and word semantic shifts. |
| Outcome: | The proposed model outperforms existing models on document influence evaluation without citations. |
CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation (2025.emnlp-main)
Copied to clipboard
Ziyue Liu, Ruijie Zhang, Zhengyang Wang, Mingsong Yan, Zi Yang, Paul D. Hovland, Bogdan Nicolae, Franck Cappello, Sui Tang, Zheng Zhang
| Challenge: | Large foundation models have become huge, but they consume computational resources in pretraining. |
| Approach: | They propose to replace full-size layers with compute-efficient auto-encoders that enforce low-rank activations throughout training. |
| Outcome: | The proposed method reduces the computing cost by 2pmbtimes and improves training throughput by 1.86pmtime. |
CARE-STaR: Constraint-aware Self-taught Reasoner (2025.findings-acl)
Copied to clipboard
Zhiliang Li, Bo Tang, Yijun Niu, Beihong Jin, Qiwen Shi, Yuchen Feng, Zhiyu Li, Jie Hu, Mingchuan Yang, Feiyu Xiong
| Challenge: | Recent research on instruction following has demonstrated that LLMs can handle complex instructions. |
| Approach: | They propose to assign constraints to different levels of constraints in instructions . they use chain-of-thought and self-taught reasoner methods to identify constraints . |
| Outcome: | The proposed method outperforms supervised fine-tuning (SFT) on three instruction-following benchmarks. |
BaseCal: Unsupervised Confidence Calibration via Base Model Signals (2026.acl-long)
Copied to clipboard
Hexiang Tan, Wanli Yang, Junwei Zhang, Xin Chen, Rui Tang, Du Su, Jingang Wang, Yuanzhuo Wang, Fei Sun, Xueqi Cheng
| Challenge: | Post-trained LLMs typically compromise reliability with severe overconfidence, resulting in inaccurate responses. |
| Approach: | They propose a solution that feeds PoLLMs into the base LLM to get confidence. |
| Outcome: | The proposed solution reduces expected calibration error (ECE) by 42.90% compared to the best unsupervised baselines. |
EvoWiki: Evaluating LLMs on Evolving Knowledge (2025.acl-long)
Copied to clipboard
Wei Tang, Yixin Cao, Yang Deng, Jiahao Ying, Bo Wang, Yizhe Yang, Yuyue Zhao, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang, Yong Liao
| Challenge: | Existing knowledge evolution benchmarks are static and fail to capture the evolving nature of LLMs and knowledge. |
| Approach: | They propose an evolving dataset that categorizes information into stable, evolved, and uncharted states. |
| Outcome: | The proposed dataset is auto-updatable and enables evaluation of continuously changing knowledge and newly released LLMs. |
Automated Tone Transcription and Clustering with Tone2Vec (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Lexical tones play a crucial role in Sino-Tibetan languages, but current phonetic fieldwork relies on manual effort. |
| Approach: | They propose a pitch-based similarity representations for tone transcription called Tone2Vec . they propose an open-source package that facilitates automated fieldwork and analysis . |
| Outcome: | Experiments on dialect clustering and variance show that Tone2Vec captures fine-grained tone variation. |
The BQ Corpus: A Large-scale Domain-specific Chinese Corpus For Sentence Semantic Equivalence Identification (D18-1)
Copied to clipboard
| Challenge: | Bank Question corpus is a corpus for sentence semantic equivalence identification (SSEI) because of rich expressions in natural languages, SSEI is really a challenging task. |
| Approach: | They propose to cluster 120,000 question pairs from 1-year online bank custom service logs into stacks by the Word Mover’s Distance (WMD) based Affinity Propagation algorithm to achieve questions with the same intent. |
| Outcome: | The proposed method achieves questions with the same intent by clustering deduplicated questions into stacks by the Word Mover’s Distance (WMD) based Affinity Propagation (AP) algorithm. |
Voice Query Auto Completion (2021.emnlp-main)
Copied to clipboard
Raphael Tang, Karun Kumar, Kendra Chalkley, Ji Xin, Liming Zhang, Wenyan Li, Gefei Yang, Yajie Mao, Junho Shin, Geoffrey Craig Murray, Jimmy Lin
| Challenge: | Existing methods fail to complete voice queries from incomplete prefixes because they use orthographic prefix and substrings instead of the true phonetic prefix. |
| Approach: | They propose to condition QAC approaches on intermediate transcriptions to complete voice queries. |
| Outcome: | The proposed method obtains an 18% relative improvement over previous methods on a speech-enabled smart television with real-life voice search traffic. |
Toward Annotator Group Bias in Crowdsourcing (2022.acl-long)
Copied to clipboard
Haochen Liu, Joseph Thekinen, Sinem Mollaoglu, Da Tang, Ji Yang, Youlong Cheng, Hui Liu, Jiliang Tang
| Challenge: | Annotator group bias is a common problem in crowdsourcing, but is often overlooked . |
| Approach: | They propose a probabilistic framework to capture annotator group bias using an extended Expectation Maximization algorithm. |
| Outcome: | The proposed model can model annotator group bias over competitive datasets and demonstrate that it is effective over multiple datasets. |
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model (2025.acl-long)
Copied to clipboard
Xun Liang, Simin Niu, Zhiyu Li, Sensen Zhang, Hanyu Wang, Feiyu Xiong, Zhaoxin Fan, Bo Tang, Jihao Zhao, Jiawei Yang, Shichao Song, Mengwei Wang
| Challenge: | Existing approaches to integrating external knowledge into large language models (LLMs) however, the incorporation of external knowledge increases the vulnerability of LLMs . |
| Approach: | They propose a benchmark to evaluate the RAG security using a dataset . they classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service . |
| Outcome: | The proposed benchmark evaluates the security of RAG against 14 representative RAG components. |
Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive capabilities but face significant challenges from hallucinations, which arise from insufficient knowledge or context. |
| Approach: | They propose a novel two-stage approach for contextual question answering that enhances LLMs’ ability to recognise their knowledge boundaries while the second reinforces instruction adherence through carefully designed causal prompts. |
| Outcome: | The proposed approach significantly reduces incorrect answers in contextual QA and improves models’ faithfulness to parametric knowledge, mitigating hallucinations in general QA tasks. |
EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing lightweight approaches to retrieval-augmented generation fail to capture latent semantic connections between disjoint entities. |
| Approach: | They propose a lightweight RAG framework that constructs a hypergraph capturing both structure and semantic relationships using a hybrid structural-semantic retrieval mechanism. |
| Outcome: | EHRAG outperforms state-of-the-art methods on four datasets while maintaining zero token consumption. |
ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language Models (2022.naacl-main)
Copied to clipboard
Junyi Li, Tianyi Tang, Zheng Gong, Lixin Yang, Zhuohao Yu, Zhipeng Chen, Jingyuan Wang, Xin Zhao, Ji-Rong Wen
| Challenge: | Recent years have featured a trend towards Transformer based pretrained language models (PLMs) in natural language processing systems. |
| Approach: | They propose to use four evaluation dimensions to evaluate ten widely-used PLMs . they find that pretrained language models are good at different ability tests . |
| Outcome: | The results show that pretrained language models are good at different ability tests and have excellent transferability between tasks. |
Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models (2025.acl-long)
Copied to clipboard
Suhang Wu, Jialong Tang, Chengyi Yang, Pei Zhang, Baosong Yang, Junhui Li, Junfeng Yao, Min Zhang, Jinsong Su
| Challenge: | Existing methods for terminology translation struggle with interference from irrelevant noise. |
| Approach: | They propose a Locate-and-Focus method that locates terminologies within utterances to construct translation knowledge by minimizing irrelevant information for ST models. |
| Outcome: | The proposed method locates terminologies within utterances and enhances the success rate of terminology translation while maintaining robust general translation performance. |
FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text data augmentation are limited to simple tasks and weak baselines. |
| Approach: | They propose a data augmentation method FlipDA that uses a generative model and a classifier to generate label-flipped data. |
| Outcome: | The proposed method improves many tasks while not negatively affecting the others. |