Papers by Xin Feng

SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have shown impressive language capabilities, but most of them have very unbalanced performance across different languages.
Approach:	They propose to use question translation data to enhance LLMs' multilingual capabilities by using mechanistic interpretability methods.
Outcome:	The proposed method improves multilingual alignment even with unannotated answers in English and a wide range of languages even with instruction-tuned LLMs.

Copied to clipboard

Xin Xie, Dongyun Xue, Wuguannan Yao, Mingxiao Feng, Wengang Zhou, Xiang Qi, Houqiang Li, Peng Zhang

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-Context QA (2025.findings-acl)

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

Jiajie Zhang, Yushi Bai, Xin Lv, Wanjun Gu, Danqing Liu, Minhao Zou, Shulin Cao, Lei Hou, Yuxiao Dong, Ling Feng, Juanzi Li

Question Answering

Challenge:	Current long-context large language models lack citations to support their responses, making verification difficult due to potential hallucinations.
Approach:	They propose to use off-the-shelf LLMs to automatically construct long-context QA instances with precise sentence-level citations and leverage this pipeline to construct a large-scale SFT dataset for LQAC.
Outcome:	The proposed pipeline can generate responses with fine-grained citations on the fly, surpassing existing models including GPT-4o.

How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel (2026.acl-industry)

Copied to clipboard

Yongqi Tong, Xiaoyun Feng, Lyuxin Xue, Jianshe Li, Xin Zhang, Jiang-Ming Yang

Challenge:	Traditional industrial agents rely on modular workflows that fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency.
Approach:	They propose a paradigm shift from external workflows to internalized knowledge representation that consolidates complex business logic and SOPs directly into the model’s parameters.
Outcome:	The proposed model breaks the impossible triangle of latency, accuracy, and complexity.

SURE: Mutually Visible Objects and Self-generated Candidate Labels For Relation Extraction (2025.coling-main)

Copied to clipboard

Yuxuan Feng, Qian Chen, Qianyou Wu, Xin Guo, Suge Wang

Information Extraction & Text Mining

Challenge:	Joint relation extraction models face high computational complexity, complex network architectures, difficult parameter tuning and limited interpretability.
Approach:	They develop a candidate label marker mechanism that prioritizes strategic label selection over simple label generation.
Outcome:	The proposed candidate label marks improve the SOTA methods by 2.5%, 1.9%, 1.2% . the proposed candidate labels improve the performance of the proposed methods .

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

Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents (2025.findings-emnlp)

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

Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xingxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao Dang, Yu Rong, Deli Zhao, Tian Feng, Lidong Bing

Challenge:	Existing methods for idea generation either trivially prompt LLMs or expose LLM to extensive literature without indicating useful information.
Approach:	They propose a chain-of-ideas agent that organizes literature in a chains structure . they propose evaluating idea-generation methods from different perspectives .
Outcome:	The proposed agent outperforms existing methods and matches human quality in idea generation.

CPL: Counterfactual Prompt Learning for Vision and Language Models (2022.emnlp-main)

Copied to clipboard

Xuehai He, Diji Yang, Weixi Feng, Tsu-Jui Fu, Arjun Akula, Varun Jampani, Pradyumna Narayana, Sugato Basu, William Yang Wang, Xin Wang

Latent Suicide Risk Detection on Microblog via Suicide-Oriented Word Embeddings and Layered Attention (D19-1)

Challenge:	Existing prompt tuning methods tend to learn spurious or entangled representations, leading to poor generalization to unseen concepts.
Approach:	They propose a prompt tuning technique that tunes the learnable prompt for pre-trained vision and language models.
Outcome:	The proposed method improves few-shot performance on vision and language tasks over existing prompt tuning methods.

Copied to clipboard

Lei Cao, Huijun Zhang, Ling Feng, Zihan Wei, Xin Wang, Ningyun Li, Xiaohao He

PRIM: Towards Practical In-Image Multilingual Machine Translation (2025.emnlp-main)

Challenge:	Existing approaches to detect suicidal ideation on social media are limited to a small group of people.
Approach:	They propose to use tree holes to embed words into microblogs to strengthen the sensibility of suicide-related lexicons and to use a two-layered attention mechanism to grasp intermittently changing points from individual's open blog streams.
Outcome:	The proposed approach can achieve over 91% accuracy with the use of suicide-oriented word embeddings and attention on a large-scale well-labelled suicide data set.

Copied to clipboard

Yanzhi Tian, Zeming Liu, Zhengyang Liu, Chong Feng, Xin Li, Heyan Huang, Yuhang Guo

LongReward: Improving Long-context Large Language Models with AI Feedback (2025.acl-long)

Challenge:	Current research on in-image machine translation focuses on synthetic data with simple background, single font, fixed text position, and bilingual translation.
Approach:	They propose an end-to-end model to handle the challenge of practical conditions in PRIM . they annotate a real-world one-line text image with complex background, fonts, diverse text positions .
Outcome:	The proposed model improves translation quality and visual effect compared to other models.

Copied to clipboard

Jiajie Zhang, Zhongni Hou, Xin Lv, Shulin Cao, Zhenyu Hou, Yilin Niu, Lei Hou, Yuxiao Dong, Ling Feng, Juanzi Li

DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection (2022.findings-emnlp)

Challenge:	In recent years, significant advancements have been achieved in the development of long-context large language models (LLMs).
Approach:	They propose a method that utilizes an off-the-shelf LLM to provide rewards for long-context model responses from four human-valued dimensions: helpfulness, logicality, faithfulness, and completeness.
Outcome:	The proposed method improves models’ long-context performance and enhances their ability to follow short instructions.

Copied to clipboard

Haoran Meng, Zheng Xin, Tianyu Liu, Zizhen Wang, He Feng, Binghuai Lin, Xuemin Zhao, Yunbo Cao, Zhifang Sui

Natural Language Interfaces

Challenge:	DialogUSR is a plug-in and domain-agnostic module that empowers multi-intent detection for chatbots . a single user query triggers inquiries on highspeed train ticket price and weather of destination.
Approach:	They propose a dialog utterance splitting and reformulation task that splits multi-intent user query into multiple single-intention sub-queries and recovers all coreferred and omitted information in the sub-questions.
Outcome:	The proposed model can be used to split multi-intent user queries into multiple sub-queries . it can be trained in two stages and perform in-depth analyses on the proposed models .

MixTEA: Semi-supervised Entity Alignment with Mixture Teaching (2023.findings-emnlp)

Copied to clipboard

Feng Xie, Xin Song, Xiang Zeng, Xuechen Zhao, Lei Tian, Bin Zhou, Yusong Tan

Low-Resource NLP

Challenge:	Existing methods to learn informative entity embeddings are insufficient for semi-supervised entity alignment.
Approach:	They propose a semi-supervised method which guides the model learning with an end-to-end mixture teaching of manually labeled mappings and probabilistic pseudo mappings.
Outcome:	The proposed method is superior to existing methods on benchmark datasets and further analyses.

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention (2026.acl-long)

Copied to clipboard

Zhen Yang, Mingyang Zhang, Feng Chen, Ganggui Ding, Liang Hou, Xin Tao, Ying-Cong Chen

Responsible & Trustworthy NLP

Challenge:	Recent advances in large language models (LLMs) have focused on test-time scaling to improve reasoning quality but at the cost of efficiency.
Approach:	They propose a training-free framework that enhances reasoning accuracy and stability with minimal overhead.
Outcome:	The proposed framework yields consistent gains across general, coding, and STEM tasks while remaining highly efficient.

Leveraging Unpaired Feedback for Long-Term LLM-based Recommendation Tuning (2025.findings-emnlp)

Copied to clipboard

Jizhi Zhang, Chongming Gao, Wentao Shi, Xin Chen, Jingang Wang, Xunliang Cai, Fuli Feng

Challenge:	a recent study highlights unpaired feedback as a key challenge for long-term LLM-based recommenders . unpaired user feedback is crucial for improving LLMs in dynamic user environments, authors say .
Approach:	They propose a framework that incorporates unpaired feedback into LLMs to improve long-term recommendation performance.
Outcome:	The proposed framework improves long-term recommendation performance by incorporating unpaired feedback without requiring paired supervision.

Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training (2025.findings-acl)

Copied to clipboard

Zhijun Wang, Jiahuan Li, Hao Zhou, Rongxiang Weng, Jingang Wang, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

Probing and Boosting Large Language Models Capabilities via Attention Heads (2025.emnlp-main)

Challenge:	Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data.
Approach:	They investigate the existence of code-switching in the pre-training corpus and categorize it into four types within two quadrants.
Outcome:	The proposed approach improves performance across benchmarks and representation space.

Copied to clipboard

Dezhi Zhao, Xin Liu, Xiaocheng Feng, Hui Wang, Bing Qin

Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information Flow (2025.findings-emnlp)

Challenge:	Existing approaches to identifying capabilities rely on external signals with limited structural grounding . emergence of specific capabilities remains poorly understood .
Approach:	They propose a lightweight approach that links LLM capabilities to internal components by identifying correspondences at the level of attention heads.
Outcome:	The proposed approach improves accuracy on MMLU and BBH by 1 to 1.5 points over gradient-based method and 5 to 6 points over other intermediate-state baselines.

Copied to clipboard

Jianfei Zhao, Feng Zhang, Xin Sun, Chong Feng

Multimodality

Challenge:	Decode-Only models propagate information from left to right, but the model's attention still focuses on the visual representations, resulting in hallucinations.
Approach:	They propose to leverage the core information embedded in semantic representations to enhance the model's visual understanding by leveraging the attention distributions.
Outcome:	The proposed method reduces hallucinations by 80% by aligning the attention distribution with the actual information flow.

DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping (2026.findings-acl)

Copied to clipboard

Wei Fan, Wenlin Yao, Zheng Li, Feng Yao, Xin Liu, Liang Qiu, Qingyu Yin, Yangqiu Song, Bing Yin

Reasoning

Challenge:	Existing approaches to planning involve implicit planning or introduce explicit planners without systematically optimizing the planning stage.
Approach:	They propose an end-to-end RL framework that enhances the planning capabilities of deep research agents.
Outcome:	Experiments show that DeepPlanner improves planning quality and achieves state-of-the-art results under a lower training budget.

Large Language Models Are Cross-Lingual Knowledge-Free Reasoners (2025.naacl-long)

Copied to clipboard

Peng Hu, Sizhe Liu, Changjiang Gao, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

Reasoning

Challenge:	Large language models have demonstrated impressive reasoning capabilities across multiple languages, but the relationship between capabilities in different languages is less explored.
Approach:	They decompose the process of reasoning tasks into two separate components: knowledge retrieval and knowledge-free reasoning.
Outcome:	The proposed model can be transferred across source-target languages despite secondary impact of resource in some specific target languages, while cross-lingual knowledge retrieval significantly hinders the transfer.

AgentOCR: Reimagining Agent History via Optical Self-Compression (2026.acl-long)

Copied to clipboard

Lang Feng, Fuchao Yang, Feng Chen, Xin Cheng, Haiyang Xu, Zhenglin Wan, Ming Yan, Bo An

Visual Data in NLP

Challenge:	Recent advances in large language models (LLMs) have enabled agentic systems trained with reinforcement learning over multi-turn interaction, but practical deployment is bottlenecked by rapidly growing textual histories that inflate token and memory costs.
Approach:	They propose a framework that represents the accumulated observation-action history as a compact rendered image.
Outcome:	The proposed framework preserves over 95% of text-based agent performance while significantly reducing token consumption (>50%), yielding consistent token and memory efficiency.

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

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

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

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.

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

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.

Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers (2026.acl-long)

Copied to clipboard

Xin Chen, Feng Jiang, Yiqian Zhang, Hardy Chen, Shuo Yan, Wenya Xie, Min Yang, Shujian Huang

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

Challenge:	Existing reasoning-oriented LLMs lack a blind self-thinking paradigm . current models fail to recognize when their reasoning is underinformed or based on ambiguous user instructions .
Approach:	They propose a new reasoning paradigm that transforms LLMs into proactive inquirers that interleave reasoning with clarification.
Outcome:	The proposed model outperforms baseline models on mathematical reasoning, code generation, and document editing.

Copied to clipboard

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

Information Retrieval

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

DPDV: Dual-Pathway and Dual-View Representation Learning for Bridging Information Asymmetry in Text-Video Retrieval (2026.acl-long)

Copied to clipboard

Zequn Xie, Xin Liu, Fangming Feng, Boyun Zhang, Tao Jin

Visual Data in NLP

Challenge:	Existing methods for text-based person anomaly search fail to address the pose-semantic gap . asymmetric cross-modal information poses a challenge to accurately establishing retrieval relationships .
Approach:	They propose a video retrieval framework that partitions visual features into two categories based on relevance to the text query and performs effective interaction.
Outcome:	The proposed framework achieves leading retrieval performance on five benchmark datasets.

PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Yunzhi Shen, Hao Zhou, Xin Huang, Xue Han, Junlan Feng, Shujian Huang

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

Challenge:	Reinforcement learning (RL) has shown strong promise for LLM-based machine translation . however, translation-oriented RL remains challenged by high-variance policy gradients induced by Monte Carlo baselines and large trajectory space that favors global exploration over fine-grained local optimization.
Approach:	They propose a two-stage RL framework that uses post-editing as an auxiliary task to stabilize training and guide overall optimization.
Outcome:	The proposed framework supports global exploration and fine-grained optimization while supporting global exploration.

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

SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs (2025.emnlp-main)

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.

Copied to clipboard

Yuanyang Yin, Yaqi Zhao, Yajie Zhang, Yuanxing Zhang, Ke Lin, Jiahao Wang, Xin Tao, Pengfei Wan, Wentao Zhang, Feng Zhao

GiFT: Gibbs Fine-Tuning for Code Generation (2025.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) integrate visual and textual inputs, yet modality alignment remains one of the most challenging aspects.
Approach:	They propose a token-level supervision alignment method that enables more precise visual-text alignment during pretraining.
Outcome:	The proposed method improves performance across various model sizes, with smaller models benefiting the most.

Copied to clipboard

Haochen Li, Wanjin Feng, Xin Zhou, Zhiqi Shen

Programming Languages in NLP

Challenge:	Training Large Language Models (LLMs) with synthetic data is a prevalent practice in code generation.
Approach:	They propose a method to fine-tune large language models with code drawn from a conditional distribution, conditioned on a specific seed description.
Outcome:	The proposed method improves performance on four datasets and shows that it can be used to fine-tune LLMs with code derived from the marginal distribution.

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.

Understanding LLMs’ Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From (2025.emnlp-main)

Copied to clipboard

Changjiang Gao, Hankun Lin, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Jiajun Chen, Shujian Huang

Cross-Lingual Transfer

Challenge:	Cross-lingual context retrieval is a fundamental aspect of cross-lingual alignment, but the performance and mechanism of it for large language models (LLMs) remains unclear.
Approach:	They evaluate cross-lingual context retrieval of over 40 large language models . they use cross-linguistic machine reading comprehension as a representative scenario .
Outcome:	The results show that open LLMs show strong cross-lingual context retrieval ability . the results also show that their oracle performances improve after training .

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards (2026.acl-long)

Copied to clipboard

Jiajie Zhang, Xin Lv, Ling Feng, Lei Hou, Juanzi Li

Responsible & Trustworthy NLP

Challenge:	Existing methods for reinforcement learning (RL) rely on binary outcome rewards that fail to capture the comprehensiveness and factuality of agents’ reasoning process.
Approach:	They propose a reward framework that emphasizes reasoning comprehensiveness, factual grounding, and evidence connectivity.
Outcome:	The proposed framework outperforms standard outcome-based RL baselines across multiple deep search benchmarks and shows that it discourages shortcut exploitation and promotes comprehensive, evidence-grounded reasoning.

SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning (2026.acl-long)

Copied to clipboard

Peidong Wang, Zhiming Ma, Xin Dai, YongKang Liu, Shi Feng, Xiaocui Yang, Wenxing Hu, Zhihao Wang, Mingjun Pan, Li Yuan, Daling Wang

Multimodality

Challenge:	Existing methods for fraud detection rely on transcribed text, lacking acoustic cues . a proposed framework for audio-based slow-thinking fraud detection eliminates transcription errors .
Approach:	They propose a framework for audio-based slow-thinking fraud detection that eliminates transcription errors and rewards slow-thought reasoning by capturing fine-grained audio details.
Outcome:	The proposed method improves accuracy, inference efficiency, and real-time processing capabilities.

LexGenius: An Expert-Level Benchmark for Large Language Models in Legal General Intelligence (2026.findings-acl)

Copied to clipboard

Wenjin Liu, Haoran Luo, Xin Feng, Xiang Ji, Lijuan Zhou, Rui Mao, Jiapu Wang, Shirui Pan, Erik Cambria