Papers by Kai Zhao
Consistent Representation Learning for Continual Relation Extraction (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to train relation extraction models overfit memory samples and perform poorly on imbalanced datasets. |
| Approach: | They propose a method which uses contrastive learning and knowledge distillation to train a model on data with new relations while avoiding forgetting old ones. |
| Outcome: | The proposed method significantly outperforms state-of-the-art baselines and yields strong robustness on the imbalanced datasets. |
Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are gaining popularity due to their lack of knowledge hallucination and lack of a coherent model. |
| Approach: | They propose a self-supervised quantized representation method to compress KG structural and semantic knowledge into discrete codes that align the format of language sentences. |
| Outcome: | The proposed framework outperforms existing unsupervised methods producing more distinguishable codes on KG link prediction and triple classification tasks. |
Adaptive Policy with Wait-k Model for Simultaneous Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to simultaneous machine translation require a robust read/write policy . a standalone multi-path wait-k model performs competitively with adaptive policies . |
| Approach: | They propose a more flexible approach by decoupling the adaptive policy model from the translation model. |
| Outcome: | The proposed approach outperforms baseline approaches in translation tasks. |
Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Parameter-Efficient Fine-Tuning (PEFT) methods have gained popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks. |
| Approach: | They propose a method to optimize the importance of full layers with layer-wise importance scoring by leveraging the estimated importance scores. |
| Outcome: | The proposed method is compatible with PEFT methods that operate on a per-layer basis and achieves better performance. |
G-LoRA: Global-Local Decoupled Low-Rank Adaptation (2026.findings-acl)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) improves the fine-tuning efficiency and performance of large language models. |
| Approach: | They propose a low-rank adaptive approach that decomposes update matrix into global and local adapters and assigns them to local and global adapters. |
| Outcome: | The proposed method achieves up to 2.7% accuracy improvement over LoRA and its variants on commonsense reasoning, mathematical reasoning, and code generation. |
Learning Geometry-Aware Representations for New Intent Discovery (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for intent classification fail to distinguish new intents due to intertwined centers . a novel framework that learns geometry-aware representations to maximally separate all intents is proposed . |
| Approach: | They propose a new intent discovery framework that learns geometry-aware representations to maximally separate all intents. |
| Outcome: | The proposed framework achieves a new state-of-the-art performance on three benchmarking datasets. |
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing (2020.acl-main)
Copied to clipboard
| Challenge: | Existing semantic parsing frameworks rely on nontrivial human labor to generate canonical utterances. |
| Approach: | They propose a framework that uses an unsupervised paraphrase model to parse canonical utterances. |
| Outcome: | The proposed framework is effective and compatible with supervised training. |
LiveCANNBench: Benchmark SWE AI Coding for Ascend CANN (2026.findings-acl)
Copied to clipboard
Sijie Wang, Kai Zhao, Wee Peng Tay, Shuo Zhang, Chengwen Liu, Quanjiang Guo, Ren Junhao, Xin Li, Heng Lian, Jingdi Lei, Rui She, Huacan Wang, Ronghao Chen
| Challenge: | Recent advances in agents have enabled multi-file, multi-language, and dependency-aware AI coding. |
| Approach: | They propose an SWE-level benchmark for AI coding in the Huawei Ascend CANN software stack. |
| Outcome: | The proposed benchmark is constructed from real-world CANN repositories and consists of over 400 task instances spanning multiple file, multi-language, and execution-aware coding challenges. |
CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space (2025.emnlp-main)
Copied to clipboard
Yong Zhao, Kai Xu, Zhengqiu Zhu, Yue Hu, Zhiheng Zheng, Yingfeng Chen, Yatai Ji, Chen Gao, Yong Li, Jincai Huang
| Challenge: | Embodied Question Answering (EQA) tasks are primarily focused on indoor environments, leaving the complexities of urban settings unexplored. |
| Approach: | They propose a task where an embodied agent answers open-vocabulary questions in dynamic city spaces. |
| Outcome: | The proposed agent achieves 60.7% of human-level answering accuracy compared to baselines . the proposed agent outperforms existing agents in open-ended city spaces . |
LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to encode text-to-SQL data are node-centric and ignore semantics embedded in the topological structure of edges. |
| Approach: | They propose a Line Graph Enhanced Text-to-SQL model to mine relational features without constructing meta-paths. |
| Outcome: | The proposed model achieves state-of-the-art on the cross-domain text-to-SQL benchmark Spider at the time of writing. |
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)
Copied to clipboard
Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He
| Challenge: | Document images are characterized by higher resolutions, denser content, and more complex structural layouts. |
| Approach: | They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition. |
| Outcome: | The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead. |
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration (2026.acl-long)
Copied to clipboard
Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
| Challenge: | Existing data arbitration strategies for large language model training rely on surface-level heuristics that fail to diagnose intrinsic learning needs. |
| Approach: | They propose a framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge. |
| Outcome: | Extensive experiments on WebShop and ALFWorld show that PRISM outperforms state-of-the-art hybrid methods while reducing computational costs by up to 3.22 . |
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection (2025.acl-long)
Copied to clipboard
Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu
| Challenge: | Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer. |
| Approach: | They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions. |
| Outcome: | The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios. |
Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Using neural machine translation to approximate human parity is difficult due to the lack of parallel training corpora. |
| Approach: | They propose an end-to-end deep learning framework for quality estimation and automatic post-editing of machine translation output. |
| Outcome: | The proposed framework achieves state-of-the-art performance on the English–German dataset and human translators can significantly expedite their post-editing processing with the model. |
QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models (2025.emnlp-main)
Copied to clipboard
Jiajun Zhou, Yifan Yang, Kai Zhen, Ziyue Liu, Yequan Zhao, Ershad Banijamali, Athanasios Mouchtaris, Ngai Wong, Zheng Zhang
| Challenge: | Large Language Models (LLMs) are quantized to lower precision to reduce memory cost and latency in inference. |
| Approach: | They propose a quantized zeroth-order framework for fine-tuning Large Language Models (LLMs) using low-precision forward passes. |
| Outcome: | The proposed method achieves comparable results to first-order methods in FP8 and superior accuracy in INT8 and INT4 training. |
Deep Reinforcement Learning-based Dialogue Policy with Graph Convolutional Q-network (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for deep reinforcement learning lack the ability to learn the relationship between dialogue states and actions. |
| Approach: | They propose a graph-structured dialogue policy framework for task-oriented dialogue systems that uses bipartite graphs to construct two different bipartites and generate user-related and knowledge-related subgraphs. |
| Outcome: | The proposed framework significantly improves the effectiveness and stability of dialogue policies. |
TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing models for structural reading comprehension (SRC) only focus on comprehension of plain text, tables, tables or knowledge bases. |
| Approach: | They propose a topological information enhanced model which transforms a token-level task into a tag-level one by introducing a two-stage process. |
| Outcome: | The proposed model outperforms baselines and achieves state-of-the-art performance on the web-based SRC benchmark WebSRC at the time of writing. |
ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing semantic parsing models struggle to adapt to unseen database schemas . a new architecture, ShadowGNN, processes schemas at abstract and semantic levels . |
| Approach: | They propose a new architecture which processes schemas at abstract and semantic levels. |
| Outcome: | The proposed architecture outperforms state-of-the-art models on a text-to-sql benchmark . it uses domain-independent representations to extract logical linking between question and schema . |
ZoomRAG: Hierarchical Random-walk Zooming across Multi-scale Information Graphs for Fast and Accurate RAG (2026.findings-acl)
Copied to clipboard
Xianming Hu, Jingyang Chen, Bin Tang, Yihe Liu, Yihong Huang, Hongbo Zhao, Nuoyi Chen, Jie Zhang, Ping Li, Kai Zhang
| Challenge: | retrieval-augmented generation (RAG) is a powerful tool for NLP applications . but it is challenging to encode large knowledge bases as compact offline structures . |
| Approach: | They propose a coarse-to-fine hierarchical graph inference method that uses random walks to retrieve information from a corpus of documents. |
| Outcome: | The proposed method reduces offline indexing costs and accelerates retrieval. |
Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks (2020.acl-main)
Copied to clipboard
| Challenge: | Existing graph-to-sequence approaches use graph neural networks as encoders, but they lack the structure information needed to translate AMR into the graph-based data. |
| Approach: | They propose a graph-to-sequence task which aims to recover natural language from Abstract Meaning Representations (AMR) they adopt graph attention networks with higher-order neighborhood information to explore the edge relations in AMR graphs. |
| Outcome: | The proposed framework achieves state-of-the-art performance on English AMR benchmark datasets and is able to translate the AMR semantics into the natural language. |
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)
Copied to clipboard
Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan
| Challenge: | Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages . |
| Approach: | They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models . |
| Outcome: | The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English . |
Data Augmentation with Atomic Templates for Spoken Language Understanding (D19-1)
Copied to clipboard
| Challenge: | Existing methods to enlarge SLU data require large amounts of labelled data. |
| Approach: | They propose a data augmentation method with atomic templates for Spoken Language Understanding which generates atomic exemplars from atomic template. |
| Outcome: | The proposed method improves on a DSTC 2&3 dataset which is a domain adaptation setting of SLU. |
GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models (2025.acl-long)
Copied to clipboard
Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Jianke Zhu, Wei Wang
| Challenge: | Existing methods for offsite-tuning of large language models require high computational costs and lack theoretical analysis. |
| Approach: | They propose an offsite-tuning approach that selectively applies compression techniques such as rank compression and channel pruning to preserve the gradients of fine-tuned adapters while ensuring privacy. |
| Outcome: | The proposed method surpasses existing OT methods in privacy protection and model performance. |
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization (2026.acl-long)
Copied to clipboard
Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
| Challenge: | Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), but its efficacy is confined to domains with verifiable ground truths. |
| Approach: | They propose a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as 'a semantic bottleneck' . Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines while preserving the efficiency advantages of GRPO. |
| Outcome: | The proposed model outperforms single-reward and static multi-objective baselines while preserving efficiency advantages. |
PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism AI Psychological Counselor (2026.findings-acl)
Copied to clipboard
Qianjun Pan, Junyi Wang, Jie Zhou, Yutao Yang, Junsong Li, Kaiyin Xu, Yougen Zhou, Yihan Li, JingYuan Zhao, Qin Chen, Ningning Zhou, Kai Chen, Liang He
| Challenge: | Existing models focus on a single therapy, but complex cases require flexible strategies among various therapies. |
| Approach: | They propose a multi-session, multi-therapy, and highly realistic benchmark . it is designed to address three key challenges: 1) can we train a highly realistic AI counselor? 2) How to systematically evaluate an AI counselor?" |
| Outcome: | The proposed benchmark is annotated with extensive professional skills and includes over 677 meta-skills and 4577 atomic skills. |
RePair: Automated Program Repair with Process-based Feedback (2024.findings-acl)
Copied to clipboard
| Challenge: | Commercial-scale language models (LMs) have taken APR to unprecedented levels, but they are limited by parameters and humans interact with them through explicit prompts. |
| Approach: | They propose a method that utilizes process supervision to improve program repair by allowing users to input feedback from compilers and test cases. |
| Outcome: | The proposed method outperforms large outcome-based generation methods and is inspired by strategies used in programming competitions. |
Adversarial Knowledge Stimulated Contrastive Prompting for Few-shot Language Learners (2023.findings-acl)
Copied to clipboard
| Challenge: | Prompt-based fine-tuning has boosted performance of Pre-trained language models on few-shot Natural Language Understanding (NLU) tasks by employing task-specific prompts. |
| Approach: | They propose a Cloze-driven prompt framework for prompt tuning that implicitly stimulates knowledge from pre-trained language models. |
| Outcome: | The proposed framework outperforms state-of-the-art for prompt-based fine-tuning on few-shot NLU tasks. |
Localized Low-Rank Adaptation within Clustered Parameter Subspaces (2026.acl-long)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) for large language models has been successful in various domains. |
| Approach: | They propose to perform low-rank updates within clustered parameter subspaces . they group rows/columns of update matrix into locally coherent, uncorrelated subspace blocks . |
| Outcome: | Empirical results show that low-rank Adaptation (LoRA) is better than global adaptations in various domains. |
LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on learning and enhancing large language models to understand and generate natural language. |
| Approach: | They propose a computational bionic memory mechanism equipped with a parameter-efficient fine-tuning schema to personalize medical assistants. |
| Outcome: | The proposed method can enhance the response with aware of previous mistakes for new queries during a dialogue session, but the training costs are prohibitive. |
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)
Copied to clipboard
Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
| Challenge: | Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood. |
| Approach: | They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction . |
| Outcome: | The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones . |
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge (2025.emnlp-main)
Copied to clipboard
Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, Kai Shu, Lu Cheng, Huan Liu
| Challenge: | Recent advances in Large Language Models (LLMs) inspire the "LLM-as-a-judge" paradigm . traditional methods of assessment and evaluation fail in dynamic and open-ended scenarios . |
| Approach: | They propose a paradigm where LLMs are leveraged to perform scoring, ranking, or selection for machine learning evaluation scenarios. |
| Outcome: | The proposed model-based judgment and evaluation paradigms are based on large language models and are compared to the current model-driven evaluation paradigm. |
Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection (2025.acl-long)
Copied to clipboard
Cilin Yan, Jingyun Wang, Lin Zhang, Ruihui Zhao, Xiaopu Wu, Kai Xiong, Qingsong Liu, Guoliang Kang, Yangyang Kang
| Challenge: | Recent work utilizes feedbacks generated from erroneous cases to guide prompt optimization . previous methods rely on computational resources and powerful GPUs . |
| Approach: | They propose an automatic prompt engineering method that leverages feedbacks from erroneous cases to guide prompt optimization. |
| Outcome: | The proposed method surpasses state-of-the-art methods with less steps and lower computational resources. |
Neural Graph Matching Networks for Chinese Short Text Matching (2020.acl-main)
Copied to clipboard
| Challenge: | Chinese word segmentation can be erroneous, ambiguous or inconsistent, causing performance problems. |
| Approach: | They propose a sentence matching framework that uses paired word lattices as input instead of a character sequence. |
| Outcome: | The proposed framework outperforms the state-of-the-art short text matching models on two Chinese datasets. |
Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation (2026.acl-long)
Copied to clipboard
| Challenge: | Traditional Video Quality Assessment (VQA) focuses on aesthetic fidelity and technical distortions. |
| Approach: | They propose a new task that evaluates whether a UGC item has positive community resonance based on multimodal attributes rather than visual quality alone. |
| Outcome: | The proposed task outperforms state-of-the-art baselines on CASTER-Bench . it provides interpretable and empathetic reasoning paths that align with real community feedback. |
Adaptive Zooming via Relevance-Informed Positional Resource Allocation for Training-free LLM Context Extension (2026.findings-acl)
Copied to clipboard
Hongbo Zhao, Huibin Wang, Bin Tang, Xianming Hu, Yihong Huang, Yijun Shen, Nuoyi Chen, Ping Li, Kai Zhang
| Challenge: | Existing training-free methods for extrapolating beyond training context lengths are semantics-agnostic . Existing methods that focus on relative token distances can indiscriminately blur semantically relevant and irrelevant tokens . |
| Approach: | They propose an adaptive positional zooming method that uses semantic relevance to extrapolate beyond training context lengths. |
| Outcome: | Experiments show that RiPRA outperforms existing training-free extrapolation methods . relevant tokens get higher positional resolution, while irrelevant tokens are compressed . |
SMASH: Improving SMAll Language Models’ Few-SHot Ability with Prompt-Based Distillation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale language models with prompts have shown remarkable performance on few-shot learning. |
| Approach: | They propose an approach to improve SMAll language models’ few-SHot ability by training on intermediate tasks before prompt-based fine-tuning on downstream tasks. |
| Outcome: | The proposed model improves on sentence-pair and sentiment classification tasks by training on intermediate tasks before fine-tuning on downstream tasks. |
Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis (2022.findings-acl)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis (ABSA) predicts sentiment polarity towards a specific aspect in a sentence. |
| Approach: | They propose to use a dynamic aspect-oriented semantics-based method to learn ABSA. |
| Outcome: | The proposed method can learn dynamic aspect-oriented semantics for ABSA on three benchmark datasets. |
TextHide: Tackling Data Privacy in Language Understanding Tasks (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Unsolved privacy challenges in distributed or federated learning are a challenge for many domains including Natural Language Processing. |
| Approach: | They propose a federated learning framework that adds an encryption step to prevent an eavesdropping attacker from recovering private text data. |
| Outcome: | The proposed model can effectively defend against attacks on shared gradients or representations and the averaged accuracy reduction is only 1.9%. |
Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to generating entailment trees lack logical consistency . static reward structures or intricate dependencies within multi-step reasoning are often ignored . |
| Approach: | They propose a method that integrates natural logic principles into reinforcement learning to guide entailment tree generation. |
| Outcome: | Experiments on EntailmentBank show that the proposed method improves interpretability and generalization. |
SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering? (2026.findings-acl)
Copied to clipboard
Yuxuan Sun, Yuze Zhao, Yufeng Wang, Yao Du, Zhiyuan Ma, Jinbo Wang, Mengdi Zhang, Kai Zhang, Zhenya Huang
| Challenge: | Evaluating software engineering capabilities is a core component of large language models (LLMs). |
| Approach: | They propose a benchmark to evaluate LLM-generated test suites that introduces mutated solutions that attempt to "fool" them. |
| Outcome: | The proposed test suites are based on 2,636 mutated variants derived from 800 original instances and include a multilingual subset spanning nine programming languages. |
RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank (2023.acl-long)
Copied to clipboard
Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Kai Chen, Rui Yan
| Challenge: | Unsupervised sentence representation learning is one of the fundamental problems in natural language processing . contrastive learning methods fail to capture fine-grained ranking information among the sentences . |
| Approach: | They propose a novel approach for unsupervised sentence representation learning that integrates ranking consistency and ranking distillation with contrastive learning into a unified framework. |
| Outcome: | The proposed approach performs better over state-of-the-art models on STS and TR tasks. |
Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in various tasks, but may rely on dataset biases as shortcuts for prediction. |
| Approach: | They propose to use a test suite to evaluate the impact of shortcuts on LLMs' performance. |
| Outcome: | The proposed test suite incorporates six shortcut types, five evaluation metrics, and four prompting strategies. |
CEAN: Contrastive Event Aggregation Network with LLM-based Augmentation for Event Extraction (2024.eacl-long)
Copied to clipboard
| Challenge: | Event Extraction is a crucial yet arduous task in natural language processing (NLP), as its performance is hindered by laborious data annotation. |
| Approach: | They propose a Contrastive Event Aggregation Network with LLM-based Augmentation to promote low-resource learning and reduce data noise for event extraction. |
| Outcome: | The proposed approach achieves new state-of-the-art results on the ACE2005 and ERE-EN datasets. |
MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification (2025.findings-acl)
Copied to clipboard
xu Zhao Pan, Pengfei Zhou, Jiaxin Ai, Wangbo Zhao, Kai Wang, Xiaojiang Peng, Wenqi Shao, Hongxun Yao, Kaipeng Zhang
| Challenge: | Existing benchmarks of large language models focus on error detection, neglecting other scenarios like reasoning search. |
| Approach: | et al. propose a multi-task, multimodal benchmark to assess effectiveness of PRMs . step correctness, answers aggregation and reasoning process search are evaluated . ethical principles of MPBench are based on a set of evaluation paradigms based in a text-based benchmark . |
| Outcome: | a new benchmark assesses the effectiveness of large language models (LLMs) in multiple scenarios . it uses three evaluation paradigms to assess the effectiveness and compares them with existing models . a the proposed model improves reasoning accuracy by providing stepwise feedback for multi-step reasoning results . |
Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning (2023.findings-emnlp)
Copied to clipboard
Yougang Lyu, Jitai Hao, Zihan Wang, Kai Zhao, Shen Gao, Pengjie Ren, Zhumin Chen, Fang Wang, Zhaochun Ren
| Challenge: | Existing methods for predicting judgment results for multiple defendants are ineffective. |
| Approach: | They propose a method to predict the judgment results for each defendant in multi-defendant cases . they formalize the multi-diffendant judgment process as hierarchical reasoning chains . |
| Outcome: | The proposed method can predict the judgment results for multiple defendants in multi-defendant cases. |
Safer-Instruct: Aligning Language Models with Automated Preference Data (2024.naacl-long)
Copied to clipboard
| Challenge: | annotating preference data by humans is resource-intensive and creativity-demanding . existing methods face limitations in data diversity and quality . |
| Approach: | They propose a pipeline for annotating large-scale preference data without human annotators. |
| Outcome: | The proposed pipeline outperforms models fine-tuned on human-annotated safety preference data while maintaining a competitive edge in downstream tasks. |
LLM Factoscope: Uncovering LLMs’ Factual Discernment through Measuring Inner States (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) produce outputs that deviate from factual reality, especially in sensitive applications such as medical consultation and legal advice. |
| Approach: | They propose a Siamese network-based model that leverages LLMs’ inner states for factual detection. |
| Outcome: | The proposed model achieves over 96% accuracy on a custom-collected factual detection dataset. |
LAMCL: A Length-aware Momentum Contrastive Learning Framework for Multiscale Machine-Revised Text Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Recent detection methods struggle to capture fine-grained semantic differences, especially for short texts. |
| Approach: | They propose a framework for machine-revised text detection that integrates two modules to enhance discriminative semantic features. |
| Outcome: | The proposed method outperforms existing detectors in identifying machine-revised text across diverse practical scenarios, tasks, and LLMs. |
Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have suggested that the composition of the pretraining corpus exerts a significant impact upon the performance of LLMs. |
| Approach: | They analyze the impact of 48 datasets from 5 major categories of pretraining data of Large Language Models and measure their impacts on LLMs using benchmarks about nine major categories. |
| Outcome: | The proposed analysis provides insights into the organization of data to support more efficient pretraining of Large Language Models. |
Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns (2025.acl-long)
Copied to clipboard
| Challenge: | Currently, LLMs learn in a data-driven schema while the instructions about complex tasks are both scarce and hard to collect or construct. |
| Approach: | They employ a gradient-based method to dissect the process that the Supervised Fine-tuning Process (SFT) adapts LLMs to downstream tasks via the perspective of attention patterns. |
| Outcome: | The proposed method dissects the process that the SFT process adapts LLMs to downstream tasks via the perspective of attention patterns. |
WebSRC: A Dataset for Web-Based Structural Reading Comprehension (2021.emnlp-main)
Copied to clipboard
| Challenge: | Using a web page and a question, a machine can't understand the contents of web pages. |
| Approach: | They propose a novel dataset for web-based structural reading comprehension that consists of 400K question-answer pairs and a dataset of 6.4K web pages. |
| Outcome: | The proposed dataset consists of 400K question-answer pairs, collected from 6.4K web pages with corresponding HTML source code, screenshots, and metadata. |
Redundancy Principles for MLLMs Benchmarks (2025.acl-long)
Copied to clipboard
Zicheng Zhang, Xiangyu Zhao, Xinyu Fang, Chunyi Li, Xiaohong Liu, Xiongkuo Min, Haodong Duan, Kai Chen, Guangtao Zhai
| Challenge: | Rapid growth of Multi-modality Large Language Models has led to significant redundancy among benchmarks. |
| Approach: | They propose a framework to improve MLLM benchmark design by identifying redundancy at three levels: dimension, instance, and cross-benchmark redundancies. |
| Outcome: | The proposed framework streamlines evaluations and enhances reliability. |
An Efficient Dialogue Policy Agent with Model-Based Causal Reinforcement Learning (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models for dialogue policy training consider one-step dialogues, leading to inaccurate simulations. |
| Approach: | They propose a framework for dialogue policy learning that trains an agent to select dialogue actions via deep reinforcement learning. |
| Outcome: | The proposed framework achieves state-of-the-art performance on three dialogue datasets . it uses model-based reinforcement learning with automatically constructed causal chains . |
Curriculum Learning based Hierarchical Scoring and Analysis Framework for Question Answering Task Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation methods rely on rule-based matching with shallow semantic understanding or adopt LLM-as-a-Judge approaches that incur high cost and latency while offering limited error interpretability. |
| Approach: | They propose a curriculum learning based hierarchical framework for QA task evaluation that supports quick scoring and fine-grained error analysis. |
| Outcome: | The proposed framework outperforms baseline methods on quick scoring and error analysis tasks while being 25 faster. |
Stepwise Reasoning Disruption Attack of LLMs (2025.acl-long)
Copied to clipboard
Jingyu Peng, Maolin Wang, Xiangyu Zhao, Kai Zhang, Wanyu Wang, Pengyue Jia, Qidong Liu, Ruocheng Guo, Qi Liu
| Challenge: | Existing attacks on LLM reasoning are constrained by specific settings or lack of imperceptibility, limiting their feasibility and generalizability. |
| Approach: | They propose a stepwise rEasoning error disruption attack that subtly injects errors into prior reasoning steps to mislead the model into producing incorrect subsequent reasoning and final answers. |
| Outcome: | The proposed attack is compatible with zero-shot and few-shot settings, maintains the natural reasoning flow, and ensures covert execution without modification of the instruction. |
Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on prompt engineering or framework scheduling of one/multiple LLMs. |
| Approach: | They propose to integrate LLMs as agents into their training corpus by decomposition and redesigning the training corpu . they propose to use LLM-FLAN to effectively fine-tune LANguage models for Agents by reducing hallucinations. |
| Outcome: | The proposed model outperforms prior best models by 3.5% across agent evaluation datasets. |
ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning (2024.emnlp-industry)
Copied to clipboard
Yihong Tang, Zhaokai Wang, Ao Qu, Yihao Yan, Zhaofeng Wu, Dingyi Zhuang, Jushi Kai, Kebing Hou, Xiaotong Guo, Jinhua Zhao, Zhan Zhao, Wei Ma
| Challenge: | Existing urban itinerary planning studies focus on traditional tourism, but they lack the precision and accuracy needed to create a personalized itinerary. |
| Approach: | They propose an open-domain urban itinerary planning system that integrates spatial optimization with large language models to provide customized urban itineraries based on user needs. |
| Outcome: | The proposed system can generate personalized urban itineraries based on user needs and scale with existing methods. |
TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition (2021.acl-demo)
Copied to clipboard
| Challenge: | TEXTOIR is the first integrated platform for text open intent recognition . currently, many dialogue systems are limited to handle the uncertain open intents . |
| Approach: | TEXTOIR is the first integrated platform for text open intent recognition . it is composed of two main modules: open intent detection and open intent discovery . authors propose a framework to implement a complete process to identify known intents and discover open intents . |
| Outcome: | TEXTOIR is the first integrated and visualized platform for text open intent recognition . it integrates state-of-the-art algorithms and benchmark intent datasets . however, there are still some issues, which bring difficulties for future research . |
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering (2021.naacl-main)
Copied to clipboard
Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, Haifeng Wang
| Challenge: | Open-domain question answering uses dense passage retrieval to find answers . however, it is difficult to effectively train a dual-encoder due to discrepancy between training and inference . |
| Approach: | They propose an optimized training approach to improve dense passage retrieval using RocketQA . they propose cross-batch negatives, denoised hard negatives and data augmentation . |
| Outcome: | The proposed approach outperforms state-of-the-art models on both MSMARCO and Natural Questions. |
Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression (2026.findings-acl)
Copied to clipboard
Jingyu Peng, Maolin Wang, Nan Wang, Jiatong Li, Yuchen Li, Yuyang Ye, Wanyu Wang, Pengyue Jia, Kai Zhang, Xiangyu Zhao
| Challenge: | Despite advances in aligning LLMs with human values, current safety mechanisms remain vulnerable to jailbreak attacks. |
| Approach: | They propose a black-box jailbreak method that uses logical expression translation to bypass LLM safety mechanisms. |
| Outcome: | The proposed method exploits the distributional gap between alignment data and logic-expressed inputs while preserving the underlying semantic intent and readability while evading safety constraints. |
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference (2025.acl-long)
Copied to clipboard
Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosongcao Maosongcao, Jiaqi Wang, Weiyun Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Hua Yang, Haodong Duan, Kai Chen
| Challenge: | Existing open-source multi-modal large language models (MLLMs) focus on enhancing foundational capabilities, leaving a significant gap in human preference alignment. |
| Approach: | They propose a dataset of 200K high-quality training samples featuring diverse images, complex questions, and varied response formats to improve MLLMs’ alignment with human preferences. |
| Outcome: | The proposed dataset of 200K high-quality training samples improves human preference alignment while maintaining or enhancing performance on standard VQA benchmarks. |
Robust Explanations for User Trust in Enterprise NLP Systems (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing studies on explanation stability under real user noise are limited . decoder LLMs produce significantly more stable explanations than encoder baselines . |
| Approach: | They propose a black-box robustness evaluation framework for token-level explanations based on leave-one-out occlusion . they propose to operationalize explanation robustness with top-token flip rate under realistic perturbations at multiple severity levels . |
| Outcome: | The proposed framework is compared with baseline models and encoder and decoder families. |
T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step (2024.acl-long)
Copied to clipboard
Zehui Chen, Weihua Du, Wenwei Zhang, Kuikun Liu, Jiangning Liu, Miao Zheng, Jingming Zhuo, Songyang Zhang, Dahua Lin, Kai Chen, Feng Zhao
| Challenge: | Existing studies evaluate the tool utilization ability of large language models based on the final output or only consider the single-step tool calling. |
| Approach: | They propose a new approach to evaluate the tool utilization capability of large language models (LLMs) they decompose the tool usage into multiple sub-processes, including instruction following, planning, reasoning, retrieval, understanding, and review. |
| Outcome: | The proposed model exhibits consistency with the outcome-oriented evaluation and provides a more fine-grained analysis of the capabilities of LLMs. |