Papers by Qi Shi

ParaMac: A General Unsupervised Paraphrase Generation Framework Leveraging Semantic Constraints and Diversifying Mechanisms (2022.findings-emnlp)

Challenge:	Recent studies have shown that large language models are useful, honest, harmless (HHH) however, RLHF requires high hardware resources and human efforts.
Approach:	They propose a framework that allows LLMs to align themselves with HHH . they use IF and reinforcement learning from human feedback to fine-tune their models .
Outcome:	The proposed framework achieves similar performance to RLHF and human-generated models with a minimal alignment tax.

Copied to clipboard

Jinxin Liu, Jiaxin Shi, Ji Qi, Lei Hou, Juanzi Li, Qi Tian

Text Generation

Challenge:	Existing unsupervised methods for paraphrase generation are weak in semantic equivalence or expression diversity.
Approach:	They propose a framework for unsupervised paraphrase generation that employs multi-aspect equivalence constraints and multi-granularity diversifying mechanisms to achieve good semantic equvalence and expressive diversity.
Outcome:	The proposed framework achieves 9.1% and 3.3% absolute gains over previous SOTA on Quora and MSCOCO and can improve to 18.0% and 4.6% on GLUE.

Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering (2024.emnlp-industry)

Copied to clipboard

Lu Shi, Bin Qi, Jiarui Luo, Yang Zhang, Zhanzhao Liang, Zhaowei Gao, Wenke Deng, Lin Sun

Information Retrieval

Challenge:	Aegis is an advanced LLM-based multi-agent for intelligent functional safety engineering that can perform all phases of a vehicle's lifecycle, including design, development, production, operation, and decommissioning.
Approach:	They introduce Aegis: An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering.
Outcome:	The proposed solution can perform Hazard Analysis and Risk Assessment (HARA), document Functional Safety Requirements (FSR), and plan test cases for Automatic Emergency Braking (AEB) systems.

MicroC-KT: Modeling Community Effect via Learning Micro-Environment for Evidence-Grounded Explainable Knowledge Tracing (2026.acl-long)

Copied to clipboard

Zhiyi Duan, Zixing Shi, Bing Jia, Qi Wang

TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators (2025.findings-acl)

Challenge:	Existing graph-based methods focus on exercise-concept relations, but lack the broader context of group references and contrastive evidence.
Approach:	They propose a framework that incorporates learning micro-environments to provide social-cognitive anchors for KT by extracting contrastive group evidence.
Outcome:	The proposed framework outperforms state-of-the-art models on four public datasets while providing more reliable and evidence-based explanations.

Copied to clipboard

Jianling Li, ShangZhan Li, Zhenye Gao, Qi Shi, Yuxuan Li, Zefan Wang, Jiacheng Huang, WangHaojie WangHaojie, Jianrong Wang, Xu Han, Zhiyuan Liu, Maosong Sun

ULMR: Unlearning Large Language Models via Negative Response and Model Parameter Average (2024.emnlp-industry)

Challenge:	Triton is a high-level Python-like programming language for building efficient GPU kernels.
Approach:	They propose a TritonBench benchmark that provides a comprehensive evaluation of Tritonic operators on widely deployed GPUs.
Outcome:	The proposed benchmarks show that current LLMs struggle to generate efficient Triton operators on widely deployed GPUs aligned with industry applications.

Copied to clipboard

Shaojie Shi, Xiaoyu Tan, Xihe Qiu, Chao Qu, Kexin Nie, Yuan Cheng, Wei Chu, Xu Yinghui, Yuan Qi

Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation (2026.acl-long)

Challenge:	Large language models (LLMs) have attracted significant interest from the research community due to their broad applicability in many language-oriented tasks.
Approach:	They propose a framework which uses pre-training datasets to rewrite instructions and generate negative responses to preserve the performance of the original LLM.
Outcome:	The proposed framework can erase the pre-training data while maintaining the performance of the original model.

Copied to clipboard

Huachen Qi, Ruiyu Zhuo, Bowen Shi, Xiang Chang, Fei Chao, Changjing Shang, Qiang Shen

On LLM-Based Scientific Inductive Reasoning Beyond Equations (2025.emnlp-main)

Challenge:	Large Language Models are scaling in size and capability, driving substantial computational and memory costs.
Approach:	They propose a mixed-precision quantization framework that uses fuzzy rule interpolation to predict quantization error from only sparse samples.
Outcome:	The proposed framework accelerates the profiling phase by up to 15.7 on DeepSeek-V2 while achieving comparable or slightly superior zero-shot accuracy.

Copied to clipboard

Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun

Structural Patent Classification Using Label Hierarchy Optimization (2025.findings-emnlp)

Challenge:	Existing research on inductive reasoning models emphasizes rule design without grounding them in specific scenarios.
Approach:	They propose to use LLMs to learn underlying patterns from limited examples in entirely new environments.
Outcome:	The proposed benchmark evaluates the inductive reasoning abilities of large language models in scientific settings.

Copied to clipboard

Mengting Gui, Shufeng Hao, Chongyang Shi, Qi Zhang

Information Extraction & Text Mining

Challenge:	Existing methods for patent classification ignore key technical content claims and citation relationships . existing methods treat labels as independent targets, failing to exploit semantic and structural information within the label taxonomy.
Approach:	They propose a Claim Structure based Patent Classification model with Label Awareness . structural graph learning is used to mine the internal logic of patent claims .
Outcome:	The proposed method is more effective than state-of-the-art classification models.

Auto-Dialabel: Labeling Dialogue Data with Unsupervised Learning (D18-1)

Copied to clipboard

Chen Shi, Qi Chen, Lei Sha, Sujian Li, Xu Sun, Houfeng Wang, Lintao Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing dialog datasets rely on human labeling, which is expensive, limited in size, and in low coverage.
Approach:	They propose a framework to automatically cluster dialogue intents and slots . they collect context features, leverage an autoencoder for feature assembly, and adapt a dynamic hierarchical clustering method for intent and slot labeling.
Outcome:	The proposed framework can promote human labeling cost to a great extent and achieve good intent clustering accuracy (84.1%) it also provides reasonable and instructive slot labeling results.

Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety (2025.emnlp-main)

Copied to clipboard

Chenhao Huang, Ziyu Shen, Yicong Ren, Huiyuan Zheng, Jiazheng Zhang, Mingxu Chai, Ming Zhang, Shihan Dou, Fan Mo, Jie Shi, Tao Gui, Qi Zhang, Xuanjing Huang

ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation (2025.acl-long)

Challenge:	Existing approaches to align large language models with human preferences lack flexibility . static alignment preferences lack the ability to correct misaligned behaviors as they emerge .
Approach:	They propose a framework that enables dynamic and continuous alignment of large language models with human preferences.
Outcome:	The proposed framework improves safety and accuracy of a 7B model with human annotations.

Copied to clipboard

Xuanle Zhao, Xianzhen Luo, Qi Shi, Chi Chen, Shuo Wang, Zhiyuan Liu, Maosong Sun

Counteracting the Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing (2026.acl-long)

Challenge:	Existing open-source MLLMs fail to fully capture dense information embedded in charts . current models still face significant challenges in understanding and analyzing visual tasks such as captioning and question answering.
Approach:	They propose a chart-to-code MLLM which leverages Code LLMs as the language backbone to enhance the executability of the generated code.
Outcome:	The proposed model surpasses existing open-source models on chart-to-code benchmarks with only 7B parameters and provides lossless representations that contain all critical details.

Copied to clipboard

Xin Guo, Zhiheng Xi, Yiwen Ding, Yitao Zhai, Xiaowei Shi, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang

Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection (2026.acl-long)

Challenge:	Large vision language models have impressive reasoning capabilities across complex multimodal tasks.
Approach:	They propose to use distribution-reshaping and trajectory-rebalancing to improve visual reasoning capabilities.
Outcome:	Experiments on Qwen2-VL-7B-Instruct and InternVL2.5-4B models show that their methods outperform baselines by 3.86 points.

Copied to clipboard

Cui Yakun, Peng Qi, Fushuo Huo, Hang Du, Weijie Shi, Juntao Dai, Zhenghao Zhu, Sirui Han

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling (2025.naacl-long)

Challenge:	Existing video fake news detection benchmarks focus on the detection accuracy, while failing to provide fine-grained assessments for the entire detection process.
Approach:	They propose a process-oriented video fake news detection benchmark that evaluates MLLMs' perception, understanding, and reasoning capabilities in VFND.
Outcome:	The proposed model achieves sota performance on video fake news detection tasks.

Copied to clipboard

Yiwen Ding, Zhiheng Xi, Wei He, Lizhuoyuan Lizhuoyuan, Yitao Zhai, Shi Xiaowei, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang

Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions (2023.findings-emnlp)

Challenge:	Large language models (LLMs) generate solutions themselves and iteratively train on filtered, high-quality rationales, but performance reaches a ceiling after a few iterations.
Approach:	They propose a strategy to improve the efficiency of sampling heavy-tailed data by using Socratic-style guidance signals to help LLMs reasoning with complex queries.
Outcome:	The proposed approach is effective on difficult queries and on held-out tasks, while requiring human supervision.

Copied to clipboard

Shulin Cao, Jiajie Zhang, Jiaxin Shi, Xin Lv, Zijun Yao, Qi Tian, Lei Hou, Juanzi Li

JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering (2022.naacl-main)

Challenge:	Large language models (LLMs) are capable of answering knowledge-intensive complex questions with chain-of-thought reasoning.
Approach:	They propose a method to solve complex questions with a tree-of-thought approach using parametric knowledge and retrieved external knowledge to augment CoT reasoning.
Outcome:	The proposed approach outperforms SOTA methods on three Complex QA datasets under the open-domain setting.

Copied to clipboard

Yueqing Sun, Qi Shi, Le Qi, Yu Zhang

LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training (2022.findings-emnlp)

Challenge:	Existing KG-augmented models for commonsense question answering ignore the effectively fusing and reasoning over question context representations and the KG representations.
Approach:	They propose a novel model which combines a logical reasoning and a dynamic pruning mechanism to solve these limitations.
Outcome:	The proposed model improves existing models and performs interpretable reasoning on the CommonsenseQA and OpenBookQA datasets.

Copied to clipboard

Qi Shi, Qian Liu, Bei Chen, Yu Zhang, Ting Liu, Jian-Guang Lou

Searching for Best Practices in Retrieval-Augmented Generation (2024.emnlp-main)

Challenge:	Existing approaches to language-based environment manipulation are difficult to generalize across environments.
Approach:	They propose a general framework for language-based environment manipulation tasks that can deal with various environments using the same generative language model.
Outcome:	The proposed framework achieves new state-of-the-art results on four of the tasks and the execution-guided pre-training strategy brings remarkable improvements on all experimental tasks.

Copied to clipboard

Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang

Information Retrieval

Challenge:	Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, especially in specialized domains.
Approach:	They propose several strategies for deploying RAG that balance performance and efficiency.
Outcome:	The proposed approaches can significantly enhance question-answering capabilities and accelerate the generation of multimodal content using a “retrieval as generation” strategy.

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

Copied to clipboard

Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)

Challenge:	Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process .
Approach:	They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation.
Outcome:	The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench.

Copied to clipboard

Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao Shi, Jianping Fan, Xuanjing Huang

Reinforcement Learning on Pre-Training Data (2026.acl-long)

Challenge:	Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities.
Approach:	They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs .
Outcome:	The proposed framework improves instruction following performance without compromising general performance.

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement (2025.emnlp-industry)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Haotan Guo, Jianfei He, Jiayuan Ma, Hongbin Na, Zimu Wang, Haiyang Zhang, Qi Chen, Wei Wang, Zijing Shi, Tao Shen, Ling Chen

Causal Intervention for Abstractive Related Work Generation (2023.findings-emnlp)

Challenge:	Phonetic Cloaking Replacement (PCR) is a problem in content moderation in China.
Approach:	They organize PCR into a four-way surface-form taxonomy and compile PCR-ToxiCN, a dataset of 500 phonetically cloaked offensive posts gathered from the RedNote platform.
Outcome:	The proposed model achieves only an F1-score and zero-shot chain-of-thought prompting pushes performance even lower.

Copied to clipboard

Jiachang Liu, Qi Zhang, Chongyang Shi, Usman Naseem, Shoujin Wang, Liang Hu, Ivor Tsang

Challenge:	Existing models ignore the inherent causality during related work generation, leading to spurious correlations which downgrade the models’ generation quality and generalizability.
Approach:	They propose a Causal Intervention Module for Related Work Generation (CaM) that captures causal relationships in related work generation and implements causal interventions to mitigate the negative impact of spurious correlations.
Outcome:	The proposed framework improves the quality and coherence of generated related work by capturing causalities in the generation process.

DoG-Instruct: Towards Premium Instruction-Tuning Data via Text-Grounded Instruction Wrapping (2024.naacl-long)

Copied to clipboard

Yongrui Chen, Haiyun Jiang, Xinting Huang, Shuming Shi, Guilin Qi

Enhancing Multimodal Large Language Models for Ancient Chinese Character Evolution Analysis via Glyph-Driven Fine-Tuning (2026.acl-long)

Challenge:	Existing methods to collect high-quality instruction-response pairs suffer from unaffordable labor costs or severe hallucinations in the self-generation of LLMs.
Approach:	They propose a method that trains LLMs to generate instruction-response pairs based on human-written documents rather than relying solely on self-generation without context.
Outcome:	The proposed method outperforms existing typical methods on multiple benchmarks and shows that it is 100% scalable.

Copied to clipboard

Rui Song, Lida Shi, Ruihua Qi, Yingji Li, Hao Xu

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Existing studies have explored the evolutionary analysis of ancient scripts, with particular attention to the transformation of character forms from oracle bone inscriptions to regular script.
Approach:	They propose a benchmark framework that leverages MLLMs to analyze the evolution of ancient Chinese scripts.
Outcome:	The proposed framework improves performance on core tasks and character recognition and evolutionary reasoning tasks while limiting performance on other tasks.

Copied to clipboard

Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun

AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage (2026.acl-long)

Challenge:	Existing RAG systems often underutilize the retrieved documents, authors say . they fail to extract and integrate key clues needed to support faithful and interpretable reasoning .
Approach:	a new framework extracts key clues from retrieved content and generates multiple reasoning paths . the framework optimizes the model by selecting the most appropriate reasoning path .
Outcome:	Experiments show that ClueAnchor outperforms baseline RAG frameworks in completeness and robustness.

Copied to clipboard

Xuanle Zhao, Zilin Sang, Yuxuan Li, Qi Shi, Weilun Zhao, Shuo Wang, Duzhen Zhang, Xu Han, Zhiyuan Liu, Maosong Sun

Challenge:	Efficient reproduction of research papers requires deep domain expertise.
Approach:	They propose a framework that systematically mines implicit knowledge from the cited literature to reproduce experimental code in a complete, end-to-end manner.
Outcome:	The proposed framework surpasses baselines across all metrics and reproduces experimental code in a complete, end-to-end manner.

PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching (2023.emnlp-industry)

Copied to clipboard

Zhenting Qi, Xiaoyu Tan, Shaojie Shi, Chao Qu, Yinghui Xu, Yuan Qi

LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding (2025.emnlp-main)

Challenge:	Low-Rank Adaptation (LoRA) has been used to adapt Large Language Models to a variety of tasks, but it requires substantial computational resources to perform.
Approach:	They propose a low-rank adaptive learning approach that leverages LoRA's in-context learning capability through prompt matching via reinforcement learning in resource-constrained environments.
Outcome:	The proposed model improves LoRA performance on evaluation metrics and utilises consumer-grade GPU resources.

Copied to clipboard

Yuxuan Hu, Jihao Liu, Ke Wang, Jinliang Zheng, Weikang Shi, Manyuan Zhang, Qi Dou, Rui Liu, Aojun Zhou, Hongsheng Li

SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models (2026.acl-long)

Challenge:	Recent advances in Large Language Models have opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS).
Approach:	They propose a framework that leverages LLMs for cross-domain neural architecture optimization without extensive domain-specific tuning.
Outcome:	The proposed framework achieves competitive performance in both in-domain and out-of-domain tasks.

Copied to clipboard

Yiyang Gu, Junwei Yang, Junyu Luo, Ye Yuan, Bin Feng, Yingce Xia, Shufang Xie, Kaili Liu, Bohan Wu, Qi Shi, Haoran Li, Beier Xiao, Zhiping Xiao, Xiao Luo, Weizhi Zhang, Philip S. Yu, Zequn Liu, Ming Zhang

ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs’ Capability via Chart Editing (2025.findings-acl)

Challenge:	Existing evaluations of large language models fail to reflect fine-grained capabilities . existing benchmarks are manually curated or domain-generic, limiting scalability and alignment with real use cases.
Approach:	They propose a framework that allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs.
Outcome:	The proposed framework reveals fine-grained differences in scientific capabilities that standard benchmarks overlook . it allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific capabilities in LLMs.

Copied to clipboard

Xuanle Zhao, Xuexin Liu, Yang Haoyue, Xianzhen Luo, Fanhu Zeng, Jianling Li, Qi Shi, Chi Chen

Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering (2023.acl-long)

Challenge:	Existing evaluations of multimodal large language models rely on limited case studies . however, they lack the ability to generate accurate edits according to the instructions .
Approach:	They propose a benchmark for chart editing that includes 1,405 edit instructions applied to 233 real-world charts.
Outcome:	The proposed benchmark includes 1,405 diverse editing instructions applied to 233 real-world charts.

Copied to clipboard

Jiajie Zhang, Shulin Cao, Tingjian Zhang, Xin Lv, Juanzi Li, Lei Hou, Jiaxin Shi, Qi Tian

Question Answering

Challenge:	Existing XQA methods focus on reasoning on a single knowledge source, e.g., structured knowledge bases, unstructured corpora, etc. Existing work in XQA focuses on integrating information from heterogeneous knowledge sources.
Approach:	They propose to leverage question decomposing for heterogeneous knowledge integration by breaking down a complex question into simpler ones and selecting the appropriate knowledge source for each sub-question.
Outcome:	The proposed framework outperforms SOTA methods on complex QA datasets.

MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing (2026.acl-demo)

Copied to clipboard

Yang Liu, Jinxuan Cai, Yishen Li, Qi Meng, Zedi Liu, Xin Li, Chen Qian, Chuan Shi, Cheng Yang

Structured Data in NLP

Challenge:	Large language model-based multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration.
Approach:	They propose a graph-centric framework for orchestrating large language model-based multi-agent systems . they compile a user's natural-language intent into an editable workflow specification and then into an executable graph .
Outcome:	The proposed framework compiles natural-language intent into an executable graph and then compile and executes it at runtime.

TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering (2022.findings-emnlp)

Copied to clipboard

Yueqing Sun, Yu Zhang, Le Qi, Qi Shi

Low-Resource NLP

Challenge:	Existing studies focus on acquiring relevant knowledge by retrieving external knowledge bases and fine-tuning pre-trained models.
Approach:	They propose a two-stage prompt-based unsupervised commonsense question answering framework that leverages implicit knowledge stored in PrLMs to generate knowledge for questions with unlimited types and possible candidate answers independent of specified choices.
Outcome:	The proposed framework significantly improves the reasoning ability of language models in unsupervised settings.

AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation (2026.findings-acl)

Copied to clipboard

Wentao Shi, Yu Wang, Yuyang Zhao, Yuxin Chen, Fuli Feng, Xueyuan Hao, Xi Su, Qi GU, Hui Su, Xunliang Cai, Xiangnan He

Challenge:	Existing approaches to verify agent behaviors in complex environments rely on rule-based verifiers or LLM-as-a-Judge models.
Approach:	They propose a benchmark to evaluate Agent-as-a-Judge across three domains . the benchmark covers search, data systems, and graphical user interfaces - with 155 tasks and 516 trajectories .
Outcome:	The proposed benchmark outperforms existing benchmarks in search, data systems, and GUI domains while revealing open challenges in agent-based verification.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization (2025.findings-emnlp)

Copied to clipboard

Zhensheng Jin, Xinze Li, Yifan Ji, Chunyi Peng, Zhenghao Liu, Qi Shi, Yukun Yan, Shuo Wang, Furong Peng, Ge Yu

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers (2025.acl-long)

Challenge:	Existing methods to train LLMs suffer from overthinking, leading to lengthy reasoning traces . Existing approaches to train large language models suffer from this problem .
Approach:	They propose a method to combine multiple reasoning chains for training LLMs . they use stepwise exploration and long-short switched sampling to evaluate reasoning paths .
Outcome:	The proposed method reduces reasoning lengths by approximately 30-50% . it also maintains or improves reasoning accuracy compared to baselines .

Copied to clipboard

Zicong Tang, Shi Luohe, Zuchao Li, Baoyuan Qi, Liu Guoming, Lefei Zhang, Ping Wang

Challenge:	Large language models (LLMs) have impressive capabilities across various fields, but their widespread use is facing a severe and realistic challenge, which is their high demand for GPU memory.
Approach:	They propose a KV cache reduction method which balances both shallow and deep layers by using an attention weight based eviction method and a codebook based replacement approach.
Outcome:	The proposed method reduces the KV cache for shallower layers while preserving similar or even better model performance.

ResLoRA: Identity Residual Mapping in Low-Rank Adaption (2024.findings-acl)

Copied to clipboard

Shuhua Shi, Shaohan Huang, Minghui Song, Zhoujun Li, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

Challenge:	Low-rank adaptation (LoRA) is one of the most popular parameter-efficient fine-tuning methods.
Approach:	They propose a low-rank adaptation method that adds residual paths during training and merges them together during inference to achieve better results.
Outcome:	The proposed method achieves 2.5x faster convergence speed and improves performance by 14.3% on NLG, NLU, and text-to-image tasks.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)

Copied to clipboard

Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du

Robustness in NLP

Challenge:	a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks.
Approach:	They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories .
Outcome:	The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points.

GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation (2022.emnlp-main)

Copied to clipboard

Lunyiu Nie, Shulin Cao, Jiaxin Shi, Jiuding Sun, Qi Tian, Lei Hou, Juanzi Li, Jidong Zhai

SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection (2026.acl-industry)

Challenge:	Existing approaches to neural semantic parsing are limited by the semantic gap between natural and formal languages.
Approach:	They propose a unified intermediate representation for graph query languages, named GraphQ IR, which has a natural-language-like expression that bridges the semantic gap and formally defined syntax that maintains the graph structure.
Outcome:	The proposed representation can convert user queries into graphQ IR, which can later be losslessly compiled into various downstream graph query languages.

Copied to clipboard

Zhiyong Cao, Dunqiang Liu, Qi Dai, Haojun Xu, Huai Yuen Khor, Hao Wang, Huan He, Yafei Liu, Ke Ma, Ruqian Shi, Sicheng Zhou, Sijia Yao

Dialogue Systems & Conversational Agents

Challenge:	High-quality data in training proactive dialogue agents is scarce, despite fine-tuning and reinforcement learning . a recent study has shown that the effectiveness of supervised fine-touring is limited by the lack of high-quality, domain-specific training data.
Approach:	They propose a framework for training recruitment proactive dialogue agents using a high-fidelity user simulator and a multi-dimensional evaluation framework based on Chain-of-Intention.
Outcome:	The proposed framework outperforms existing simulator-based data selection strategies in a real-world recruitment scenario.

RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation (2025.findings-emnlp)

Copied to clipboard

Tianjiao Li, Mengran Yu, Chenyu Shi, Yanjun Zhao, Xiaojing Liu, Qi Zhang, Xuanjing Huang, Qiang Zhang, Jiayin Wang

Text Generation

Challenge:	Using reinforcement learning from human feedback, large language models perform poorly when applied to colloquial subtitle translation tasks.
Approach:	They propose an adversarial training framework that iteratively updates the offline reward model and the online LLM to improve training outcomes.
Outcome:	The proposed training framework significantly improves upon translation baselines.

Explanation Graph Generation via Generative Pre-training over Synthetic Graphs (2023.findings-acl)

Copied to clipboard

Han Cui, Shangzhan Li, Yu Zhang, Qi Shi

Incremental Transformer: Efficient Encoder for Incremented Text Over MRC and Conversation Tasks (2025.coling-main)

Challenge:	Existing frameworks for explanation graph generation are limited due to the large number of datasets available.
Approach:	They propose a text-to-graph generative task to pre-train a model to bridge the text-graph gap.
Outcome:	The proposed framework surpasses all baseline systems with remarkable margins on ExplaGraphs and CommonsenseQA.

Copied to clipboard

Weisheng Li, Yuechen Wang, Jiaxin Shi, Wengang Zhou, Qi Tian, Houqiang Li

Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification (2021.emnlp-main)

Challenge:	Existing encoders that encode incremented inputs have to re-encode the whole text to obtain the encoding of the extended input.
Approach:	They propose an efficient encoder dedicated for faster encoding of incremented input . it takes only added input as input but attends to cached representations of original input a lower layer .
Outcome:	The proposed encoder achieves 6.2x speedup over current encoders . it takes only added input as input but attends to cached representations of original input .

Copied to clipboard

Qi Shi, Yu Zhang, Qingyu Yin, Ting Liu

A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)

Challenge:	Existing methods leverage programs that contain rich logical information to enhance the verification process.
Approach:	They propose a table-based fact verification task as an evidence retrieval framework . they retrieve logic-level program-like evidence from the given table and a statement as supplementary evidence for the table .
Outcome:	The proposed method is able to retrieve logic-level program-like evidence from a table and a statement as supplementary evidence for the table.

Copied to clipboard

Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang

AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code (2026.findings-acl)

Challenge:	Inductive reasoning is an important task for large language models (LLMs).
Approach:	They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation.
Outcome:	The proposed method improves inductive reasoning in large language models.

Copied to clipboard

ShangZhan Li, Xinyu Yin, Xuanyu Jin, Ye He, Yuxin Zhou, Yuxuan Li, Xu Han, Wanxiang Che, Qi Shi, Ting Liu, Maosong Sun

Programming Languages in NLP

Challenge:	Current development practices face a dichotomy between automation and performance.
Approach:	They propose a framework to empower LLMs with the capability of automated explicit vectorization.
Outcome:	The proposed framework achieves state-of-the-art performance on the SSE and AVX subsets of SimdBench.

Exploring Hybrid Question Answering via Program-based Prompting (2024.acl-long)

Copied to clipboard

Qi Shi, Han Cui, Haofeng Wang, Qingfu Zhu, Wanxiang Che, Ting Liu

Advancing Sequential Numerical Prediction in Autoregressive Models (2025.acl-short)

Challenge:	Existing approaches to question answering over heterogeneous data are limited due to large scale of information and organic coupling of heterogenous data.
Approach:	They propose a program-based prompting framework for hybrid question answering tasks . it integrates various functions to perform hybrid information-seeking over data .
Outcome:	The proposed framework surpasses baseline systems and achieves the best performance under the fewshot settings.

Copied to clipboard

Xiang Fei, Jinghui Lu, Qi Sun, Hao Feng, Yanjie Wang, Wei Shi, An-Lan Wang, Jingqun Tang, Can Huang

Challenge:	Autoregressive models are the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences.
Approach:	They propose a novel approach to entropy loss by extending the Earth Mover’s Distance to preserve ordinal relationships between numerical values and sequence-level to penalize the overall discrepancy between predicted and actual sequences.
Outcome:	Extensive experiments show that NTIL improves numerical prediction and integrates effectively with LLMs/MLLMs.

Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling (2026.findings-acl)

Copied to clipboard

Zhenghua Wang, Yiran Ding, Changze Lv, Yixin Wu, Tianlong Li, Zhibo Xu, Muling Wu, Tianyuan Shi, Shizheng Li, Qi Qian, Xuanjing Huang, Xiaoqing Zheng

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels (2025.emnlp-main)

Challenge:	Existing methods to address the "lost-in-the-middle" problem suffer from high latency or suboptimal hand-crafted scaling strategies.
Approach:	They propose a layer-specific positional embedding scaling method that assigns distinct scaling factors to each layer.
Outcome:	Experiments show that the proposed method mitigates positional attention bias and delivers consistent improvements across multiple long-context benchmarks.

Copied to clipboard

Junjie Ye, Yuming Yang, Yang Nan, Shuo Li, Qi Zhang, Tao Gui, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan

LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models (2025.acl-long)

Challenge:	Large language models (LLMs) acquire substantial world knowledge during pretraining, which is further shaped by post-training techniques such as supervised fine-tuning (SFT).
Approach:	They evaluate closed-book question answering (CBQA) performance across five LLMs from the LLaMA-2 and LLama-3 families and examine the impact of supervised fine-tuning on model knowledge.
Outcome:	The proposed model performance is 14% worse than models fine-tuned on 1,920 samples and 12% worse on 240 samples.

Copied to clipboard

Zihan Zhou, Chong Li, Xinyi Chen, Shuo Wang, Yu Chao, Zhili Li, Haoyu Wang, Qi Shi, Zhixing Tan, Xu Han, Xiaodong Shi, Zhiyuan Liu, Maosong Sun

Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification (2020.coling-main)

Challenge:	Existing studies have focused on extending the context length of large language models (LLMs) due to their quadratic computational complexity and a lack of high-quality long training examples, most LLMs are trained with a limited window size.
Approach:	They propose a training-free framework that enables large language models to effectively process long texts using a divide-and-conquer strategy for comprehensive document understanding.
Outcome:	The proposed framework outperforms open-source and commercial long-context LLMs and is compatible with several models.

Copied to clipboard

Qi Shi, Yu Zhang, Qingyu Yin, Ting Liu

Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection (2026.acl-long)

Challenge:	Existing methods for fact verification lack attention to combine linguistic and symbolic information.
Approach:	They propose a graph-based reasoning approach that learns to combine linguistic and symbolic information effectively.
Outcome:	The proposed method can combine linguistic and symbolic information effectively.

Copied to clipboard

Linxuan Du, Guangquan Xue, Xiaobo Liang, Qipeng Huang, Yuyang Ding, Xinyu Shi, Zhang Yijun, Ji Qi, Wenpeng Zhu, Juntao Li, Min Zhang

Challenge:	Existing methods for multi-turn self-reflection are limited by the Echo Trap problem . the model is limited by its inherent capabilities and repeats earlier reflections to preserve reward signals .
Approach:	They propose a tree-structured extension of GRPO for multi-turn self-reflection which enables more accurate advantage estimation.
Outcome:	The proposed method mitigates behavior collapse and improves performance across benchmarks.

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting (2025.findings-acl)

Copied to clipboard

Hao Feng, Shu Wei, Xiang Fei, Wei Shi, Yingdong Han, Lei Liao, Jinghui Lu, Binghong Wu, Qi Liu, Chunhui Lin, Jingqun Tang, Hao Liu, Can Huang

Navigating the OverKill in Large Language Models (2024.acl-long)

Challenge:	Current document image parsing solutions rely on specialized models or generate content autoregressively.
Approach:	They propose a multimodal document image parsing model that integrates specialized models with autogeneous content generation.
Outcome:	The proposed model achieves state-of-the-art performance across diverse page-level and element-level settings while ensuring superior efficiency.

Copied to clipboard

Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin

KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding (2025.acl-long)

Challenge:	Recent studies have highlighted a tendency among large language models to refuse to answer benign queries.
Approach:	They propose a model-agnostic approach to reduce excessive attention to harmful words like ‘kill’ and a method to decode the next-token predictions by contrastive decoding.
Outcome:	The proposed approach reduces the refusal rate by 20% while having little impact on safety.

Copied to clipboard

Shi Luohe, Zuchao Li, Lefei Zhang, Baoyuan Qi, Liu Guoming, Hai Zhao