Papers by Qi Feng

CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios (2025.emnlp-main)

Challenge:	a new framework casts LLM planning as non-parametric retrieval, but high latency of inference-time search and supervised fine-tuning are limitations.
Approach:	They propose a framework that casts LLM planning as non-parametric retrieval . they leverage Monte Carlo Tree Search to explore the solution space .
Outcome:	Empirical results show that SGA-MCTS can match the performance of SOTA systems without task-specific fine-tuning.

Copied to clipboard

Shiting Huang, Zhen Fang, Zehui Chen, Siyu Yuan, Junjie Ye, Yu Zeng, Lin Chen, Qi Mao, Feng Zhao

Context-DPO: Aligning Language Models for Context-Faithfulness (2025.findings-acl)

Challenge:	a number of tools are used to perform complex tasks, but the tool utilization process can cause errors.
Approach:	They propose a critique evaluation benchmark for tool learning that analyzes function-calling errors on tool evaluation benchmarks.
Outcome:	The proposed critique evaluation benchmark holds diverse tool-use errors with varying complexities, which better reflects real-world scenarios.

Copied to clipboard

Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu

From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM (2025.coling-main)

Challenge:	Context-DPO is the first alignment method specifically designed to enhance contextfaithfulness for large language models.
Approach:	They propose a benchmark that simulates Retrieval-Augmented Generation scenarios with knowledge conflicts to evaluate context-faithfulness.
Outcome:	The proposed method improves LLMs' context-faithfulness by 35% to 280% over open-source models.

Copied to clipboard

Jianyu Liu, Yi Huang, Sheng Bi, Junlan Feng, Guilin Qi

Knowledge Representation

Challenge:	Existing methods for generating follow-up questions are limited to shallow contextual questions that are uninspiring and have a large gap to the human level.
Approach:	They propose a three-stage external knowledge-enhanced follow-up question generation method which generates questions by identifying contextual topics, building a knowledge graph online, and finally combining these with a large language model to generate the final question.
Outcome:	The proposed method generates questions by identifying contextual topics, building a knowledge graph (KG) online, and finally combining these with a large language model to generate the final question.

MAIN: Mutual Alignment Is Necessary for instruction tuning (2025.emnlp-main)

Copied to clipboard

Fanyi Yang, Jianfeng Liu, Xin Zhang, Haoyu Liu, Xixin Cao, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models (2026.acl-long)

Challenge:	Instruction tuning has enabled large language models to achieve remarkable performance, yet its success heavily depends on the availability of high-quality instruction-response pairs.
Approach:	They propose a mutual alignment framework which enforces coherence between instructions and responses through mutual constraints.
Outcome:	The proposed framework generalizes well across model architectures and sizes, achieving state-of-the-art performance on LLaMA, Mistral, and Qwen models across diverse benchmarks.

Copied to clipboard

Ziyan Wang, Enmao Diao, Qi Le, Pu Wang, Minwoo Lee, Shu-ping Yeh, Evgeny Stupachenko, Hao Feng, Li Yang

HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition (2024.acl-long)

Challenge:	Structured pruning is a practical approach to deploying large language models (LLMs) but it fails to capitalize on modest task-specific calibration signals, causing limited downstream gains.
Approach:	They propose a method that removes attention heads and MLP channels using loss-based important scores . they use perplexity for language modeling and a margin-based objective for decision-style tasks .
Outcome:	The proposed method lowers perplexity and improves accuracy at higher sparsity . it also stabilizes accuracy and mitigates perxity collapse without fine-tuning .

Copied to clipboard

Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering (2025.findings-acl)

Challenge:	Large language models (LLMs) are a promising alternative to expensive human evaluations.
Approach:	They propose a framework that iteratively aligns LLM-based evaluators with human preference . they decompose a given evaluation task into finer-grained criteria .
Outcome:	The proposed framework iteratively aligns LLM-based evaluators with human preference . it decomposes a given evaluation task into finer-grained criteria . the framework is efficient to train and more explainable than relying solely on prompts .

Copied to clipboard

Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, An-Lan Wang, Chunhui Lin, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang

Multilinguality

Challenge:	Text-Centric Visual Question Answering (TEC-VQA) is a text-centric visual task understanding tool.
Approach:	They introduce a benchmark that features human expert annotations across 9 languages . they prioritize the text in question-answer pairs while disregarding visual text in images .
Outcome:	The proposed benchmarks prioritize the text in question-answer pairs while disregarding visual text in images.

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding (2025.acl-srw)

Copied to clipboard

Qi Feng, Yihong Liu, Hinrich Schuetze

CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)

Challenge:	Existing curriculum learning approaches rely on manually defined difficulty metrics which may not accurately reflect the model’s own perspective.
Approach:	They propose a self-adaptive curriculum learning paradigm that prioritizes fine-tuning examples based on difficulty scores predicted by pre-trained language models (PLMs) they evaluate four datasets covering binary and multi-class classification tasks.
Outcome:	The proposed model leads to faster convergence and improved performance compared to standard random sampling.

Copied to clipboard

Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu

GeAR: Generation Augmented Retrieval (2025.findings-acl)

Challenge:	Existing approaches to constraint-aware planning fail to enhance the model’s intrinsic focus on constraints.
Approach:	They propose a constraint-aware reinforcement learning framework that encourages constraint focus and penalizes neglect of LLMs.
Outcome:	The proposed framework outperforms existing frameworks and state-of-the-art reasoning models in a number of real-world applications.

Copied to clipboard

Haoyu Liu, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Furu Wei, Qi Zhang

Information Retrieval

Challenge:	Document retrieval techniques are used to compute semantic similarity between a query and documents, but the scalar similarity fails to reflect enough information, hindering the interpretation of retrieval results.
Approach:	They propose a method which improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules.
Outcome:	The proposed method improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules.

Democratizing Reasoning Ability: Tailored Learning from Large Language Model (2023.emnlp-main)

Copied to clipboard

Zhaoyang Wang, Shaohan Huang, Yuxuan Liu, Jiahai Wang, Minghui Song, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (2025.findings-acl)

Challenge:	Large language models (LLMs) exhibit impressive emergent abilities in natural language processing, but their democratization is hindered due to huge computation requirements and closed-source nature.
Approach:	They propose a tailored learning approach to distill the exclusive reasoning ability to smaller LMs to facilitate democratization.
Outcome:	The proposed approach enables the democratization of the exclusive reasoning ability by leveraging the black-box model as a reasoning teacher.

Copied to clipboard

Jinghui Lu, Haiyang Yu, Yanjie Wang, Yongjie Ye, Jingqun Tang, Ziwei Yang, Binghong Wu, Qi Liu, Hao Feng, Han Wang, Hao Liu, Can Huang

WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models (2025.acl-long)

Challenge:	Existing methods for integrating spatial layouts with text have limitations . existing methods produce overly long text sequences or lack autoregressive traits of LLMs .
Approach:	They introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM) they use OCR-derived text and spatial layouts to integrate with LLMs for document understanding .
Outcome:	The proposed model shows an increase in performance in KIE and VQA tasks.

Copied to clipboard

Huawen Feng, Pu Zhao, Qingfeng Sun, Can Xu, Fangkai Yang, Lu Wang, Qianli Ma, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

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

Challenge:	Recent code large language models have demonstrated impressive performance on code-related tasks.
Approach:	They propose a paradigm that learns from expert battles to address these limitations . they create an arena where leading LLMs challenge each other with evaluations .
Outcome:	The proposed model improves on existing models by leveraging expert battles . it achieves state-of-the-art performance even without relying on proprietary models .

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

Responsible & Trustworthy NLP

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.

Dynamic Curriculum Learning for Low-Resource Neural Machine Translation (2020.coling-main)

Copied to clipboard

Chen Xu, Bojie Hu, Yufan Jiang, Kai Feng, Zeyang Wang, Shen Huang, Qi Ju, Tong Xiao, Jingbo Zhu

Text Generation

Challenge:	Recent work on neural machine translation (NMT) has demonstrated impressive performance improvements and became the de-facto standard.
Approach:	They propose a dynamic curriculum learning method to reorder training samples in training using a Transformer-based system.
Outcome:	The proposed method outperforms baselines on three low-resource machine translation benchmarks and different sized data of WMT’16 En-De.

WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? (2025.emnlp-main)

Copied to clipboard

An-Lan Wang, Jingqun Tang, Lei Liao, Hao Feng, Qi Liu, Xiang Fei, Jinghui Lu, Han Wang, Hao Liu, Yuliang Liu, Xiang Bai, Can Huang

Robustness in NLP

Challenge:	Existing benchmarks for document understanding in the wild are based on scanned or digital documents . however, these benchmarks fail to capture the challenges posed by documents in the real world .
Approach:	They propose a new benchmark that incorporates a diverse set of manually captured document images reflecting real-world conditions.
Outcome:	The proposed model is based on a set of manually captured document images reflecting real-world conditions and is compared with digital or scanned documents.

Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

Copied to clipboard

Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang

Challenge:	Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions?
Approach:	They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values.
Outcome:	The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure.

Auto Search Indexer for End-to-End Document Retrieval (2023.findings-emnlp)

Copied to clipboard

Tianchi Yang, Minghui Song, Zihan Zhang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang

Information Retrieval

Challenge:	Generative retrieval heavily relies on the “preprocessed” document identifiers, thus limiting its retrieval performance and ability to retrieve new documents.
Approach:	They propose a fully end-to-end retrieval paradigm that can learn the best docids for existing and new documents automatically via a semantic indexing module.
Outcome:	The proposed model outperforms baselines on public and industrial datasets and can handle new documents.

MECoT: Markov Emotional Chain-of-Thought for Personality-Consistent Role-Playing (2025.findings-acl)

Copied to clipboard

Yangbo Wei, Zhen Huang, Fangzhou Zhao, Qi Feng, Wei W. Xing

Dialogue Systems & Conversational Agents

Challenge:	Existing Large Language Models struggle to maintain emotionally consistent and psychologically plausible character personalities.
Approach:	They propose a framework that enhances LLMs’ ability to generate authentic personality-driven dialogues through stochastic emotional transitions.
Outcome:	The proposed framework achieves 93.3% emotional accuracy on the RAPD dataset and significantly outperforms existing approaches.

Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding (2026.acl-long)

Copied to clipboard

Yupeng Qi, Ziyu Lyu, Lixin Cui, Lu Bai, Feng Xia

InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles (2025.emnlp-main)

Challenge:	Existing methods for mitigating over-refusal can't maintain low refusal ratio for harmless queries while keeping high for malicious queries.
Approach:	They propose a model-agnostic approach to mitigate over-refusal in large language models . they propose an adaptive contrastive decoding strategy that incorporates or removes the refusal token distribution .
Outcome:	The proposed approach reduces the refusal ratio for over-refusal queries by 10.35% while increasing the refusal rate for malicious queries by 0.13%.

Copied to clipboard

Zizhen Li, Chuanhao Li, Yibin Wang, Qi Chen, Diping Song, Yukang Feng, Jianwen Sun, Jiaxin Ai, Fanrui Zhang, Mingzhu Sun, Kaipeng Zhang

Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning (2026.findings-acl)

Challenge:	Recent large language models (LLMs) have demonstrated strong reasoning abilities across complex mathematical and scientific domains.
Approach:	They propose a framework to assess whether LLMs can capture and apply personalized reasoning styles in social deduction games.
Outcome:	The proposed framework evaluates LLMs on the game Avalon and shows that they can capture and apply individualized reasoning styles.

Copied to clipboard

Heng Yu, Rui Li, Qi Liu, Wenjun Feng, Junfeng Kang, Yi Zhan

Information Retrieval

Challenge:	Existing methods for retrieval-augmented generation fail to provide explicit supervision for internal reasoning process.
Approach:	They propose an Evaluation-driven Retrieval-Augmented Reasoning framework that uses reinforcement learning and a fine-grained evaluation reward to optimize the process.
Outcome:	Eval-RAR outperforms existing methods on QA benchmarks on seven single-hop and multi-hop tasks.

ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format (2023.emnlp-demo)

Copied to clipboard

Qi Zhu, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Baolin Peng, Zheng Zhang, Shutong Feng, Michael Heck, Nurul Lubis, Dazhen Wan, Xiaochen Zhu, Jianfeng Gao, Milica Gasic, Minlie Huang

Robustness in NLP

Challenge:	Existing tools for building TOD systems often lack a user-friendly interface . a toolkit with advanced, easily integrable modules is needed to bridge this gap .
Approach:	They propose a multifaceted dialogue system toolkit that integrates diverse datasets and models with a streamlined training process and in-depth evaluation tools.
Outcome:	The proposed toolkit combines RL and transfer learning to support the rapid development and evaluation of robust dialogue policies.

AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Copied to clipboard

Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song

Thought-Action Graph Reasoning: Faithful and Efficient Reasoning of Large Language Models via Reusing Past Experience (2026.findings-acl)

Challenge:	Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach:	They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome:	The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.

Copied to clipboard

Zhixiao Qi, Feng Huang, Yunqi Zhang, Shijie Zhang, Qingqing Sun, Yongfeng Huang, Minghu Jiang, Shuai Chen, Tianyi Zhang

NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement Learning (2025.emnlp-main)

Challenge:	Existing methods for integrating knowledge graphs with LLMs suffer from poor generalization or low reasoning efficiency.
Approach:	They propose a thought-action Graph (TAG) that decomposes LLM-KG interaction trajectories into fine-grained semantic operators and guides LLM to execute on them.
Outcome:	The proposed paradigm outperforms state-of-the-art methods on KGQA benchmarks while reducing the number of LLM calls and generated tokens.

Copied to clipboard

Yue Fang, Shaohan Huang, Xin Yu, Haizhen Huang, Zihan Zhang, Weiwei Deng, Furu Wei, Feng Sun, Qi Zhang, Zhi Jin

Machine Translation

Challenge:	Existing formal proof assistants rely on instruction tuning and lack fine-grained structural and semantic alignment.
Approach:	They propose a reinforcement learning framework that enables LLMs to translate natural language into formal language such as Lean 4 . they use a model with basic translation ability to refine the model's reinforcement learning .
Outcome:	The proposed method outperforms baseline models on NL-to-Lean 4 tasks.

DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)

Copied to clipboard

Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability.
Approach:	They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence.
Outcome:	The proposed model outperforms baselines on three real-world datasets.

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

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

Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory (2026.acl-long)

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

Zihao Tang, Xin Yu, Ziyu Xiao, Zengxuan Wen, Zelin Li, Jiaxi Zhou, Hualei Wang, Haohua Wang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang

Multimodality

Challenge:	Existing methods for retrieving historical messages are based on similarity-based mechanisms.
Approach:	They propose a system that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection.
Outcome:	The proposed framework achieves state-of-the-art on long-term memory benchmarks and 93.9 on LoCoMo and 91.6 on LongMemEval-S.

SAM3-I: Segment Anything with Instructions (2026.acl-long)

Copied to clipboard

Jingjing Li, Yue Feng, Yuchen Guo, Jincai Huang, Wei Ji, Qi Bi, Yongri Piao, Miao Zhang, Xiaoqi Zhao, Qiang Chen, Shihao Zou, Huchuan Lu, Li Cheng

Low-Resource NLP

Challenge:	Existing methods for concept-level grounding and instruction-level reasoning use coarse representations and iterative mask filtering.
Approach:	They propose an instruction-following extension of the Segment Anything Model 3 family that unifies concept-level grounding and instruction-level reasoning within a single segmentation framework.
Outcome:	Experiments show that SAM3-I achieves appealing performance across referring and reasoning-based segmentation while maintaining its strong concept recall ability.

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.

Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation (2025.emnlp-main)

Copied to clipboard

Yu Zeng, Yukun Qi, Yiming Zhao, Xikun Bao, Lin Chen, Zehui Chen, Shiting Huang, Jie Zhao, Feng Zhao

Multimodality

Challenge:	Existing pipelines for generating high-quality, ultra-detailed image captions are limited by the scarcity of image caption data.
Approach:	They propose a pipeline for generating high-quality, ultra-detailed image captions that integrates both pre-processing and post-processor stages.
Outcome:	The proposed pipeline improves LVLMs' perception and cognitive abilities across multiple vision-language benchmarks.

RouterHGC: Optimized Router for LLM-based Multi-Agent Systems via Heterogeneous Graph Contrastive Learning (2026.findings-acl)

Copied to clipboard

Yitao Xiao, Shaoyong Guo, Guoming Yang, Qingnan Wang, Yinlin Ren, Xuesong Qiu, Qi Feng

Dynamic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis (2024.emnlp-main)

Challenge:	Large Language Models (LLMs)-driven Multi-Agent Systems (MAS) have demonstrated remarkable scalability and generalizability across complex tasks.
Approach:	They propose a new framework for routing using large language models . they formalize routing as node selection through edge-weight prediction .
Outcome:	The proposed framework outperforms the best single LLM and baselines on five datasets . it achieves 0.80%–6.17% accuracy gains on MATH and HotpotQA while reducing inference cost by 27.40%.

Copied to clipboard

Yanjiang Chen, Kai Zhang, Feng Hu, Xianquan Wang, Ruikang Li, Qi Liu

Sentiment Analysis

Challenge:	Existing methods for predicting sentiment polarity of aspects are susceptible to interference caused by irrelevant contexts and lack sentiment knowledge at a data-specific level.
Approach:	They propose a novel Aspect-based sentiment analysis method that leverages attention scores to model the relationships between aspects and contexts.
Outcome:	The proposed method is able to predict sentiments from a set of five benchmark datasets.

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.

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Copied to clipboard

Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

Multilinguality

Challenge:	Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach:	They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome:	The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.

Larger-Context Tagging: When and Why Does It Work? (2021.naacl-main)

Copied to clipboard

Jinlan Fu, Liangjing Feng, Qi Zhang, Xuanjing Huang, Pengfei Liu

Syntactic Text Processing

Challenge:	Existing tagging systems that use sentence-level data are not well understood.
Approach:	They propose a larger-context approach to tagging tasks that incorporates contextual information into existing tapping systems.
Outcome:	The proposed aggregators improve on four tagging tasks and 13 datasets.

Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling (2025.acl-long)

Copied to clipboard

Shihan Dou, Jiayi Chen, Chenhao Huang, Feng Chen, Wei Chengzhi, Huiyuan Zheng, Shichun Liu, Yan Liu, Chenxiao Liu, Chao Xin, Lin Yan, Zongzhang Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Existing reward models concatenate contexts and responses, but they often ignore crucial segments of the context that are important for evaluating the response quality.
Approach:	They propose a reward model that evaluates the response quality based on a given context and assigns a rewards reward.
Outcome:	The proposed framework significantly improves preference modeling by increasing attention to relevant information within the context and achieves better generalizability.

Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2026.acl-long)

Copied to clipboard

Fengyuan Liu, Yi Huang, Sichun Luo, Yuqi Wang, Yazheng Yang, Xinye Li, Zefa Hu, Junlan Feng, Qi Liu

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

Challenge:	Existing approaches to finding effective predictive signals from financial data are limited by their complexity and low signal-to-noise ratio.
Approach:	They propose a framework that combines code-level alpha representation with LLM-driven reasoning and evolutionary search.
Outcome:	The proposed framework combines code-level alpha representation with LLM-driven reasoning and evolutionary search.

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.

SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check (2020.acl-main)

Copied to clipboard

Xingyi Cheng, Weidi Xu, Kunlong Chen, Shaohua Jiang, Feng Wang, Taifeng Wang, Wei Chu, Yuan Qi

Multimodality

Challenge:	Existing methods to detect and correct spelling errors in Chinese take external input or just heuristic rules.
Approach:	They propose to incorporate phonological and visual similarity knowledge into Chinese language models by using a specialized graph convolutional network.
Outcome:	The proposed method outperforms existing models on three human-annotated datasets.

Calibrating LLM-Based Evaluator (2024.lrec-main)

Copied to clipboard

Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

Alleviating Performance Degradation Caused by Out-of-Distribution Issues in Embedding-Based Retrieval (2025.findings-emnlp)

Challenge:	Existing models for large language models lack the ability to calibrate their outputs towards human preference.
Approach:	They propose a multi-stage, gradient-free approach to calibrate an LLM-based evaluator toward human preference.
Outcome:	The proposed approach improves correlation with expert evaluation on multiple text quality evaluation datasets.

Copied to clipboard

Haotong Bao, Jianjin Zhang, Qi Chen, Weihao Han, Zhengxin Zeng, Ruiheng Chang, Mingzheng Li, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang

AlphaQT-Bench: Diagnosing the Gap between Financial Code Generation and Quantitative Reasoning in LLMs (2026.findings-acl)

Challenge:	Recent studies reveal query out-of-distribution issues degrading ANN performance . a distribution regularizer is introduced into the encoder training objective to encourage alignment between query and base embeddings.
Approach:	They introduce a distribution regularizer into the encoder training objective to encourage alignment between query and base embeddings.
Outcome:	The proposed method consistently improves retrieval performance across multiple datasets.

Copied to clipboard

Sichun Luo, Yi Huang, Shichang Meng, Fengyuan Liu, Mukai Li, Qinghua Yao, Zefa Hu, Junlan Feng, Qi Liu

Programming Languages in NLP

Challenge:	Existing benchmarks rely on outcome-driven metrics such as profitability and look-ahead bias.
Approach:	They propose a diagnostic benchmark for instruction-grounded financial code generation under strict semantic and temporal constraints.
Outcome:	The proposed benchmarks show that the models fail under causal, structural, or functional constraints.

STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training (2026.acl-long)

Copied to clipboard

Qiuyi Qi, Tian Liang, Mutian Bao, Jinjian Zhang, Dongnan Liu, Wei Zhou, Linjian Mo, Ming Kong, Jie Liu, Feng Zhang, Qiang Zhu

AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following (2026.acl-long)

Challenge:	Prior work has explored step-level supervision using Shannon-entropy-based uncertainty signals, which conflate inherent state complexity with agent confidence.
Approach:	They propose a hierarchical group-based RL framework that leverages normalized entropy to locate outlier steps associated with trajectory neglect and optimizes them via a mechanism of trajectory-aware reward and trajectory-independent penalty.
Outcome:	Experiments on ALFWorld, WebShop, and Search-Augmented QA show that STAPO achieves state-of-the-art performance while substantially alleviating trajectory neglect.

Copied to clipboard

Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Kumar Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Hassan Awadalla, Manaal Faruqui