Papers by Zhi Li

Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency (2024.lrec-main)

Challenge:	Experimental results show that VideoEraser outperforms prior methods regarding efficacy, integrity, fidelity, robustness, and generalizability.
Approach:	They propose a training-free framework that prevents T2V diffusion models from generating videos with undesirable concepts even when explicitly prompted with those concepts.
Outcome:	The proposed framework outperforms existing methods in erasure, celebrity erasion, and explicit content erasing tasks.

Copied to clipboard

Taiji Li, Zhi Li, Yin Zhang

Information Extraction & Text Mining

Challenge:	Abstractive summarization models (LLMs) have demonstrated impressive performance in various tasks, but they are still suffering from factual inconsistency problem called hallucination.
Approach:	They propose to improve the faithfulness of large language models by impelling them to process the entire article more fairly and faithfully.
Outcome:	The proposed strategy improves the faithfulness of large language models in summarization while maintaining their fluency and informativeness.

Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories (2026.acl-long)

Copied to clipboard

Peiyang Liu, Zhirui Chen, Xi Wang, Di Liang, Youru Li, Zhi Cai, Wei Ye

I-AM-G: Interest Augmented Multimodal Generator for Item Personalization (2024.emnlp-main)

Challenge:	MCTS methods retain only the single highest-reward trajectory, discarding comparative signals present in the many explored paths.
Approach:	They propose a framework that transforms supervision extraction into a synthesis procedure.
Outcome:	The proposed framework matches or exceeds baselines on 60K CRPS-synthesized examples on out-of-domain benchmarks.

Copied to clipboard

Xianquan Wang, Likang Wu, Shukang Yin, Zhi Li, Yanjiang Chen, Hufeng Hufeng, Yu Su, Qi Liu

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)

Challenge:	e-commerce and recommender systems lack a framework for personalized generation . a new framework extracts tags from multimodal information of items that the user has interacted with .
Approach:	They propose a framework that extracts tags from multimodal information and rewrites item description . they then use a decoupled text-to-text and image-to image retriever to search for similar item text .
Outcome:	The proposed framework can generate results aligned with user preferences . it can be used in e-commerce and recommender systems to win over diverse user base .

Copied to clipboard

Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang

Exploring Schema Generalizability of Text-to-SQL (2023.findings-acl)

Challenge:	Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs).
Approach:	They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories.
Outcome:	The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks.

Copied to clipboard

Jieyu Li, Lu Chen, Ruisheng Cao, Su Zhu, Hongshen Xu, Zhi Chen, Hanchong Zhang, Kai Yu

Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and Grounding (2024.findings-emnlp)

Challenge:	Existing text-to-SQL models are limited in their generalizability, despite their performance being over-estimated.
Approach:	They propose a framework to generate novel text-to-SQL data via automatic and synchronous (DS, SQL) pair altering.
Outcome:	The proposed framework generates text-to-SQL data via automatic and synchronous (DS, SQL) pair altering.

Copied to clipboard

Ziqi Wang, Chen Zhu, Zhi Zheng, Xinhang Li, Tong Xu, Yongyi He, Qi Liu, Ying Yu, Enhong Chen

UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings (2021.findings-emnlp)

Challenge:	Existing methods for fine-grained content extraction are limited by long-tailed distribution of textual entity categories and performance of object detectors.
Approach:	They propose a multi-granularity entity recognition module and a reranking module to integrate hierarchical information of entity categories, visual cues, and external textual resources collectively.
Outcome:	The proposed framework achieves state-of-the-art on the fine-grained content extraction task.

Copied to clipboard

Zhi Li, Yuchen Zhai, Chengyu Wang, Minghui Qiu, Kailiang Li, Yin Zhang

Self-Edit: Fault-Aware Code Editor for Code Generation (2023.acl-long)

Challenge:	Existing methods to reduce word embedding parameters ignore semantic information . existing methods do not consider semantic information, allowing for performance degradation .
Approach:	They propose a method that leverages semantic similarity with weight sharing to reduce dimensionality of word embeddings.
Outcome:	The proposed method reduces word embedding parameters by more than 11x on a standard English-German dataset.

Copied to clipboard

Kechi Zhang, Zhuo Li, Jia Li, Ge Li, Zhi Jin

ExploraCoder: Advancing Code Generation for Multiple Unseen APIs via Planning and Chained Exploration (2025.acl-long)

Challenge:	Existing Large language models (LLMs) have low pass rates and accuracy on competitive programming tasks.
Approach:	They propose a generate-and-edit approach that uses execution results of generated code from LLMs to improve code quality on competitive programming tasks.
Outcome:	The proposed method improves pass@1 by 89% on APPS-dev, 31% on apps-test, and 48% on HumanEval over nine popular code generation LLMs with parameter sizes ranging from 110M to 175B.

Copied to clipboard

Yunkun Wang, Yue Zhang, Zhen Qin, Chen Zhi, Binhua Li, Fei Huang, Yongbin Li, Shuiguang Deng

CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges (2024.acl-long)

Challenge:	Large language models face intrinsic limitations in coding with unseen APIs in training corpora.
Approach:	They propose a training-free framework that empowers LLMs to invoke multiple unseen APIs in code solution by planning a complex problem into several API invocation subtasks and experimenting with correct API usage at intermediate steps.
Outcome:	The proposed framework significantly improves performance for models lacking prior API knowledge, achieving 11.99% over retrieval-based approaches and 17.28% over pretraining-based methods in pass@10.

Copied to clipboard

Kechi Zhang, Jia Li, Ge Li, Xianjie Shi, Zhi Jin

PACE: Improving Prompt with Actor-Critic Editing for Large Language Model (2024.findings-acl)

Challenge:	Large Language Models excel in simple tasks such as generating standalone code units, but real-world software development often involves complex code repositories with complex dependencies and extensive documentation.
Approach:	They propose a novel LLM-based agent framework that employs external tools for effective repo-level code generation.
Outcome:	The proposed framework outperforms commercial products like Github Copilot in the humanEval benchmark and shows that it is adaptable and efficient across multiple code generation tasks.

Copied to clipboard

Yihong Dong, Kangcheng Luo, Xue Jiang, Zhi Jin, Ge Li

A Novel Matching Paradigm: Unified Generative and Discriminative LLM with Prompt Compression for Relevance Learning (2026.acl-industry)

Challenge:	Prompt with Actor-Critic Editing (PACE) for LLMs improves performance of different human-written prompts, resulting in significant performance discrepancies.
Approach:	They propose to use LLMs as actors and critics to enable automatic prompt editing by taking feedback from both actors performing prompt and criticizing response into account.
Outcome:	The proposed model improves the performance of human-written prompts by 98% and compares to high-quality human-writing prompts.

Copied to clipboard

Guoliang Zhao, Zixin Cui, Chao Ye, Dengwu He, Fei Huang, Yubo Liu, Shuanglong Li, Tzungren Kuo, Bin Ding, Shuang Zhang, null KunhongZhu, Zhi Guo, Liu Lin

TabularMath: Understanding Math Reasoning over Tables with Large Language Models (2026.findings-acl)

Challenge:	Existing approaches to matching use Large Language Models as feature extractors, underutilizing their full modeling capabilities.
Approach:	They propose a matching paradigm that integrates two-tower, single-towing, and generative tasks within a unified LLM framework via attention-mask partitioning.
Outcome:	The proposed model achieves superior performance and strong practical value in an industrial search engine.

Copied to clipboard

Shi-Yu Tian, Zhi Zhou, Wei Dong, Kun-Yang Yu, Ming Yang, Zi-Jian Cheng, Lan-Zhe Guo, Yu-Feng Li

Guide the Many-to-One Assignment: Open Information Extraction via IoU-aware Optimal Transport (2023.acl-long)

Challenge:	Mathematical reasoning has long been a key benchmark for evaluating large language models.
Approach:	They propose a framework that transforms math word problems into scalable tabular reasoning tasks.
Outcome:	The proposed framework transforms math word problems into scalable and verified tabular reasoning tasks.

Copied to clipboard

Kaiwen Wei, Yiran Yang, Li Jin, Xian Sun, Zequn Zhang, Jingyuan Zhang, Xiao Li, Linhao Zhang, Jintao Liu, Guo Zhi

Information Extraction & Text Mining

Challenge:	Open Information Extraction (OIE) aims to extract structured information from text without the limitations of close ontology.
Approach:	They propose a method to assign ground truth labels to parallelly generated tuple proposals . they leverage intersection-over-union (IoU) as assignment quality measurement .
Outcome:	The proposed method outperforms the state-of-the-art models on three benchmarks.

Focus-Constrained Attention Mechanism for CVAE-based Response Generation (2020.findings-emnlp)

Copied to clipboard

Zhi Cui, Yanran Li, Jiayi Zhang, Jianwei Cui, Chen Wei, Bin Wang

Text Generation

Challenge:	Existing models generate high-frequency but trivial responses such as "I don't know" or "I'm ok" due to the discrepancy in discourse-level information, standard models generate one-to-many relationships.
Approach:	They propose to transform coarse-grained discourse-level information into fine-grounded word-level knowledge by introducing a fine-grain focus signal and a focus-constrained attention mechanism to take full advantage of focus.
Outcome:	The proposed model can generate more diverse and informative responses compared with state-of-the-art models.

Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory (2025.acl-long)

Copied to clipboard

Yexiang Liu, Zekun Li, Zhi Fang, Nan Xu, Ran He, Tieniu Tan

Translate the Beauty in Songs: Jointly Learning to Align Melody and Translate Lyrics (2023.findings-emnlp)

Challenge:	Recent studies have shown that scaling test-time compute can also effectively improve reasoning.
Approach:	They propose a probabilistic method to efficiently predict scaling performance and identify the best prompting strategy under large sampling times.
Outcome:	The proposed method significantly improves the scaling performance of majority voting on large language models.

Copied to clipboard

Chengxi Li, Kai Fan, Jiajun Bu, Boxing Chen, Zhongqiang Huang, Zhi Yu

Machine Translation

Challenge:	Song translation requires both translation of lyrics and alignment of music notes . human translators of songs need to have a mastery of cultural traditions and the poetic usage of both source and target languages .
Approach:	They propose a model that can model lyric translation and lyrics-melody alignment . they use an encoder-decoder framework that can translate lyrics and determine number of aligned notes .
Outcome:	The proposed framework can translate lyrics and determine the number of aligned notes at each decoding step.

HiRoPE: Length Extrapolation for Code Models Using Hierarchical Position (2024.acl-long)

Copied to clipboard

Kechi Zhang, Ge Li, Huangzhao Zhang, Zhi Jin

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)

Challenge:	Existing LLMs are constrained by their pre-trained context lengths, leading to performance issues . elucidating this limitation, we propose a training-free solution to the context length limitation in LLM applications .
Approach:	They propose a method that integrates hierarchical rotary position embedding into LLMs without extra training costs.
Outcome:	The proposed method improves performance on language modeling and long code completion tasks.

Copied to clipboard

Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen

NeuroSym-Cal: Bridging the Reasoning-Execution Gap in Code Generation via Hierarchical Calibration (2026.findings-acl)

Challenge:	Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities.
Approach:	They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance.
Outcome:	The proposed method achieves a superior balance between downstream learning and general capability retention.

Copied to clipboard

Peiyang Liu, Yining Wang, Youru Li, Long Li, Zhi Cai, Wei Ye

Assist Non-native Viewers: Multimodal Cross-Lingual Summarization for How2 Videos (2022.emnlp-main)

Challenge:	Existing calibration methods rely on the assumption that consensus implies correctness . Existing methods fail under systematic errors, leading to miscalibrated high-confidence predictions.
Approach:	They propose a hierarchical calibration framework that measures confidence at two levels . they propose sensitivity analysis to measure local curvature of deductive process .
Outcome:	The proposed framework de-saturates overconfident errors and improves selective generation performance on OOD benchmarks.

Copied to clipboard

Nayu Liu, Kaiwen Wei, Xian Sun, Hongfeng Yu, Fanglong Yao, Li Jin, Guo Zhi, Guangluan Xu

KELE: A Multi-Agent Framework for Structured Socratic Teaching with Large Language Models (2025.findings-emnlp)

Challenge:	Existing multimodal summarization methods are limited to monolingual videos . a proposed task aims to generate cross-lingual summaries from multimodal inputs .
Approach:	They propose a task to generate cross-lingual summaries from multimodal inputs of videos . they propose fusion network that integrates multimodal and cross-linguistic information .
Outcome:	The proposed task outperforms existing methods on a reorganized How2 dataset on the reorganized How2 data set.

Copied to clipboard

Xian Peng, Pan Yuan, Dong Li, Junlong Cheng, Qin Fang, Zhi Liu

Dialogue Systems & Conversational Agents

Challenge:	Socratic teaching places high demands on teachers’ expertise and real-time feedback capabilities, making it difficult to scale in large educational settings.
Approach:	They propose a multi-agent framework for structured Socratic teaching with LLMs that integrates a structured SocRule and a consultant-teacher collaborative teaching mechanism.
Outcome:	The proposed framework outperforms existing LLMs in natural language generation and dialogue comprehension in the classroom.

Benchmarking Long-Context Language Models on Long Code Understanding (2025.acl-long)

Copied to clipboard

Jia Li, Xuyuan Guo, Lei Li, Kechi Zhang, Ge Li, Jia Li, Zhengwei Tao, Fang Liu, Chongyang Tao, Yuqi Zhu, Zhi Jin

AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking (2025.findings-emnlp)

Challenge:	Currently, long-context language models are limited by the lack of a rigorous evaluation framework for long code understanding.
Approach:	They propose to use a long code understanding benchmark LongCodeU to evaluate LCLMs' long code comprehension ability for practical applications.
Outcome:	The proposed benchmarks show that current LCLMs are limited in their long code understanding ability, particularly when the long code length is greater than 32K, falling far short of their claimed 128K to 1M context windows.

Copied to clipboard

Ding-Chu Zhang, Xiaowen Zhang, Yue Fei, Renjun Hu, Xiao-Wen Yang, Zhi Zhou, Baixuan Li, Yu-Feng Li, Xing Shi, Wei Lin

Information Retrieval

Challenge:	Existing automated generation methods exhibit Weak Applicability and Weak Scalability . existing methods are limited by their reliance on metadata from specific corpora .
Approach:	They propose an approach to generate scalable RAG benchmarks using corpus-agnostic methods . they propose a difficulty-guided metric that directs query evolution process .
Outcome:	The proposed approach evolves queries significantly more challenging than existing methods . it is able to dynamically increase difficulty, limiting scalability of the query .

AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models (2025.findings-acl)

Copied to clipboard

Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Wan Guanglu, Xunliang Cai, Zhi Zheng, Tong Xu

Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL (2021.findings-acl)

Challenge:	Existing multi-objective preference alignment methods for large language models face limitations such as auxiliary reward/reference models and computational complexity.
Approach:	They propose a framework that achieves dynamic balance across preference dimensions by using dimension-aware generation metrics as implicit rewards.
Outcome:	Empirical results show that AMoPO outperforms state-of-the-art methods by 28.5% .

Copied to clipboard

Zhi Chen, Lu Chen, Hanqi Li, Ruisheng Cao, Da Ma, Mengyue Wu, Kai Yu

VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning (2025.emnlp-main)

Challenge:	Recent work on Text-to-SQL for multi-turn dialogue has attracted great interest . current approaches mostly employ end-to end models and face data sparsity problems .
Approach:	They propose a decoupled multi-turn text-to-SQL framework where dialogue context is explicitly solved by an utterance rewrite model and a single-turn Text-toSQl parser are proposed.
Outcome:	The proposed method outperforms existing models on SParC and CoSQL datasets without annotated in-domain data.

Copied to clipboard

Shi-Yu Tian, Zhi Zhou, Kun-Yang Yu, Ming Yang, Lin-Han Jia, Lan-Zhe Guo, Yu-Feng Li

Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction (2021.acl-long)

Challenge:	Existing studies have improved the performance of Large language models on well-defined mathematical benchmarks, but they often overlook ill-defined problems.
Approach:	They develop a large-scale benchmark that contains over 5,000 ill-defined mathematical problems.
Outcome:	The proposed framework improves the accuracy of identifying unsolvable problems by at least 12% across different LLMs, thus achieving stronger robust mathematical reasoning ability.

Copied to clipboard

Kaiwen Wei, Xian Sun, Zequn Zhang, Jingyuan Zhang, Guo Zhi, Li Jin

MLeVLM: Improve Multi-level Progressive Capabilities based on Multimodal Large Language Model for Medical Visual Question Answering (2024.findings-acl)

Challenge:	Existing methods to extract event arguments focus on learning pair-wise information between arguments and the given trigger.
Approach:	They propose a framework to extract event-related arguments from a given event frame-level scope.
Outcome:	The proposed method achieves state-of-the-art on the RAMS dataset.

Copied to clipboard

Dexuan Xu, Yanyuan Chen, Jieyi Wang, Yue Huang, Hanpin Wang, Zhi Jin, Hongxing Wang, Weihua Yue, Jing He, Hang Li, Yu Huang

Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points (2025.findings-acl)

Challenge:	Existing MVQA models ignore multi-level progressive capabilities due to unspecific data and plain architecture.
Approach:	They propose a multi-level visual language model for medical visual question answering (MVQA) which covers multi- level questions and answers as well as reasoning processes from visual clues to semantic cognition.
Outcome:	The proposed model outperforms existing medical multimodal large language models on a multi-level instruction dataset and a feature alignment module.

Copied to clipboard

Kechi Zhang, Ge Li, Jia Li, Yihong Dong, Jia Li, Zhi Jin

Saber: Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model in Code Generation (2026.acl-long)

Challenge:	Current code generation models produce errors concentrated at specific error-prone points, affecting accuracy of code.
Approach:	They propose a framework that focuses preference optimization on error-prone areas . focused-DPO improves the accuracy and reliability of code generation by reducing common errors .
Outcome:	The proposed framework improves code generation by focusing on error-prone areas.

Copied to clipboard

Yihong Dong, Zhaoyu Ma, Xue Jiang, Zhiyuan Fan, Jiaru Qian, Yongmin Li, Jianha Xiao, Zhi Jin, Ge Li

Rethinking Repetition Problems of LLMs in Code Generation (2025.acl-long)

Challenge:	Diffusion language models (DLMs) offer advantages in parallel generation and bidirectional context modeling, but they face a critical trade-off between inference speed and output quality for tasks with strict structural constraints such as code generation.
Approach:	They propose an efficient sampling algorithm that reduces the number of tokens unmasked per step based on the model’s evolving confidence.
Outcome:	The proposed method improves Pass@1 accuracy by 1.9% while achieving 251.4% inference speedup.

Copied to clipboard

Yihong Dong, Yuchen Liu, Xue Jiang, Bin Gu, Zhi Jin, Ge Li

Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search (2024.findings-emnlp)

Challenge:	Recent studies have focused on content repetition, but structural repetition is a more prevalent problem in code generation.
Approach:	They propose a decoding approach that eliminates repetition problems in code generation by identifying grammar rules and strategically decaying the likelihood of critical tokens that contribute to repetitions.
Outcome:	The proposed approach outperforms baselines and humanEval benchmarks on CodeRepetEval dataset and MBPP benchmarks, effectively reducing repetitions and enhancing the quality of generated code.

Copied to clipboard

Li Chenglin, Qianglong Chen, Zhi Li, FengTao FengTao, Yicheng Li, Hao Chen, Fei Yu, Yin Zhang

Red Teaming Large Reasoning Models (2026.acl-long)

Challenge:	Extensive research has highlighted the quality of instruction data is essential for the success of this alignment.
Approach:	They propose a framework for iteratively improving existing instruction data by using Monte Carlo tree search to find suitable prompts that align the language model to effectively learn multiple skills.
Outcome:	The proposed framework improves the evaluation scores of seed instruction data, raising the average evaluation scores from 2.19 to 3.81.

Copied to clipboard

Jiawei Chen, Yang Yang, Chao Yu, Yu Tian, Zhi Cao, Xue Yang, Linghao Li, Hang Su, Zhaoxia Yin

LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English Writing (2025.acl-long)

Challenge:	Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, but they introduce safety and reliability risks, such as CoT-hijacking and prompt-induced inefficiencies.
Approach:	They propose a unified benchmark to assess the trustworthiness of Large Reasoning Models.
Outcome:	The proposed benchmark evaluates truthfulness, safety and efficiency on 26 models.

Copied to clipboard

Zhengxiang Wang, Veronika Makarova, Zhi Li, Jordan Kodner, Owen Rambow

Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models (2024.findings-acl)

Challenge:	a growing number of studies have indicated the general usefulness of LLMs for automated writing assessments.
Approach:	They propose a framework that evaluates LLMs' ability to provide scores and comments based on multiple assessment criteria.
Outcome:	The proposed framework is interpretable, cost-efficient, scalable, and reproducible . it is compared to existing methods that rely on manual judgments .

Copied to clipboard

Yihong Dong, Xue Jiang, Huanyu Liu, Zhi Jin, Bin Gu, Mengfei Yang, Ge Li

Cultural Concept Adaptation on Multimodal Reasoning (2023.emnlp-main)

Challenge:	Considering the vast size and wide-ranging sources of LLMs’ training data, it could explicitly or implicitly include test data.
Approach:	They propose a Contamination Detection via output Distribution (CDD) which detects data contamination only by identifying the peakedness of LLM's output distribution.
Outcome:	The proposed method improves performance by 21.8%-30.2% on humanEval and TED: trustworthy evaluation via output distribution.

Copied to clipboard

Zhi Li, Yin Zhang

Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs (2024.lrec-main)

Challenge:	Past methods focused on multilingual and multimodal capabilities, and the improvement of multicultural competence is still an unexplored problem.
Approach:	They propose an annotation-free method for cultural-concept adaptation and construct a concept mapping set to facilitate model's comprehension of cultural-consensual mappings.
Outcome:	The proposed method outperforms baseline models on zero-shot and few-shot settings on five languages and cultures.

Copied to clipboard

Zhihong Sun, Chen Lyu, Bolun Li, Yao Wan, Hongyu Zhang, Ge Li, Zhi Jin

Text Generation

Challenge:	Large Language Models (LLMs) have made significant advances in code generation through the ‘Chain-of-Thought’ prompting technique.
Approach:	They propose a framework which aims to transfer LLMs’ reasoning capabilities to smaller models through distillation.
Outcome:	The proposed framework improves the smaller model's code generation performance by over 130% on the APPS benchmark.

Rethinking Positional Encoding in Tree Transformer for Code Representation (2022.emnlp-main)

Copied to clipboard

Han Peng, Ge Li, Yunfei Zhao, Zhi Jin

Towards Autonomous Tool Utilization in Language Models: A Unified, Efficient and Scalable Framework (2024.lrec-main)

Challenge:	Recent works have proposed novel tree Transformers to capture the syntactic structure in source code.
Approach:	They propose a novel tree Transformer encoding node positions based on a description method for tree structures to incorporate inductive bias into Transformer.
Outcome:	The proposed model outperforms baselines on code summarization and completion tasks across two languages, and it is able to perform better on both local and global paradigms.

Copied to clipboard

Zhi Li, Yicheng Li, Hequan Ye, Yin Zhang

Beyond A Single AI Cluster: A Survey of Decentralized LLM Training (2025.emnlp-main)

Challenge:	Recent advances in tool learning for large language models have led to a new trend to allow LLMs to leverage external tools.
Approach:	They propose a framework for fine-tuning language models that categorizes queries into three different types . they also introduce an "instruct, execute, and reformat" strategy specifically designed for efficient data annotation .
Outcome:	The proposed framework surpasses open-source language models and GPT-3.5/4 on multiple evaluation metrics.

Copied to clipboard

Haotian Dong, Jingyan Jiang, Rongwei Lu, Jiajun Luo, Jiajun Song, Bowen Li, Ying Shen, Zhi Wang

Text Clustering

Challenge:	Decentralized LLM training leverages dispersed resources at varying scales.
Approach:	They propose a resource-driven paradigm that leverages dispersed resources across clusters, datacenters and even regions.
Outcome:	The proposed model scales are 175 billion to 660 billion parameters, and the exponential growth in computational requirements poses significant challenges.

Cross-lingual Contextualized Phrase Retrieval (2024.findings-emnlp)

Copied to clipboard

Huayang Li, Deng Cai, Zhi Qu, Qu Cui, Hidetaka Kamigaito, Lemao Liu, Taro Watanabe

Multilinguality

Challenge:	Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks.
Approach:	They propose a task formulation of dense retrieval, cross-lingual contextualized phrase retrieval . they extract pairs of cross-linguistic phrases using word alignment information .
Outcome:	The proposed task formulation surpasses baselines on the phrase retrieval task and a downstream task, i.e., machine translation, and achieves top-1 accuracy 13 points higher.

Event Causality Extraction via Implicit Cause-Effect Interactions (2023.emnlp-main)

Copied to clipboard

Jintao Liu, Zequn Zhang, Kaiwen Wei, Zhi Guo, Xian Sun, Li Jin, Xiaoyu Li

Information Extraction & Text Mining

Challenge:	Existing studies have not exploited the interactions between the cause and effect event that could provide crucial clues for causality reasoning.
Approach:	They propose an Implicit Cause-Effect interaction framework which captures the implicit intra- and inter-event interactions by incorporating the privileged information for reasoning.
Outcome:	The proposed framework captures the implicit intra- and inter-event interactions by incorporating the privileged information (ground truth event types and arguments) for reasoning.

KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development? (2026.acl-long)

Copied to clipboard

Xue Jiang, Ge Li, Jiaru Qian, Xianjie Shi, Chenjie Li, Hao Zhu, Ziyu Wang, Jielun Zhang, Zeyu Zhao, Kechi Zhang, Jia Li, Wenpin Jiao, Zhi Jin, Yihong Dong

MusTQ: A Temporal Knowledge Graph Question Answering Dataset for Multi-Step Temporal Reasoning (2024.findings-acl)

Challenge:	Existing domain-specific code benchmarks focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge.
Approach:	They propose a benchmark to evaluate domain specialization methods in real-world software development.
Outcome:	KOCO-bench is a new benchmark for evaluating domain specialization methods in real-world software development.

Copied to clipboard

Tingyi Zhang, Jiaan Wang, Zhixu Li, Jianfeng Qu, An Liu, Zhigang Chen, Hongping Zhi

Entropy-Aware Reshaping of Reinforcement Signals for Multi-Answer Reasoning (2026.findings-acl)

Challenge:	Existing studies focus on fact-centered reasoning with limited attention to temporal reasoning.
Approach:	They propose a new TKGQA dataset, MusTQ, which contains 666K multi-step temporal reasoning questions and a TKG.
Outcome:	The proposed model achieves state-of-the-art multi-step temporal reasoning ability with entity-time attention mechanism and optimized temporal knowledge graph representation.

Copied to clipboard

Zhi Li, Huidan Xu, Zhen Hu, Yali Du, Ying Liu

VulAgent: Hypothesis-Validation Driven Multi-Agent Architecture for Vulnerability Detection (2026.findings-acl)

Challenge:	Reinforcement learning with verifiable rewards (RLVR) is a standard post-training paradigm for large language models.
Approach:	They propose a framework that reshapes how learning signals are normalized and aggregated.
Outcome:	Experiments on MCTACO and MMLU-Multi show that the proposed framework improves accuracy, training stability and cross-dataset transfer performance.

Copied to clipboard

Ziliang Wang, Ge Li, Jia Li, Hao Zhu, Zhi Jin

Challenge:	Recent reports indicate that software vulnerabilities caused by insecure coding practices remain a major security threat.
Approach:	They propose a multi-agent vulnerability detection framework based on hypothesis validation . they use multi-view analyzers to localize and localize security-sensitive operations .
Outcome:	The proposed framework reduces false positives and increases accuracy by 6.6 percentage points on PrimeVul and SVEN.

CodeDPO: Aligning Code Models with Self Generated and Verified Source Code (2025.acl-long)

Copied to clipboard

Kechi Zhang, Ge Li, Yihong Dong, Jingjing Xu, Jun Zhang, Jing Su, Yongfei Liu, Zhi Jin

Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models (2026.acl-long)

Challenge:	Existing training methods for code generation do not improve code correctness and efficiency.
Approach:	They propose a framework that integrates preference learning into code generation to improve code correctness and efficiency.
Outcome:	The proposed framework improves code correctness and efficiency by integrating preference learning into code generation.

Copied to clipboard

Chung-ju Huang, Huiqiang Zhao, Yuanpeng He, Lijian Li, Wenpin Jiao, Zhi Jin, Peixuan Chen, Leye Wang

QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language (2025.findings-acl)

Challenge:	Existing approaches fail to ensure privacy, maintain model performance, and preserve computational efficiency simultaneously.
Approach:	They propose a confidential inference framework that partitions the LLM pipeline between a client-verified Confidential Virtual Machine (CVM) and the public cloud to protect client data without compromising the cloud’s model intellectual property or inference quality.
Outcome:	The proposed framework can defend against state-of-the-art token inference attacks while preserving model privacy, performance, and efficiency.

Copied to clipboard

Qingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan, Yuhang Wang, Li Xu, Wenxuan Wang, Kuofeng Gao, Ruoyu Li, Yong Jiang

RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (2026.acl-long)

Challenge:	Existing methods to bypass security defenses of large language models (LLMs) are not effective, but QueryAttack can be jailbroken.
Approach:	They propose a framework to examine generalizability of safety alignment by translating malicious queries into structured non-natural query languages.
Outcome:	The proposed framework can achieve high attack success rates and jailbreak various defense methods on mainstream LLMs.

Copied to clipboard

Yihong Dong, Xue Jiang, Yongding Tao, Huanyu Liu, Kechi Zhang, Lili Mou, Rongyu Cao, Yingwei MA, Jue Chen, Binhua Li, Zhi Jin, Fei Huang, Yongbin Li, Ge Li

CLEVA: Chinese Language Models EVAluation Platform (2023.emnlp-demo)

Challenge:	Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs).
Approach:	They propose a hybrid-policy optimization approach that synergizes internal exploitation with external data to achieve stronger reasoning capabilities.
Outcome:	The proposed approach achieves state-of-the-art performance on six math reasoning benchmarks and superior performance on out-of distribution reasoning tasks.

Copied to clipboard

Yanyang Li, Jianqiao Zhao, Duo Zheng, Zi-Yuan Hu, Zhi Chen, Xiaohui Su, Yongfeng Huang, Shijia Huang, Dahua Lin, Michael Lyu, Liwei Wang

KuiLeiXi: a Chinese Open-Ended Text Adventure Game (2021.acl-demo)

Challenge:	Large language models (LLMs) have revolutionized natural language processing.
Approach:	They propose a Chinese-based platform that assesses Chinese LLMs using a standardized workflow and a unique sampling strategy.
Outcome:	CLEVA evaluates Chinese LLMs on a standardized workflow and a competitive leaderboard with minimal coding.

Copied to clipboard

Yadong Xi, Xiaoxi Mao, Le Li, Lei Lin, Yanjiang Chen, Shuhan Yang, Xuhan Chen, Kailun Tao, Zhi Li, Gongzheng Li, Lin Jiang, Siyan Liu, Zeng Zhao, Minlie Huang, Changjie Fan, Zhipeng Hu