Papers by Jie Sun

Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation (2026.acl-long)

Challenge:	Data augmentation aims to alleviate the overfitting issue in low-resource or class-imbalanced situations.
Approach:	They propose a framework called Text AutoAugment to enhance training samples . they use a Bayesian optimization algorithm to search for the best policy .
Outcome:	The proposed framework outperforms baseline methods on six benchmark datasets.

Copied to clipboard

Tianjun Wei, Huizhong Guo, Yingpeng Du, Zhu Sun, Huang Chen, Dongxia Wang, Jie Zhang

Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models (2022.coling-1)

Challenge:	Large Language Models lack specific task alignment and large-scale simulations are challenging due to their ambiguity, noise and massive volume.
Approach:	They propose a framework that leverages user feedback in RSs with advanced LLM capabilities to generate high-quality simulation data.
Outcome:	The proposed framework boosts the alignment with human preferences and in-domain reasoning capabilities of the fine-tuned LLMs.

Copied to clipboard

Zichun Yu, Tianyu Gao, Zhengyan Zhang, Yankai Lin, Zhiyuan Liu, Maosong Sun, Jie Zhou

Learning In-context Learning for Named Entity Recognition (2023.acl-long)

Challenge:	Prompting has shown to be sample efficient compared to fine-tuning with pre-trained models.
Approach:	They propose a fully automatic prompting method that uses natural language prompts on sequence-to-sequence models and a beam search method to generate a large amount of label sequence candidates.
Outcome:	The proposed method significantly outperforms other no-manual-design methods on single label words and generates large amount of label sequence candidates.

Copied to clipboard

Jiawei Chen, Yaojie Lu, Hongyu Lin, Jie Lou, Wei Jia, Dai Dai, Hua Wu, Boxi Cao, Xianpei Han, Le Sun

FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner (2026.acl-long)

Challenge:	Existing methods to recognize entities in text are limited by the diversity of entity types and the lack of high-quality annotations.
Approach:	They propose an in-context learning-based NER approach that can inject in-const NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances.
Outcome:	The proposed method outperforms the PLMs+fine-tuning counterparts on 4 few-shot NER datasets and significantly outperformed the Plms+initialized extractors.

Copied to clipboard

Hao Wu, Hongru Sun, Wanqing Li, Xinguo Yu, Hao Ming, Xiao Luo, Wenbin Zhang, Jiahong Zhao, Yi Guo, Jie Yang

Causal Intervention Improves Implicit Sentiment Analysis (2022.coling-1)

Challenge:	Existing approaches to mathematical reasoning rely on static heuristics or pre-determined reasoning strategies.
Approach:	They propose an adaptive framework that integrates fuzzy theory into LLM-based mathematical reasoning.
Outcome:	The proposed framework outperforms state-of-the-art models while offering effective and interpretable diagnostics of intermediate problem-solving states.

Copied to clipboard

Siyin Wang, Jie Zhou, Changzhi Sun, Junjie Ye, Tao Gui, Qi Zhang, Xuanjing Huang

Sentiment Analysis

Challenge:	Existing neural models struggle with implicit sentiment analysis because they latch onto spurious correlations, resulting in poor generalization and robustness.
Approach:	They propose a CausaL intervention model for implicit sEntiment ANalysis using instrumental variable to eliminate confounding causal effects and extract the pure causal effect between sentence and sentiment.
Outcome:	The proposed model extracts the pure causal effect between sentence and sentiment using instrumental variable.

Contrastive Preference Learning for Neural Machine Translation (2024.findings-naacl)

Copied to clipboard

Jianfei He, Shichao Sun, Sen Peng, Jie Xu, Xiaohua Jia, Wenjie Li

Machine Translation

Challenge:	Existing discrepancies between token-level objective and overall sequence-level quality of a model are causing exposure bias and other issues in NMT.
Approach:	They propose a contrastive preference model that integrates an indicator function to fine-tune a pre-trained model in Neural Machine Translation.
Outcome:	The proposed model outperforms the traditional Plackett-Luce model on three language pairs and also outperFORMs token-level and sequence-level baseline models.

MemSearcher: Iterative Memory Integration for Search Agent via End-to-End Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Qianhao Yuan, Jie Lou, Zichao Li, Jiawei Chen, Yaojie Lu, Hongyu Lin, Le Sun, Debing Zhang, Xianpei Han

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning (2026.acl-long)

Challenge:	Recent LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs and increasing compute cost and memory overhead.
Approach:	They propose an agent framework that maintains a compact memory during multi-turn interactions.
Outcome:	The proposed framework outperforms strong history-concatenation (ReAct-style) baselines on a range of public datasets while maintaining nearly constant token counts across multi-turn interactions.

Copied to clipboard

Junjie Wang, Zequn Xie, Dan Yang, Jie Feng, Yue Shen, Duolin Sun, Meixiu Long, Yihan Jiao, Zhehao Tan, Jian Wang, Peng Wei, Jinjie Gu

Structured Data in NLP

Challenge:	Open-source web agents rely on long tool-call trajectories with cyclic reasoning loops and exploration of unproductive branches.
Approach:	They propose a framework that compresses web agent trajectories via graph-based pruning.
Outcome:	The proposed framework reduces tool-call rounds by 20% while improving accuracy and efficiency while maintaining the same level of performance as existing models.

Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias (2023.findings-acl)

Copied to clipboard

Zhiyuan Zhang, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

Exploring Mode Connectivity for Pre-trained Language Models (2022.emnlp-main)

Challenge:	Existing methods to fine-tune pre-trained language models (PLMs) are not safe, since the fine-uning process is invisible to the user.
Approach:	They propose a technique to study the dynamic process of fine-tuning for finding poisonous dimensions using diffusion theory.
Outcome:	The proposed approach can detect poisonous dimensions with abnormal dynamics, purify them and fine-tune them on a clean dataset.

Copied to clipboard

Yujia Qin, Cheng Qian, Jing Yi, Weize Chen, Yankai Lin, Xu Han, Zhiyuan Liu, Maosong Sun, Jie Zhou

Knowledge Inheritance for Pre-trained Language Models (2022.naacl-main)

Challenge:	Recent years have witnessed the prevalent application of pre-trained language models (PLMs) in NLP. From the perspective of parameter space, PLMs provide generic initialization, starting from which high-performance minima could be found.
Approach:	They investigate the geometric connections of different minima through the lens of mode connectivity, which measures whether two minima can be connected with a low-loss path.
Outcome:	The proposed model can be used to find low-loss paths between two minima, and to understand how their mode connectivity affects their task knowledge.

Copied to clipboard

Yujia Qin, Yankai Lin, Jing Yi, Jiajie Zhang, Xu Han, Zhengyan Zhang, Yusheng Su, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Towards Fine-grained Text Sentiment Transfer (P19-1)

Challenge:	Existing large-scale pre-trained language models are mainly trained from scratch individually, ignoring that many well-taught PLMs are available.
Approach:	They propose a pre-training framework called knowledge inheritance and propose auxiliary supervision to efficiently learn larger PLMs.
Outcome:	The proposed framework can be used to train large-scale language models with huge parameters and a large dataset can be adapted to domain adaptation and knowledge transfer.

Copied to clipboard

Fuli Luo, Peng Li, Pengcheng Yang, Jie Zhou, Yutong Tan, Baobao Chang, Zhifang Sui, Xu Sun

Sentiment Analysis

Challenge:	Existing methods for fine-grained text sentiment transfer only reverse the sentiment polarity of text, but they lack a robust and parallel learning algorithm.
Approach:	They propose a novel fine-grained text sentiment transfer task that revises a sequence to satisfy a given sentiment intensity while preserving the original semantic content.
Outcome:	The proposed model outperforms existing methods by a large margin in automatic evaluation and human evaluation.

PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference (2026.findings-eacl)

Copied to clipboard

Krishna Teja Chitty-Venkata, Jie Ye, Siddhisanket Raskar, Anthony Kougkas, Xian Sun, Murali Emani, Venkatram Vishwanath, Bogdan Nicolae

LaMP-Val: Large Language Models Empower Personalized Valuation in Auction (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) are exploding to large sizes, including GPT, LLaMA, and DeepSeek.
Approach:	They propose a fine-grained, structured KV cache pruning strategy that enhances the memory efficiency of vLLM’s PagedAttention.
Outcome:	The proposed method integrates seamlessly with PagedAttention without any modifications to its CUDA attention kernels.

Copied to clipboard

Jie Sun, Tianyu Zhang, Houcheng Jiang, Kexin Huang, Xiang Shu, Zhibo Zhu, Lintao Ma, Xingyu Lu, Jun Zhou, Junkang Wu, Chi Luo, An Zhang, Jiancan Wu, Xiang Wang

Formally Specifying the Intended Behavior of the Program: LLM-Driven Neuro-Symbolic Program Specification Synthesis (2026.acl-demo)

Challenge:	Currently, most research focuses on the bidding algorithms used within auction mechanisms.
Approach:	They propose a personalized valuation framework that integrates Large Language Models to incorporate personalized semantic preference into users valuation process.
Outcome:	The proposed framework incorporates Large Language Models to incorporate personalized semantic preference into users valuation process.

Copied to clipboard

Cheng Wen, Hu Junjie, YiKun Hu, Jie Su, Bin Yu, Dugang Liu, Zhiwu Xu, Weidi Sun, Shengchao Qin, Cong Tian

KARL: Reinforcement Learning for LLM Agents on Multi-Turn Knowledge-Intensive Agentic Tasks (2026.acl-long)

Challenge:	Formal verification typically requires developers to write detailed formal specifications . a formal verification system that generates candidate specifications is costly and error-prone .
Approach:	They propose an LLM-driven neuro-symbolic demonstration system that reframes specification writing as constrained structured synthesis.
Outcome:	The proposed system reduces hallucinations and produces proof-ready annotations.

Copied to clipboard

Xueqiao Sun, Xiao Liu, Bowen Lv, Hanchen Zhang, Bohao Jing, Zehan Qi, Yifan Xu, Yuxiao Dong, Jie Tang

Adaptive and Representative Multi-Interest Modeling for Recommendation with Large Language Model (2026.findings-acl)

Challenge:	Large Language Models have shown remarkable potential as autonomous agents, but their effectiveness in knowledge-intensive tasks remains limited by passive knowledge utilization.
Approach:	They propose a framework that enables LLM agents to dynamically explore structured knowledge sources through multi-turn interactions.
Outcome:	The proposed framework outperforms existing retrieval-augmented approaches on knowledge graph and database tasks while maximizing tool-use behaviors end-to-end.

Copied to clipboard

Ziyan Wang, Yingpeng Du, Tianjun Wei, Haoyan Chua, Jieyi Bi, Jie Zhang, Zhu Sun

More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020.aacl-main)

Challenge:	Existing methods for multi-interest analysis of users rely on heuristic assumptions . however, the granularity of raw generation of LLMs is agnostic, leading to overly fine or coarse interest grouping.
Approach:	They propose an LLM-driven adaptive and representative multi-interest modeling framework that exploits the agnostic granularity of LLMs for multi-interest analysis.
Outcome:	The proposed model outperforms baselines on real-world datasets.

Copied to clipboard

Xu Han, Tianyu Gao, Yankai Lin, Hao Peng, Yaoliang Yang, Chaojun Xiao, Zhiyuan Liu, Peng Li, Jie Zhou, Maosong Sun

Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents (2024.acl-long)

Challenge:	Existing methods for extracting relational facts from text have been successful . but with explosion of Web text, human knowledge is increasing drastically .
Approach:	They propose to improve relation extraction methods to extract relational facts from text . they analyze existing methods and show promising directions towards more powerful RE .
Outcome:	The proposed methods can extract relational facts from text, but they are still lacking in the current field.

Copied to clipboard

Cheng Qian, Bingxiang He, Zhong Zhuang, Jia Deng, Yujia Qin, Xin Cong, Zhong Zhang, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun

LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System (2025.emnlp-demos)

Challenge:	Current language model-driven agents lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions.
Approach:	They propose a benchmark to inspect users’ implicit intentions through explicit queries and a model expert as the upstream in agent design to enhance user-agent interaction.
Outcome:	The proposed approach excels at identifying vague user tasks, recovering and summarizing critical missing information, setting precise and necessary agent execution goals, and minimizing redundant tool usage, thus boosting overall efficiency.

Copied to clipboard

Yu Chao, Siyu Lin, Xiaorong Wang, Zhu Zhang, Zihan Zhou, Haoyu Wang, Shuo Wang, Jie Zhou, Zhiyuan Liu, Maosong Sun

Challenge:	Generating high-quality long-form survey articles poses significant challenges to AI Agent systems.
Approach:	They propose a hierarchically modular agent system for long-form survey generation . they use atomic models to implement skeleton initialization, digest construction, and skelet refinement . human evaluations demonstrate system surpasses representative baselines .
Outcome:	The proposed system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning.

AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling (2024.acl-long)

Copied to clipboard

Jun Zhan, Junqi Dai, Jiasheng Ye, Yunhua Zhou, Dong Zhang, Zhigeng Liu, Xin Zhang, Ruibin Yuan, Ge Zhang, Linyang Li, Hang Yan, Jie Fu, Tao Gui, Tianxiang Sun, Yu-Gang Jiang, Xipeng Qiu

KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion (2021.findings-acl)

Challenge:	Existing language models that use discrete representations for unified processing of various modalities are limited to text generation and do not include multimodal output.
Approach:	They propose a multimodal language model that utilizes discrete representations for unified processing of various modalities.
Outcome:	The proposed model can be trained stably without any alterations to existing models or training paradigms.

Copied to clipboard

Jie Zhou, Shengding Hu, Xin Lv, Cheng Yang, Zhiyuan Liu, Wei Xu, Jie Jiang, Juanzi Li, Maosong Sun

Improving Multi-turn Dialogue Modelling with Utterance ReWriter (P19-1)

Challenge:	Existing studies focus on partial aspects of knowledge abstraction, concretization, and completion (KACC).
Approach:	They propose a unified knowledge graph benchmark to improve existing benchmarks . they collect new datasets that contain larger concept graphs and cross-view links .
Outcome:	The proposed benchmark improves existing benchmarks in terms of dataset scale, task coverage, and difficulty.

Copied to clipboard

Hui Su, Xiaoyu Shen, Rongzhi Zhang, Fei Sun, Pengwei Hu, Cheng Niu, Jie Zhou

Paraphrasing

Challenge:	Recent research has achieved impressive results in single-turn dialogue modelling, but multi-turn models still remain challenging.
Approach:	They propose to rewrite human utterances as a pre-process to help multi-turn dialgoue modelling.
Outcome:	The proposed architecture achieves remarkably good performance on the utterance rewriting task.

Robust Preference Optimization via Dynamic Target Margins (2025.findings-acl)

Copied to clipboard

Jie Sun, Junkang Wu, Jiancan Wu, Zhibo Zhu, Xingyu Lu, Jun Zhou, Lintao Ma, Xiang Wang

Exploring Conditional Variational Mechanism to Pinyin Input Method for Addressing One-to-Many Mappings in Low-Resource Scenarios (2024.acl-short)

Challenge:	Direct Preference Optimization (DPO) is an efficient method for ensuring safety and reliability in practical applications.
Approach:	They propose a dynamic target margin preference optimization algorithm that adjusts reward margins at the pairwise level.
Outcome:	The proposed method achieves an average 4.4% improvement over baselines, setting new benchmarks for state-of-the-art performance.

Copied to clipboard

Bin Sun, Jianfeng Li, Hao Zhou, Fandong Meng, Kan Li, Jie Zhou

HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning (2026.acl-long)

Challenge:	Experimental results demonstrate the superior performance of our method.
Approach:	They propose to leverage conditional variational mechanism to simplify pinyin IME . they employ a strategy that facilitates interaction between pinyan and Chinese character information .
Outcome:	The proposed method improves the performance of pinyin input method engine (IME) under low-resource conditions.

Copied to clipboard

Yangfan Wang, Tianyang Sun, Chen Tang, Jie Liu, Wei Cai, Jingchi Jiang

Challenge:	Existing approaches to lifelong model editing apply parameter perturbations to static and dense layers for all instances.
Approach:	They propose a hierarchical reinforcement learning framework that identifies the most knowledge-relevant layers for each editing instance.
Outcome:	The proposed framework boosts the performance of the competitive RLEdit by 8.48% with perturbing only half of the layers per edit.

Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment (2024.emnlp-main)

Copied to clipboard

Yiju Guo, Ganqu Cui, Lifan Yuan, Ning Ding, Zexu Sun, Bowen Sun, Huimin Chen, Ruobing Xie, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun

Challenge:	Existing algorithms for achieving optimal alignment are mostly unidirectional . a recent study suggests that large language models can be ground with evident preferences .
Approach:	They propose to ground large language models with evident preferences . they propose to use controllable preference optimization to specify different objectives .
Outcome:	The proposed models can provide responses that match various preferences among the ”3H” desiderata.

APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs (2025.acl-long)

Copied to clipboard

Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Sun Ao, Hao Zhou, Jie Zhou, Zhiyuan Liu, Maosong Sun

Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic (2025.findings-acl)

Challenge:	Long-context inference is crucial for advancing large language models, but its prefill speed remains a bottleneck.
Approach:	They propose an efficient long-context inference framework that leverages multi-host approximate attention to enhance prefill speed.
Outcome:	The proposed framework achieves speedups of 9.2, 4.2, and 1.6 without any degradation in performance.

Copied to clipboard

Xin Zheng, Jie Lou, Boxi Cao, Xueru Wen, Yuqiu Ji, Hongyu Lin, Yaojie Lu, Xianpei Han, Debing Zhang, Le Sun

HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Existing approaches to improve the reasoning performance of large language models rely on intuitive instance-level feedback, which limits the reasoning capabilities.
Approach:	They propose a framework that pushes LLMs toward System-2-like critic capability by using a step-wise CoT reasoning paradigm and automatic construction of weak-supervision data without human annotation.
Outcome:	The proposed model significantly improves task-solving performance by filtering out invalid solutions or iterative refinement.

Copied to clipboard

Yihan Jiao, Zhehao Tan, Dan Yang, Duolin Sun, Jie Feng, Yue Shen, Jian Wang, Peng Wei

GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification (P19-1)

Challenge:	In-depth research on the specific capabilities needed by the RAG generation model is lacking, leading to inconsistent document quality and retrieval system imperfections.
Approach:	They propose that RAG models should possess three progressively hierarchical abilities: (1) Filtering: the ability to select relevant information; (2) Combination: the capability to combine semantic information across paragraphs; (3) RAG-specific reasoning: the capacity to further process external knowledge using internal knowledge.
Outcome:	Experiments show that the proposed method significantly improves the model’s open-book examination capability on datasets such as RGB, PopQA, MuSiQue, HotpotQA, and PubmedQA.

Copied to clipboard

Jie Zhou, Xu Han, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension (2025.acl-long)

Challenge:	Existing methods to extract information from evidence are unable to grasp relational and logical information among the evidence.
Approach:	They propose a graph-based evidence aggregating and reasoning framework to integrate evidence from multiple pieces of evidence.
Outcome:	The proposed framework achieves significant performance improvements on a large-scale benchmark dataset.

Copied to clipboard

Kun Ouyang, Yuanxin Liu, Shicheng Li, Yi Liu, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Challenge:	Existing benchmarks on punchline comprehension suffer from language shortcuts that allow models to rely on text, lack of question diversity, and narrow focus on a specific domain of multimodal content.
Approach:	They propose a multimodal punchline comprehension benchmark to assess models' ability to comprehend punchlines.
Outcome:	The proposed model surpasses in-context learning and chain-of-thought in punchline comprehension.

Copied to clipboard

Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang

LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation (2024.findings-acl)

Challenge:	Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach:	They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome:	The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.

Copied to clipboard

Zengkui Sun, Yijin Liu, Fandong Meng, Jinan Xu, Yufeng Chen, Jie Zhou

RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension (2026.acl-long)

Challenge:	Existing LT strategies cannot indicate the desired target language on zero-shot translation, i.e., the off-target issue.
Approach:	They propose a language converter strategy that embeds the target language into the top encoder layers to mitigate confusion in the encoder and ensures stable language indication for the decoder.
Outcome:	The proposed language converter strategy significantly mitigates off-target issue on multiUN, TED, and OPUS-100 datasets.

Copied to clipboard

Yelin Chen, Fanjin Zhang, Suping Sun, Yunhe Pang, Yuanchun Wang, Jian Song, XiaoYan Li, Lei Hou, Shu Zhao, Jie Tang, Juanzi Li

Challenge:	Existing benchmarks for understanding research papers offer limited fine-grained evaluation at scale.
Approach:	They propose a large-scale question-answering benchmark built from review–rebuttal exchanges of high-quality computer science papers.
Outcome:	The proposed model is based on human-verified QA pairs and contains 15K questions.

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces (2026.findings-acl)

Copied to clipboard

Yukang Feng, Jianwen Sun, Zelai Yang, Jiaxin Ai, Chuanhao Li, Zizhen Li, Fanrui Zhang, Kang He, Rui Ma, Jifan Lin, Jie Sun, Yang Xiao, Sizhuo Zhou, Wenxiao Wu, Yiming Liu, Pengfei Liu, Shenglin Zhang, Kaipeng Zhang

Stochastic Bridges as Effective Regularizers for Parameter-Efficient Tuning (2023.findings-acl)

Challenge:	Existing benchmarks for agentic programming in long-horizon command-line interface tasks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics.
Approach:	They propose a benchmark to evaluate agentic capabilities across long-horizon command-line interface tasks.
Outcome:	The proposed benchmarks cover four engineering categories: from scratch, feature addition, bug fixing, and refactoring.

Copied to clipboard

Weize Chen, Xu Han, Yankai Lin, Zhiyuan Liu, Maosong Sun, Jie Zhou

On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation (2025.findings-acl)

Challenge:	Existing methods for tuning pre-trained language models ignore the running cost and only optimize the terminal cost.
Approach:	They propose to use stochastic bridges to regularize intermediate states and use regularization as running cost of PETs.
Outcome:	The proposed methods can be used to tune large pre-trained language models . they can be compared to full-parameter fine-tuning by tuning a small number of parameters .

Copied to clipboard

Xueru Wen, Jie Lou, Xinyu Lu, Yuqiu Ji, Xinyan Guan, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Debing Zhang, Le Sun

ReFT: Reasoning with Reinforced Fine-Tuning (2024.acl-long)

Challenge:	Large language models exhibit behavior that deviates from the boundaries of their knowledge during response generation.
Approach:	They propose a framework that allows large language models to explore their knowledge boundaries and self-correct generation behavior through fine-grained feedback signals.
Outcome:	The proposed framework enables LLMs to explore their knowledge boundaries and self-correct generation behavior through fine-grained feedback signals.

Copied to clipboard

Luong Trung, Xinbo Zhang, Zhanming Jie, Peng Sun, Xiaoran Jin, Hang Li

Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives (2022.emnlp-main)

Challenge:	Existing approaches to improve the generalization of large language models are using Supervised Fine-Tuning (SFT) this approach does not show sufficient generalization ability because it only relies on the given CoT data.
Approach:	They propose to use Chain-of-Thought annotations to train Large Language Models using supervised fine-tuning to improve generalization.
Outcome:	The proposed approach outperforms SFT on GSM8K, MathQA, and SVAMP datasets and shows a superior generalization ability.

Copied to clipboard

Si Sun, Chenyan Xiong, Yue Yu, Arnold Overwijk, Zhiyuan Liu, Jie Bao

Emergent Modularity in Pre-trained Transformers (2023.findings-acl)

Challenge:	Recent research shows strong empirical advantages of dense retrieval in various information access scenarios, such as openQA.
Approach:	They propose a method which accumulates momentum negatives from past iterations and approximates future iteration with lookahead negatives as "teleportations" on web search and OpenQA, ANCE-Tele outperforms previous state-of-the-art systems of similar size and eliminates the dependency on sparse retrieval negatives.
Outcome:	The proposed method outperforms previous state-of-the-art systems on web search and OpenQA and is competitive among systems with significantly more parameters.

Copied to clipboard

Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Chaojun Xiao, Xiaozhi Wang, Xu Han, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Jie Zhou

Outdated Issue Aware Decoding for Factual Knowledge Editing (2024.findings-acl)

Challenge:	Existing studies on pre-trained Transformers show that they learn fine-grained neuron functions.
Approach:	They examine the presence of modularity in pre-trained Transformers . they focus on Mixture-of-Experts, a promising candidate for modularity .
Outcome:	The proposed structure stabilizes at the early stage, which is faster than neuron stabilization.

Copied to clipboard

Zengkui Sun, Yijin Liu, Jiaan Wang, Fandong Meng, Jinan Xu, Yufeng Chen, Jie Zhou

P²Net: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts (2025.findings-acl)

Challenge:	Existing knowledge editing methods retain outdated responses for reasoning questions . naively retraining LLMs can be computationally intensive and can lead to catastrophic forgetting .
Approach:	They propose a simple yet effective decoding strategy to enhance edited models on reasoning questions.
Outcome:	The proposed method outDates ISsue aware deCOding (DISCO) to improve models on reasoning questions.

Copied to clipboard

Kaiwen Wei, Jie Yao, Jiang Zhong, Yangyang Kang, Jingyuan Zhang, Changlong Sun, Xin Zhang, Fengmao Lv, Li Jin

Adversarial Training for Code Retrieval with Question-Description Relevance Regularization (2020.findings-emnlp)

Challenge:	Existing methods for key information extraction are based on a limited set of entity categories and fixed layouts.
Approach:	They propose a large-scale, human-annotated dataset for key information extraction . it is based on a human-annotated layout and 1,162 entity categories . they propose 'parallel pointer-based network' that leverages implicit relationships .
Outcome:	Experiments on widely-used datasets show that the proposed model outperforms state-of-the-art methods while maintaining fast inference speeds.

Copied to clipboard

Jie Zhao, Huan Sun

TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems (2026.findings-acl)

Challenge:	Existing methods for code retrieval are based on question-description relevance . code retrievals are a key task aiming to match natural and programming languages .
Approach:	They propose to use question-description relevance to regularize adversarial learning for code retrieval . they adapt a simple adversarial learning technique to generate difficult code snippets .
Outcome:	The proposed method can improve the performance of state-of-the-art models on large-scale code retrieval datasets of two programming languages.

Copied to clipboard

Rui Sun, Jie Ding, Chenghua Gong, Tianjun Gu, Yihang Jiang, Juyuan Zhang, Liming Pan, Linyuan Lü

Dialogue Systems & Conversational Agents

Challenge:	Existing communication topologies rely on spatio-temporal dialogues, which incur high latency and computation.
Approach:	They propose a framework for one-shot Topology generation with Diverse Interaction Modes that enables agents to construct heterogeneous communication without iterative coordination.
Outcome:	The proposed framework reduces total token consumption by 46.41% while improving average performance by 1.50% over state-of-the-art methods.

BMInf: An Efficient Toolkit for Big Model Inference and Tuning (2022.acl-demo)

Copied to clipboard

Xu Han, Guoyang Zeng, Weilin Zhao, Zhiyuan Liu, Zhengyan Zhang, Jie Zhou, Jun Zhang, Jia Chao, Maosong Sun

FewRel 2.0: Towards More Challenging Few-Shot Relation Classification (D19-1)

Challenge:	Recent years, pre-trained language models (PLMs) have achieved promising results on various NLP tasks.
Approach:	They propose an open-source toolkit for big model inference and tuning which can support big model tuning at extremely low computation cost.
Outcome:	The proposed toolkit can support big model inference and tuning at extremely low computation cost.

Copied to clipboard

Tianyu Gao, Xu Han, Hao Zhu, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Enhancing Byzantine-Resistant Aggregations with Client Embedding (2024.findings-emnlp)

Challenge:	Few-shot domain adaptation and NOTA detection are two real-world challenges for few-shot relation classification models.
Approach:	They propose a task to investigate two aspects of few-shot relation classification models . they build upon the FewRel dataset by adding a new test set in a different domain .
Outcome:	The proposed task can evaluate few-shot domain adaptation and few- shot none-of-the-above detection on a new domain and NOTA relation choice.

Copied to clipboard

Zhiyuan Zhang, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling (2025.acl-long)

Challenge:	Existing Byzantine-resistant aggregations detect poisonous clients but cannot defend against backdoor injection by malicious attackers in natural language tasks.
Approach:	They propose to embed client parameters to enhance Byzantine-resistant aggregations.
Outcome:	The proposed client embeddings detect poisonous clients and discard them . the proposed algorithms can't defend against backdoor injection by malicious attackers in natural language tasks .

Copied to clipboard

Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Sun Ao, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jie Zhou, Hao Zhou, Jianyong Wang, Maosong Sun, Zhiyuan Liu

Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters (2026.acl-long)

Challenge:	Speculative sampling is an efficient way to accelerate the auto-regressive generation process of large language models.
Approach:	They propose a frequency-ranked speculative sampling framework that optimizes draft candidate selection through vocabulary space compression.
Outcome:	Experiments show that FR-Spec reduces LM Head computation overhead by 75% while ensuring the equivalence of the final output distribution.

Copied to clipboard

Zhiyu Xu, Lean Wang, Yuanxin Liu, Lei Li, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

MoEfication: Transformer Feed-forward Layers are Mixtures of Experts (2022.findings-acl)

Challenge:	Existing research lacks systematic analysis of the applicability and methodology of cross-modal skill injection.
Approach:	They investigate the applicability and methodology of cross-modal skill injection by integrating a domain-expert LLM into a VLM.
Outcome:	The proposed method enables transfer of domain-specific expertise from Large Language Models (LLMs) to VLMs without incurring additional training data requirements or significant computational overhead.

Copied to clipboard

Zhengyan Zhang, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision (2021.acl-long)

Challenge:	Recent work has shown that feed-forward networks (FFNs) in pre-trained Transformers are a key component, storing various linguistic and factual knowledge.
Approach:	They propose to convert a model into its MoE version with the same parameters and build expert routers to decide which experts will be used for each input.
Outcome:	The proposed model can use 10% to 30% of FFN parameters while maintaining over 95% original performance.

Copied to clipboard

Si Sun, Yingzhuo Qian, Zhenghao Liu, Chenyan Xiong, Kaitao Zhang, Jie Bao, Zhiyuan Liu, Paul Bennett

Low-Resource NLP

Challenge:	Neural information retrieval models have shown advanced results in many ranking scenarios where massive relevance labels or clickthrough data are available.
Approach:	They propose a domain adaptive learning method that generalizes Neu-IR models from label-rich source domains to few-shot target domains.
Outcome:	The proposed method improves the few-shot ranking accuracy of Neu-IR models on three TREC benchmarks in the web, news, and biomedical domains.

On Transferability of Prompt Tuning for Natural Language Processing (2022.naacl-main)

Copied to clipboard

Yusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Huadong Wang, Kaiyue Wen, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou, Maosong Sun, Jie Zhou

Plug-and-Play Knowledge Injection for Pre-trained Language Models (2023.acl-long)

Challenge:	Pre-trained language models (PLMs) can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but require much more training time than fine-timing.
Approach:	They empirically investigate the transferability of soft prompts across different downstream tasks and PLMs to determine what decides prompt transferability.
Outcome:	The proposed method can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but requires much more training time than fine-timing.

Copied to clipboard

Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Huadong Wang, Deming Ye, Chaojun Xiao, Xu Han, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2025.acl-long)

Challenge:	Existing knowledge injection methods are not suitable for enhancing pre-trained language models with external knowledge bases.
Approach:	They propose a plug-and-play knowledge injection method where knowledge bases are injected into frozen existing downstream models by a knowledge plugin.
Outcome:	The proposed method improves the performance of knowledge injection on knowledge-driven tasks while keeping model parameters frozen.

Copied to clipboard

Yifan Xu, Xiao Liu, Xueqiao Sun, Siyi Cheng, Hao Yu, Hanyu Lai, Shudan Zhang, Dan Zhang, Jie Tang, Yuxiao Dong

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)

Challenge:	Existing studies on Android agents lack systematic research on open-source and closed-source models.
Approach:	They propose a framework for Android agents that includes an operation environment and a reproducible benchmark.
Outcome:	The proposed framework lifts the success rate of open-source LLMs and LMMs from 4.59% to 21.50% for LLM and 1.93% to 13.28% for LMM.

Copied to clipboard

Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun

Open-Set Living Need Prediction with Large Language Models (2025.findings-acl)

Challenge:	Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks.
Approach:	They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions.
Outcome:	The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning.

Copied to clipboard

Xiaochong Lan, Jie Feng, Yizhou Sun, Chen Gao, Jiahuan Lei, Xinleishi Xinleishi, Hengliang Luo, Yong Li

RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models (2021.emnlp-main)

Challenge:	Existing approaches to living need prediction treat it as a closed-set classification problem, severely limiting their ability to capture diversity and complexity of living needs.
Approach:	They propose a system leveraging large language models for unrestricted need prediction that leverages Maslow's hierarchy of needs to align predictions with human living needs.
Outcome:	The proposed system outperforms closed-set approaches on need-based life service recall by an average of 19.37% on real-world datasets.

Copied to clipboard

Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, Xu Sun

Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models (2025.findings-acl)

Challenge:	Backdoor attacks are a serious threat to the safety of reusing deep neural networks (DNNs).
Approach:	They propose an efficient online defense mechanism based on robustness-aware perturbations to distinguish poisoned and clean samples to defend against backdoor attacks on natural language processing models.
Outcome:	The proposed method achieves better defending performance and lower computational costs than existing defense methods.

Copied to clipboard

Qingyu Ren, Jie Zeng, Qianyu He, Jiaqing Liang, Yanghua Xiao, Weikang Zhou, Zeye Sun, Fei Yu

Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models (2023.findings-emnlp)

Challenge:	In real-world scenarios, user instructions often contain soft constraints, which are semantically related and cannot be rule-based verified, posing challenges for large language models.
Approach:	They propose a pipeline to construct datasets with high-quality outputs for instructions containing soft constraints automatically and use Direct Preference Optimization (DPO) as the training method.
Outcome:	The proposed model improves the LLMs' soft constraint following ability by using direct preference optimization (DPO) and constraint quantity.

Copied to clipboard

Weize Chen, Xiaoyue Xu, Xu Han, Yankai Lin, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou

RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents (2025.acl-long)

Challenge:	Parameter-shared pre-trained language models (PLMs) have emerged as a successful approach in resource-constrained environments.
Approach:	They propose a method to enhance the inference efficiency of parameter-shared PLMs by pre-training models that can achieve even greater acceleration.
Outcome:	The proposed method improves inference efficiency on autoregressive and autoencoding models.

Copied to clipboard

Pinyi Zhang, Siyu An, Lingfeng Qiao, Yifei Yu, Jingyang Chen, Jie Wang, Di Yin, Xing Sun, Kai Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing research has focused on role-playing agents’ ability to portray specified characters, but their ability to advance the plot requires substantial improvements to deliver more engaging interaction.
Approach:	They propose a role-playing framework to evaluate and enhance the plot-progression capabilities of role-players.
Outcome:	The proposed framework improves RPAs’ ability to time plot developments and yields a significant increase in conversation turns and sustained higher arousal levels.

Graph Neural Networks with Generated Parameters for Relation Extraction (P19-1)

Copied to clipboard

Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-Seng Chua, Maosong Sun

An Empirical Study of Many-to-Many Summarization with Large Language Models (2025.acl-long)

Challenge:	Existing graph neural networks can only process multi-hop relational reasoning on pre-defined graphs and cannot be directly applied in natural language relational reasoning.
Approach:	They propose a graph neural network with generated parameters using natural language sentences as inputs.
Outcome:	The proposed model can process relational reasoning on graphs and in natural language processing tasks.

Copied to clipboard

Jiaan Wang, Fandong Meng, Zengkui Sun, Yunlong Liang, Yuxuan Cao, Jiarong Xu, Haoxiang Shi, Jie Zhou

Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA (2026.acl-industry)

Challenge:	Recent studies have shown that large language models (LLMs) have strong multilingual abilities, giving them the potential to perform M2MS in real applications.
Approach:	They propose to use many-to-many summarization (M2MS) to generate a brief summary in any language given a document also in any other language.
Outcome:	The proposed model outperforms zero-shot LLMs in terms of automatic evaluations.

Copied to clipboard

Wenwei Li, Ming Xu, Tianle Xia, Lingxiang Hu, Yiding Sun, Linfang Shang, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang

Structured Data in NLP

Challenge:	Existing methods for QA in industrial environments are inherently relational and often updated.
Approach:	They propose a framework that optimizes retrieval and generation through two components: Graph-aware Retrieval and evidence-constrained reinforcement learning.
Outcome:	Experiments on an internal advertising QA dataset show consistent gains across expert-judged dimensions including accuracy, completeness, safety, and URL validity.

Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation (P19-1)

Copied to clipboard

Shuming Ma, Pengcheng Yang, Tianyu Liu, Peng Li, Jie Zhou, Xu Sun

Text Generation

Challenge:	Existing methods for table-to-text generation use encoder-decoder framework, but lack of large parallel data is a problem for many domains.
Approach:	They propose a model to separate table-to-text generation into two stages: key fact prediction and surface realization.
Outcome:	The proposed model achieves 27.34 BLEU score with only 1,000 parallel data, while the baseline model only achieves 9.71 BLUE score.

TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation (2025.emnlp-main)

Copied to clipboard

Daiye Miao, Yufang Liu, Jie Wang, Changzhi Sun, Yunke Zhang, Demei Yan, Shaokang Dong, Qi Zhang, Yuanbin Wu

Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts (2025.emnlp-main)

Challenge:	Existing studies have shown that LoRA introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders the effectiveness of fine-tuning.
Approach:	They propose a method that leverages importance information from the pretrained model’s weights to mitigate LoRA redundancy.
Outcome:	The proposed method significantly reduces the number of trainable parameters required for task adaptation while providing a task-aligned perspective for LoRA redundancy reduction.

Copied to clipboard

Yifei Yu, Qian-Wen Zhang, Lingfeng Qiao, Di Yin, Fang Li, Jie Wang, Chen Zeng Xi, Suncong Zheng, Xiaolong Liang, Xing Sun

DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models (2024.emnlp-main)

Challenge:	Recent models have extended Corresponding Author. context lengths to millions of tokens while maintaining reasoning and comprehension capabilities.
Approach:	They propose a benchmark to evaluate the ability of large language models to extract sequential information items from long contexts.
Outcome:	The proposed model achieves maximum accuracy of 63.50% on six well-known LLMs.

Copied to clipboard

Ranchi Zhao, Zhen Thai, Yifan Zhang, Shengding Hu, Jie Zhou, Yunqi Ba, Jie Cai, Zhiyuan Liu, Maosong Sun

BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving (2025.acl-long)

Challenge:	Large Language Models (LLMs) are pre-trained on vast datasets composed of billions of tokens harvested from diverse text sources.
Approach:	They propose a data engineering method to refine the pretraining corpus through data rating, tagging and editing.
Outcome:	The proposed method improves the quality of the pretraining corpus by enhancing 100 billion tokens of the training corpus.

Copied to clipboard

Ran Xin, Chenguang Xi, Jie Yang, Feng Chen, Hang Wu, Xia Xiao, Yifan Sun, Shen Zheng, Ming Ding

WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Challenge:	Existing approaches to theorem proving in large language models rely on value functions and/or Monte Carlo Tree Search (MCTS), but the potential of simpler methods like Best-First Tree Search remains underexplored.
Approach:	They propose a scalable expert iteration framework that implements strategic data filtering at each expert iteration round, excluding problems solvable via beam search node expansion to focus on harder cases.
Outcome:	The proposed framework achieves a state-of-the-art score of 72.95 on the MiniF2F test set and challenges the perceived necessity of complex tree search methods.

Copied to clipboard

Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou

Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction (2021.findings-acl)

Challenge:	Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach:	They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome:	The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .

Copied to clipboard

Tianyu Gao, Xu Han, Yuzhuo Bai, Keyue Qiu, Zhiyu Xie, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs (2026.findings-acl)

Challenge:	Distantly supervised relation extraction (RE) has attracted much attention in the past few years . previous methods to evaluate models manually or directly on autolabeled data have produced inaccurate evaluations .
Approach:	They propose to use distant supervision to generate large-scale autolabeled data . they build manually-annotated test sets for two DS-RE datasets and evaluate models .
Outcome:	The proposed method produces 53% wrong labels at the entity pair level in the popular NYT10 dataset.

Copied to clipboard

Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, Binbin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong, Jian Wang, Peng Wei, Jinjie Gu

Rethinking Stealthiness of Backdoor Attack against NLP Models (2021.acl-long)

Challenge:	Existing rankers excel in lexical-matching scenarios, while they struggle with complex queries requiring deep reasoning.
Approach:	They propose a new paradigm that balances flexibility and context awareness to unlock the full potential of groupwise reranking.
Outcome:	The proposed approach achieves a state-of-the-art 65.2 NDCG@10 on BRIGHT and surpasses baselines by 2.1 points on R2MED while delivering a 6.4 inference speedup.

Copied to clipboard

Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, Xu Sun

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following (2026.acl-long)

Challenge:	Existing backdoor attacks are not stealthy to system deployers or users.
Approach:	They propose a novel backdoor attack method based on negative data augmentation and modifying word embeddings that is much stealthier while maintaining pretty good attacking performance.
Outcome:	The proposed method is much stealthier while maintaining pretty good attacking performance.

Copied to clipboard

Qingyu Ren, Qianyu He, Powei Chang, Jie Zeng, Zeye Sun, Fei Yu, Jiaqing Liang, Yanghua Xiao

UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs (2024.acl-demos)

Challenge:	Existing reinforcement learning approaches suffer from dependency on external supervision and sparse reward signals from multi-constraint tasks.
Approach:	They propose a self-supervised reinforcement learning framework that eliminates dependency on external supervision by deriving reward signals directly from instructions and generating pseudo-labels for reward model training.
Outcome:	The proposed framework achieves strong improvements across 3 in-domain and 5 out-of-domain datasets while maintaining computational efficiency.

Copied to clipboard

Chaoqun He, Renjie Luo, Shengding Hu, Ranchi Zhao, Jie Zhou, Hanghao Wu, Jiajie Zhang, Xu Han, Zhiyuan Liu, Maosong Sun

Fully Hyperbolic Neural Networks (2022.acl-long)

Challenge:	Existing evaluation platforms are complex and poorly modularized, hindering seamless incorporation into researcher’s workflows.
Approach:	They propose a lightweight evaluation framework characterized by lightweight, comprehensiveness, modularity, and efficiency that integrates models, data, and metrics into a unified evaluation workflow.
Outcome:	The proposed evaluation framework is lightweight, comprehensive, modular, and efficient.

Copied to clipboard

Weize Chen, Xu Han, Yankai Lin, Hexu Zhao, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Challenge:	Existing hyperbolic neural networks encode features in the hyperbolical space yet formalize most of their operations in the tangent space.
Approach:	They propose a fully hyperbolic framework to build hyperbolical networks based on the Lorentz model by adapting Lorentzer transformations to formalize essential operations of neural networks.
Outcome:	The proposed framework has better performance on four NLP tasks compared with existing hyperbolic models .

Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules (2023.findings-emnlp)

Copied to clipboard

Chaojun Xiao, Yuqi Luo, Wenbin Zhang, Pengle Zhang, Xu Han, Yankai Lin, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou

Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning (2023.emnlp-main)

Challenge:	Large language models (LLMs) have been successful on NLP tasks but require huge parameter sizes and computational resources.
Approach:	They propose a parameter-efficient acceleration method that enhances computational efficiency through plug-and-play compression plugins.
Outcome:	The proposed method saves 53% computational costs using only 0.9% additional parameters with a performance drop of less than 2%.

Copied to clipboard

Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun

HMEAE: Hierarchical Modular Event Argument Extraction (D19-1)

Challenge:	In-context learning (ICL) is a promising capability for large language models (LLMs) but its underlying mechanism remains unexplored.
Approach:	They propose a demonstration compression technique to expedite inference and an analysis framework for diagnosing ICL errors in GPT2-XL.
Outcome:	The proposed method improves ICL performance and expedites inference.

Copied to clipboard

Xiaozhi Wang, Ziqi Wang, Xu Han, Zhiyuan Liu, Juanzi Li, Peng Li, Maosong Sun, Jie Zhou, Xiang Ren

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)

Challenge:	Existing event extraction methods classify each argument role independently, ignoring conceptual correlations between different argument roles.
Approach:	They propose a Hierarchical Modular Event Argument Extraction model to provide inductive bias from the concept hierarchy of event argument roles.
Outcome:	The proposed model outperforms existing methods on real-world datasets and shows that it leverages useful knowledge from the concept hierarchy.

Copied to clipboard

Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo

Uncertainty Quantification for In-Context Learning of Large Language Models (2024.naacl-long)

Challenge:	Existing research on reinforcement learning for LLMs under data scarcity has not been unified.
Approach:	They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric.
Outcome:	The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area.

Copied to clipboard

Chen Ling, Xujiang Zhao, Xuchao Zhang, Wei Cheng, Yanchi Liu, Yiyou Sun, Mika Oishi, Takao Osaki, Katsushi Matsuda, Jie Ji, Guangji Bai, Liang Zhao, Haifeng Chen

Joint Optimization of Training Data and Policy in RLHF (2026.findings-acl)

Challenge:	Existing studies on in-context learning have focused on quantifying the uncertainty associated with the model's response, but they neglect the complexity of the LLM and the uniqueness of in-constitut learning.
Approach:	They propose a method to quantify the uncertainty associated with in-context learning and propose corresponding estimation method to quantify both types of uncertainties.
Outcome:	The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion.

Copied to clipboard

Zhuohao Yu, Jiali Zeng, Weizheng Gu, Mengyuan Sun, Yidong Wang, Fandong Meng, Jie Zhou, Shikun Zhang, Wei Ye

Challenge:	JODP optimizes policies on fixed training inputs, limiting the diversity of learning signals.
Approach:	They propose a framework where policy generates improved variants of training problems to enhance its own learning.
Outcome:	The proposed framework improves on safety alignment tasks by allowing 4B models to reach 8B model performance with less than 1% additional computational overhead.

Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training (2026.acl-industry)

Copied to clipboard

Tianle Xia, Ming Xu, Lingxiang Hu, Yiding Sun, Wenwei Li, Linfang Shang, Liqun Liu, Peng Shu, Huan Yu, Jie Jiang

From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models (2022.findings-emnlp)

Challenge:	Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet traditional singleround retrieval struggles with complex multistep reasoning.
Approach:	They propose a framework that introduces path-centric reward shaping for agentic RAG training.
Outcome:	The proposed framework improves on existing methods with an average accuracy gain of 7.7 points.

Copied to clipboard

Lei Li, Yankai Lin, Xuancheng Ren, Guangxiang Zhao, Peng Li, Jie Zhou, Xu Sun

ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning (2021.acl-long)

Challenge:	Existing models for natural language processing (NLP) are fine-tuned and released for research and deployments.
Approach:	They propose a PLM reuse paradigm that merges teacher-PLM knowledge into a student model.
Outcome:	The proposed paradigm can reduce the computational cost and environmental side-effects of retraining the PLM from scratch.

Copied to clipboard

Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun, Jie Zhou

CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the Wild (2021.emnlp-main)

Challenge:	Existing pre-training objectives do not explicitly model relational facts in text . Experimental results show that ERICA can improve typical PLMs on several language understanding tasks, including relation extraction, entity typing and question answering.
Approach:	They propose a contrastive learning framework ERICA to obtain a deep understanding of entities and relations in text.
Outcome:	The proposed framework can improve PLMs on several language understanding tasks, especially under low-resource settings.

Copied to clipboard

Yuan Yao, Jiaju Du, Yankai Lin, Peng Li, Zhiyuan Liu, Jie Zhou, Maosong Sun

ONSEP: A Novel Online Neural-Symbolic Framework for Event Prediction Based on Large Language Model (2024.findings-acl)

Challenge:	Existing relation extraction methods focus on extracting relational facts between entity pairs within single sentences or documents.
Approach:	They present a problem of cross-document relation extraction (CRE) using human annotations.
Outcome:	The proposed dataset is the first human-annotated cross-document RE dataset . it shows that it is challenging to existing RE methods including strong BERT-based models.

Copied to clipboard

Xuanqing Yu, Wangtao Sun, Jingwei Li, Kang Liu, Chengbao Liu, Jie Tan

An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learning (2022.coling-1)

Challenge:	TKGF is a technique that requires experience during testing and relying on a single short-term history.
Approach:	They propose a framework that integrates dynamic causal rule mining and dual history augmented generation to enhance event prediction.
Outcome:	The proposed framework shows significant performance improvements across diverse datasets and significantly improves Hit@k.

Copied to clipboard

Shaobin Chen, Jie Zhou, Yuling Sun, Liang He

HPSS: Heuristic Prompting Strategy Search for LLM Evaluators (2025.findings-acl)

Challenge:	Recent contrastive learning methods keep positive pairs similar and push negative pairs apart, which leads to redundant information in sentence embeddings.
Approach:	They propose a contrastive learning approach which maximizes mutual information and minimizes the information entropy between positive and negative instances.
Outcome:	The proposed model outperforms all previous competitors on supervised and unsupervised tasks.

Copied to clipboard

Bosi Wen, Pei Ke, Yufei Sun, Cunxiang Wang, Xiaotao Gu, Jinfeng Zhou, Jie Tang, Hongning Wang, Minlie Huang

Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch (2025.acl-long)

Challenge:	Existing efforts to optimize text evaluation prompts neglect the combinatorial impact of multiple factors, leading to insufficient optimization of the evaluation pipeline.
Approach:	They propose to integrate 8 key factors for evaluation prompts and integrate them into an algorithm that searches for well-behaved prompting strategies for LLM evaluators.
Outcome:	The proposed method outperforms existing methods and human-designed evaluation prompts on four evaluation tasks.

Copied to clipboard

Xueru Wen, Jie Lou, Zichao Li, Yaojie Lu, XingYu XingYu, Yuqiu Ji, Guohai Xu, Hongyu Lin, Ben He, Xianpei Han, Le Sun, Debing Zhang

Challenge:	Existing Chinese resources are small in scale and limited to specific domains, making them insufficient for LLM post-training.
Approach:	They propose a Chinese-annotated reward model and a preference dataset to address this gap . they evaluate Chinese RMs on CheemsBench and construct an RM that captures human preferences .
Outcome:	The proposed RM achieves state-of-the-art performance on CheemsBench and CheeMePreference.

LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Copied to clipboard

Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen

Continual Relation Learning via Episodic Memory Activation and Reconsolidation (2020.acl-main)

Challenge:	a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach:	They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome:	The proposed library is based on extensive experiments in a variety of evaluation settings.

Copied to clipboard

Xu Han, Yi Dai, Tianyu Gao, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Challenge:	Existing methods to learn incessantly emerging novel relations are overfitting the few memorized examples of old relations, causing confusion among existing relations.
Approach:	They introduce episodic memory activation and reconsolidation (EMAR) to continual relation learning.
Outcome:	The proposed method outperforms state-of-the-art models in catastrophic forgetting old relations.

Is “hot pizza” Positive or Negative? Mining Target-aware Sentiment Lexicons (2021.eacl-main)

Copied to clipboard

Jie Zhou, Yuanbin Wu, Changzhi Sun, Liang He

Sentiment Analysis

Challenge:	Existing sentiment lexicons assume words’ sentiments are invariant within a domain, but this assumption is weak for fine-granularity analyses of text sentiments.
Approach:	They propose a "perturb-and-see" method to extract commonsense sentiments from large-scale datasets by binding a word's sentiment to its collocation words instead of domain labels.
Outcome:	The proposed framework is able to achieve highly competitive performances on the unsupervised opinion relation extraction task.

Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following (2025.findings-acl)

Copied to clipboard

Jie Zeng, Qianyu He, Qingyu Ren, Jiaqing Liang, Weikang Zhou, Zeye Sun, Fei Yu, Yanghua Xiao

Challenge:	Existing large language models struggle to follow multi-constraint instructions in real-world applications.
Approach:	They propose to quantify the difficulty distribution of constraints by a novel Difficulty Distribution Index (CDDI) they find that LLMs are more performant when presented with constraints in a “hard-to-easy” order.
Outcome:	The proposed model is more performant when presented with constraints in a “hard-to-easy” order, compared with existing models with different architectures and sizes of parameters.

CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)

Copied to clipboard

Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying, Shu Zhao

Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Parameter-Efficient Tuning (2022.findings-emnlp)

Challenge:	Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios.
Approach:	They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions.
Outcome:	The proposed framework improves generalization and realism of large language models under complex and irregular table conditions.

Copied to clipboard

Jing Yi, Weize Chen, Yujia Qin, Yankai Lin, Ning Ding, Xu Han, Zhiyuan Liu, Maosong Sun, Jie Zhou

Improving Contextual Query Rewrite for Conversational AI Agents through User-preference Feedback Learning (2023.emnlp-industry)

Challenge:	Existing delta tuning algorithms freeze most of the parameters and only optimize minimal adaptive parameters.
Approach:	They propose to decompose DETs into a unified optimization subspace and conduct optimization within the subspace.
Outcome:	The proposed DETs achieve comparable performance to the original DET and can be transferred to another DET with non-trivial performance.

Copied to clipboard

Zhongkai Sun, Yingxue Zhou, Jie Hao, Xing Fan, Yanbin Lu, Chengyuan Ma, Wei Shen, Chenlei Guo

Natural Language Interfaces

Challenge:	Contextual query rewriting (CQR) is a crucial component in Conversational AI agents, leveraging contextual information from previous user-agent conversations to improve comprehension of current user intent.
Approach:	They propose a framework to enhance the CQR model's capability in generating user preference-aligned rewrites.
Outcome:	The proposed framework improves the CQR model's ability to generate user preference-aligned rewrites.

AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts (2026.acl-long)

Copied to clipboard

Keyu Li, Junhao Shi, Yang Xiao, Mohan Jiang, Jie Sun, Yunze Wu, Dayuan Fu, Shijie Xia, Xiaojie Cai, Tianze Xu, Weiye Si, Wenjie Li, Dequan Wang, Pengfei Liu

Challenge:	Existing benchmarks focus on single agentic capability, failing to capture long-horizon real-world scenarios.
Approach:	They propose a benchmark that evaluates 6 agentic capabilities across 32 real-world scenarios.
Outcome:	Experiments show that closed-source models outperform open-source model (48.4% vs 32.1%) integrating models with advanced scaffolds to form autonomous agents is a paradigm shift.

ELLE: Efficient Lifelong Pre-training for Emerging Data (2022.findings-acl)

Copied to clipboard

Yujia Qin, Jiajie Zhang, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Learning from Context or Names? An Empirical Study on Neural Relation Extraction (2020.emnlp-main)

Challenge:	Existing pre-trained language models are typically trained with static data, ignoring that streaming data of various sources may continuously grow.
Approach:	They propose to use function preserved model expansion to expand existing PLM's width and depth to improve efficiency of knowledge acquisition.
Outcome:	The proposed model improves pre-training efficiency and performance over existing models on BERT and GPT.

Copied to clipboard

Hao Peng, Tianyu Gao, Xu Han, Yankai Lin, Peng Li, Zhiyuan Liu, Maosong Sun, Jie Zhou

More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection (2026.findings-acl)

Challenge:	Existing datasets may leak shallow heuristics via entity mentions, thus contributing to the high performance on RE benchmarks.
Approach:	They propose an entity-masked contrastive framework for relation extraction to gain a deeper understanding on textual context and type information while avoiding rote memorization of entities.
Outcome:	The proposed framework improves the effectiveness and robustness of neural models in different RE scenarios.

Copied to clipboard

Runze Sun, Yu Zheng, Zexuan Xiong, Zhongjin Qu, Lei Chen, Jie Zhou, Jiwen Lu

SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs (2026.findings-acl)

Challenge:	Existing systems struggle with multimodal content where the emergent meaning transcends the aggregation of individual modalities.
Approach:	They propose a framework to characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks on H-VLI and on established benchmarks.

Copied to clipboard

Jie Sun, Yu Liu, Lu Han, Qiwen Deng, Xiang Shu, Yang Xiao, Lintao Ma, Xingyu Lu, Jun Zhou, Pengfei Liu, Jiancan Wu, Xiang Wang

Dynamic Knowledge Distillation for Pre-trained Language Models (2021.emnlp-main)

Challenge:	Existing large-scale large-context models suffer from performance degradation when processing long numerical sequences.
Approach:	They propose a framework to mitigate attention dispersion by strategically inserting separator tokens into the model to recalibrat attention to local segments while preserving global context.
Outcome:	The proposed framework improves accuracy and reduces inference token consumption by 16.4% on 9 widely-adopted LLMs.

Copied to clipboard

Lei Li, Yankai Lin, Shuhuai Ren, Peng Li, Jie Zhou, Xu Sun

CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade (2021.findings-emnlp)

Challenge:	Existing methods conduct knowledge distillation statically, e.g., student model aligns output distribution to teacher model on pre-defined training dataset.
Approach:	They propose a dynamic knowledge distillation that empowers the student to adjust the learning procedure according to its competency . they find it is promising and provide discussions on potential future directions towards more efficient methods .
Outcome:	The proposed method can boost student model performance while accelerating training . the proposed method reduces memory usage and accelerates model inference .

Copied to clipboard

Lei Li, Yankai Lin, Deli Chen, Shuhuai Ren, Peng Li, Jie Zhou, Xu Sun

DocRED: A Large-Scale Document-Level Relation Extraction Dataset (P19-1)

Challenge:	Experimental results show that CascadeBERT can achieve an overall 15% improvement under 4x speed-up compared with existing dynamic early exiting methods on six classification tasks.
Approach:	They propose a framework which emits predictions in internal layers without passing through the entire model.
Outcome:	The proposed framework can achieve 15% improvement under 4x speed-up compared with existing methods on six classification tasks yielding more calibrated and accurate predictions.

Copied to clipboard

Yuan Yao, Deming Ye, Peng Li, Xu Han, Yankai Lin, Zhenghao Liu, Zhiyuan Liu, Lixin Huang, Jie Zhou, Maosong Sun