Papers by Xinyu Zhang

On Prefix-tuning for Lightweight Out-of-distribution Detection (2023.acl-long)

Challenge:	Existing tabular data synthesis methods fail to account for cross-modal heterogeneity of real-world tables, where structured continuous and discrete attributes coexist with unstructured long-text columns.
Approach:	They propose a framework that synergistically trains an LLM-based text generator and a deep-learning-based non-textual generator to quantify cross-modal semantic alignment.
Outcome:	The proposed framework outperforms state-of-the-art frameworks in fidelity, diversity, and task utility.

Copied to clipboard

Yawen Ouyang, Yongchang Cao, Yuan Gao, Zhen Wu, Jianbing Zhang, Xinyu Dai

TC–RAG: Turing–Complete RAG’s Case study on Medical LLM Systems (2025.acl-long)

Challenge:	Out-of-distribution (OOD) detection is a fundamental task vexing real-world applications . fine-tuning based methods require storing fine- tuned models for each scenario .
Approach:	They propose an unsupervised prefix-tuning based OOD detection framework called PTO . they propose to take advantage of optional training data labels and targeted OOD data .
Outcome:	The proposed framework performs better than existing methods under a wide range of metrics, detection settings, and OOD types.

Copied to clipboard

Xinke Jiang, Yue Fang, Rihong Qiu, Haoyu Zhang, Yongxin Xu, Hao Chen, Wentao Zhang, Ruizhe Zhang, Yuchen Fang, Xinyu Ma, Xu Chu, Junfeng Zhao, Yasha Wang

Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot (2025.findings-emnlp)

Challenge:	Existing approaches to RAG neglect system state variables, resulting in poor performance and erroneous knowledge accumulation.
Approach:	They propose a framework that incorporates a Turing Complete System to manage state variables and manage retrieval halting.
Outcome:	The proposed framework improves on seven real-world healthcare datasets and shows that it is more accurate than existing methods.

Copied to clipboard

Xiang Cheng, Chengyan Pan, Minjun Zhao, Deyang Li, Fangchao Liu, Xinyu Zhang, Xiao Zhang, Yong Liu

Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment (2024.acl-long)

Challenge:	In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs).
Approach:	They introduce CoT to exemplars of ICL to enhance the reasoning capability . however, it remains unclear whether CoT exemplar is still beneficial for recent, stronger models in such tasks.
Outcome:	The enhanced exemplars fail to improve the model’s reasoning performance, despite being constructed using answers from advanced models such as Qwen2.5-Max and DeepSeek-R1.

Copied to clipboard

Yunxin Li, Xinyu Chen, Baotian Hu, Haoyuan Shi, Min Zhang

Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards (2026.acl-long)

Challenge:	Recent Large Multimodal Models (LMMs) focus on visual knowledge-dimension alignment, but ignore visual knowledge.
Approach:	They propose a cognitive visual-language mapper that integrates visual-linguistic knowledge alignment with a fine-grained knowledge Adapter.
Outcome:	The proposed model significantly improves LMMs on knowledge-based visual question answering (VQA) it also improves the performance of other models, including GPT-4V and Gemini-Pro.

Copied to clipboard

Xinyu Tang, Yuliang Zhan, Zhixun Li, Xin Zhao, Zhenduo Zhang, Zujie Wen, Zhiqiang Zhang, Jun Zhou

Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation (2023.emnlp-main)

Challenge:	Large reasoning models are typically trained using reinforcement learning with verifiable reward (RLVR) positive and negative self-generated rollouts are used to update the model's policy . positive samples sharpen existing correct reasoning patterns, while negative samples encourage exploration of new reasoning paths.
Approach:	They propose a method that allocates advantage signals to key tokens across different polarities.
Outcome:	The proposed method improves the ability of large reasoning models to learn from their own generated rollouts.

Copied to clipboard

Jiayu Lin, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei

TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs (2026.acl-long)

Challenge:	Existing work describes paragraph-level counter-argument generation task as paragraph-based . however, sentence-level generation can be quite different due to its unique constraints and brevity-focused challenges.
Approach:	They propose a benchmark framework for sentence-level counter-argument generation . they use an annotated debate forum dataset to generate high-quality counter-argments .
Outcome:	The proposed framework and evaluator are competitive in counter-argument generation tasks.

Copied to clipboard

Ziyi Wang, Chen Zhang, Wenjun Peng, Qi Wu, Xinyu Wang

Unraveling and Mitigating Retriever Inconsistencies in Retrieval-Augmented Large Language Models (2024.findings-acl)

Challenge:	Existing explainability methods for large language models have been limited in capturing interaction-dependent belief dynamics and multi-agent reasoning.
Approach:	They propose a tri-view explainability framework that instruments sequential decision making with aligned artifacts.
Outcome:	The proposed framework enables analysis of explanation faithfulness, belief dynamics, and evaluator reliability, revealing systematic mismatches between what agents say, what they believe, and what they do.

Copied to clipboard

Mingda Li, Xinyu Li, Yifan Chen, Wenfeng Xuan, Weinan Zhang

Exploring Multimodal Relation Extraction of Hierarchical Tabular Data with Multi-task Learning (2025.acl-long)

Challenge:	Retrieval-Augmented Large Language Models (RALMs) do not consistently outperform the original retrieval-free Language Model (LM).
Approach:	They propose a trainable framework that can adaptively retrieve from different knowledge sources and effectively decrease unpredictable reader errors.
Outcome:	The proposed framework significantly improves performance over the RALM with a single retriever by significantly reducing inconsistent behaviors.

Copied to clipboard

Xinyu Zhang, Aibo Song, Jingyi Qiu, Jiahui Jin, Tianbo Zhang, Xiaolin Fang

ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models (2024.emnlp-main)

Challenge:	Existing studies overlook the need of mining relations among multiple columns rather than just the semantic relation between two specific columns in real-world practice.
Approach:	They propose a Chain-of-Thought distillation framework with self-correction mechanism to enhance MLLMs’ reasoning capabilities without increasing parameter scale.
Outcome:	The proposed method significantly outperforms baselines on wide datasets.

Copied to clipboard

Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana

M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis (2023.emnlp-main)

Challenge:	Currently, tool-augmented large language models (LLMs) only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100.
Approach:	They propose a multi-level diagnostic process to assess the LLM's hallucinations through two perspectives: depth and breadth.
Outcome:	The proposed diagnostic process assesses the hallucinations of large language models through two perspectives: depth and breadth.

Copied to clipboard

Fei Zhao, Chunhui Li, Zhen Wu, Yawen Ouyang, Jianbing Zhang, Xinyu Dai

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline (2022.naacl-main)

Challenge:	Existing work mainly utilizes image information to improve the performance of MABSA task.
Approach:	They propose a multimodal Aspect-based Sentiment Analysis task that uses image information to improve model performance.
Outcome:	The proposed framework outperforms state-of-the-art work on three sub-tasks of MABSA.

Copied to clipboard

Xiangyang Liu, Tianxiang Sun, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu

OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving (2026.findings-acl)

Challenge:	Rather than pursuing the reachless SOTA accuracy, researchers are focusing on model efficiency and usability.
Approach:	They propose an evaluation and a public leaderboard for efficient NLP models that depicts the Pareto Frontier for various language understanding tasks.
Outcome:	The proposed model outperforms or performs on par with SOTA compressed and early exiting models.

Copied to clipboard

Xinyu Zhang, Boxuan Zhang, Yuchen Wan, Lingling Zhang, YiXing Yao, Bifan Wei, Yaqiang Wu, Jun Liu

Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning (2023.findings-acl)

Challenge:	Existing benchmarks focus on Mathematical Programming and Combinatorial Optimization, hindering comprehensive evaluation.
Approach:	They propose a benchmarking tool that compares 1,000 curated optimization problems across three difficulty levels.
Outcome:	The proposed model improves performance on hard problems while maintaining 27% accuracy.

Copied to clipboard

Yongkang Wu, Meng Han, Yutao Zhu, Lei Li, Xinyu Zhang, Ruofei Lai, Xiaoguang Li, Yuanhang Ren, Zhicheng Dou, Zhao Cao

Are LLM-based Evaluators Confusing NLG Quality Criteria? (2024.acl-long)

Challenge:	SylloBase is a benchmark for syllogistic reasoning, a critical capability widely required in natural language understanding tasks, such as text entailment and question answering.
Approach:	They propose to use a benchmark to learn syllogistic reasoning on a set of templates and to use them to generate and understand slogisms.
Outcome:	The proposed benchmark covers a complete taxonomy of syllogism reasoning patterns, and contains both automatically and manually constructed samples.

Copied to clipboard

Xinyu Hu, Mingqi Gao, Sen Hu, Yang Zhang, Yicheng Chen, Teng Xu, Xiaojun Wan

Text Classification

Challenge:	Existing studies show that LLMs confuse evaluation criteria, which reduces their reliability.
Approach:	They propose a hierarchical classification system for 11 common aspects with corresponding different evaluation criteria.
Outcome:	The proposed system is based on 11 common aspects with different evaluation criteria.

Towards General Agentic Intelligence via Environment Scaling (2026.findings-acl)

Copied to clipboard

Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Ningyu Zhang, Fei Huang, Wentao Zhang, Jingren Zhou

MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency (2025.findings-acl)

Challenge:	Diverse real-world APIs require precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments.
Approach:	They propose a framework that scales up environments to enable agentic intelligence . they use a two-phase agent fine-tuning strategy to first endow agents with basic agentic capabilities, then specializing them for domain-specific contexts.
Outcome:	Experiments on -bench, -Bench, and ACEBench show that the model significantly enhances the models’ function-calling capability.

Copied to clipboard

Junzhe Zhang, Huixuan Zhang, Xunjian Yin, Baizhou Huang, Xu Zhang, Xinyu Hu, Xiaojun Wan

Reward Mixology: Crafting Hybrid Signals for Reinforcement Learning Driven In-Context Learning (2025.findings-emnlp)

Challenge:	Existing benchmarks for knowledge editing in multimodal large language models focus on limited scenarios due to the lack of rigorous definition of multimodal knowledge.
Approach:	They propose a decomposed definition of multimodal knowledge and a benchmark to evaluate it.
Outcome:	The proposed method reveals that it is difficult to define multimodal knowledge editing in LLMs.

Copied to clipboard

Changshuo Zhang, Ang Gao, Xiao Zhang, Yong Liu, Deyang Li, Fangchao Liu, Xinyu Zhang

Low-Resource NLP

Challenge:	Existing methods for in-context learning (ICL) performance rely on quality and ordering of demonstrations.
Approach:	They propose a method that models iterative demonstration selection as a Markov Decision Process and craft hybrid reward signals.
Outcome:	The proposed method combines outcome-based accuracy signals with process-oriented signals like stepwise influence and label entropy improvement.

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction (2026.findings-acl)

Copied to clipboard

Xu Shen, Qi Zhang, Song Wang, Zhen Tan, Xinyu Zhao, Laura Yao, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Kwonjoon Lee, Tianlong Chen

SCoder: Progressive Self-Distillation for Bootstrapping Small-Scale Data Synthesizers to Empower Code LLMs (2025.findings-emnlp)

Challenge:	Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors.
Approach:	They propose a metacognitive framework that enables step-level error detection and self-correction in Large Language Model based multi-agent systems (MAS) .
Outcome:	The proposed framework outperforms baselines on the Who When benchmark and delivers consistent gains on AgentErrorBench.

Copied to clipboard

Xinyu Zhang, Changzhi Zhou, Linmei Hu, Luhao Zhang, Xiancai Chen, Haomin Fu, Yang Yang, Mengdi Zhang

Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch (2025.acl-long)

Challenge:	Existing code large language models rely on large-scale instruction data distilled from proprietary LLMs for fine-tuning, which typically incurs high costs.
Approach:	They propose an iterative self-distillation approach to bootstrap small-scale LLMs . they use large-scale instruction data distilled from proprietary LLM for fine-tuning .
Outcome:	The proposed method reduces reliance on proprietary LLMs and minimizes costs.

Copied to clipboard

Yuyang Ding, Xinyu Shi, Xiaobo Liang, Juntao Li, Zhaopeng Tu, Qiaoming Zhu, Min Zhang

MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation (2026.findings-acl)

Challenge:	Existing methods to improve the mathematical reasoning capabilities of Large Language Models (LLMs) are limited due to the proprietary nature of the data.
Approach:	They propose a data synthesis method that generates large-scale mathematical reasoning datasets using lightweight 7B-scale models.
Outcome:	The proposed method outperforms existing open-source datasets in both in-domain and out-of-domain evaluations and shows improvements in code reasoning tasks.

Copied to clipboard

Haoyuan Shi, Yunxin li, Nanhao Deng, Zhenran Xu, Xinyu Chen, Longyue Wang, Baotian Hu, Min Zhang

PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning (2025.acl-long)

Challenge:	Existing evaluation methods for complex multi-shot video are anchored to single-shot paradigms, lacking comprehensive story assets and cross-shot metrics.
Approach:	They propose a framework that synergizes the high-level semantic reasoning of Large Multimodal Models with the fine-grained perceptual rigor of domain-specific expert models.
Outcome:	The proposed framework synergizes the high-level semantic reasoning of Large Multimodal Models with the fine-grained perceptual rigor of domain-specific expert models.

Copied to clipboard

Xinyu Zhang, Yuxuan Dong, Yanrui Wu, Jiaxing Huang, Chengyou Jia, Basura Fernando, Mike Zheng Shou, Lingling Zhang, Jun Liu

HierGR: Hierarchical Semantic Representation Enhancement for Generative Retrieval in Food Delivery Search (2025.acl-industry)

Challenge:	Large language models demonstrate remarkable capabilities across various domains, including mathematics and logic reasoning.
Approach:	They propose a physics-based reasoning benchmark that includes physics theorems and constraints and a Physics Solution Auto Scoring Framework to evaluate physics based reasoning in large language models.
Outcome:	The proposed framework enables models to achieve less than 60% on answer-level evaluation, with performance dropping from knowledge questions (75.11%) to hard problems (31.99%).

Copied to clipboard

Fuwei Zhang, Xiaoyu Liu, Xinyu Jia, Yingfei Zhang, Zenghua Xia, Fei Jiang, Fuzhen Zhuang, Wei Lin, Zhao Zhang

Accurate KV Cache Quantization with Outlier Tokens Tracing (2025.acl-long)

Challenge:	Generative retrieval (GR) is an emerging search paradigm for food delivery search.
Approach:	They propose a method that harnesses the advanced query understanding capabilities of large language models to enhance the retrieval of results for complex and long-tail queries in food delivery search scenarios.
Outcome:	The proposed method increases the number of online orders by 0.68% for complex search intents.

Copied to clipboard

Yi Su, Yuechi Zhou, Quantong Qiu, Juntao Li, Qingrong Xia, Ping Li, Xinyu Duan, Zhefeng Wang, Min Zhang

EFUF: Efficient Fine-Grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) require substantial computational resources during deployment.
Approach:	They propose a method to identify outlier tokens and exclude them from quantization . they find that the method can deliver a 6.4 times reduction in memory usage and a 2.5 times increase in throughput .
Outcome:	The proposed method delivers a 6.4 times reduction in memory usage and a 2.5 times increase in throughput under 2-bit quantization.

Copied to clipboard

Shangyu Xing, Fei Zhao, Zhen Wu, Tuo An, Weihao Chen, Chunhui Li, Jianbing Zhang, Xinyu Dai

RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios (2025.findings-emnlp)

Challenge:	Existing methods to eliminate hallucinations require expensive human annotation . hallucination in multimodal large language models poses unique challenges for current research .
Approach:	They propose a fine-grained unlearning framework that performs gradient ascent to eliminate hallucinations without paired data.
Outcome:	The proposed method reduces hallucinations while preserving quality with modest computational overhead.

Copied to clipboard

Fei Zhao, Chengqiang Lu, Yufan Shen, Qimeng Wang, Yicheng Qian, Haoxin Zhang, Yan Gao, null Yiwu, Yao Hu, Zhen Wu, Shangyu Xing, Xinyu Dai

Minos: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text (2026.findings-acl)

Challenge:	RealBench is the first Chinese multimodal multi-image dataset . the dataset contains 9393 samples and 69910 images .
Approach:	They propose to create a Chinese multimodal multi-image dataset using 21 models . they use closed-source models that support multi-inputs as well as open-source visual and video models a .
Outcome:	The first Chinese multimodal multi-image dataset contains 9393 samples and 69910 images.

Copied to clipboard

Junzhe Zhang, Huixuan Zhang, Xinyu Hu, Li Lin, Mingqi Gao, Shi Qiu, Xiaojun Wan

STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework (2025.findings-acl)

Challenge:	Existing evaluation models struggle to achieve consistent performance across image-to-text (I2T) and text-to image (T2I) tasks.
Approach:	They construct a multimodal evaluation model using a large multimodal dataset and rigorous quality control strategies to train it.
Outcome:	The proposed model achieves state-of-the-art evaluation performance across 16 out-of domain datasets covering both I2T and T2I tasks among all open-source multimodal evaluation models and remain competitive with closed-source models.

Copied to clipboard

Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jerry Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Xie Kun, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma

Multi-Hop Knowledge Editing via Critic-Guided Multi-Agent Reasoning (2026.findings-acl)

Challenge:	Existing datasets suffer from outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation.
Approach:	They propose a human-in-the-loop, multi-agent data generation framework that integrates reasoning-dense filters, multiagent collaboration, and human mathematicians’ evaluations to ensure the reliability and quality of the dataset.
Outcome:	The proposed framework improves accuracy and quality of the 2,000-synthesized datasets by integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians’ evaluations.

Copied to clipboard

Xudong Li, Yuhang Tian, Dandan Song, Zhijing Wu, Shuhao Zhang, Jun Yang, Yongyu Huo, Changzhi Zhou, Xinyu Zhang, Chenhao Li, Huipeng Ma, Luan Zhang, Yan Xu, Qian Liu

KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models (2025.findings-emnlp)

Challenge:	Existing knowledge editing methods rely on unidirectional, feed-forward pipelines . a minor retrieval error or logical mismatch at an early hop can become a silent failure .
Approach:	They propose a framework for closed-loop post-edit reasoning that uses a Critic agent to verify coherence and step-wise correctness.
Outcome:	Experiments on MQuAKE-2002 and MQuADE-hard show that CARE effectively mitigates error propagation . a minor retrieval error or logical mismatch at an early hop can become a silent failure .

Copied to clipboard

Zhen Zhang, Xinyu Wang, Yong Jiang, Zile Qiao, Zhuo Chen, Guangyu Li, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang

Multi-Objective Forward Reasoning and Multi-Reward Backward Refinement for Product Review Summarization (2024.lrec-main)

Challenge:	Retrieval-augmented generation (RAG) is employed to tackle these challenges . a Knowledge Boundary Model (KBM) is used to express the known/unknown of a given question .
Approach:	They propose a Knowledge Boundary Model to express the known/unknown of a given question . they find that not all questions need to trigger RAG to improve performance .
Outcome:	The proposed model reduces time and computational costs by retrieving parts of unknown knowledge . the proposed model can express the known/unknown of a given question and determine whether a RAG needs to be triggered .

Copied to clipboard

Libo Sun, Siyuan Wang, Meng Han, Ruofei Lai, Xinyu Zhang, Xuanjing Huang, Zhongyu Wei

AfriCLIRMatrix: Enabling Cross-Lingual Information Retrieval for African Languages (2022.emnlp-main)

Challenge:	Product review summarization aims to generate a concise summary based on product reviews . factual accuracy, aspect comprehensiveness, and content relevance are challenges .
Approach:	They propose an FB-Thinker framework to improve product review summarization ability . they propose two Chinese product review summary datasets for instruction-tuning and evaluation .
Outcome:	The proposed framework improves product review summarization with forward reasoning and backward refinement.

Copied to clipboard

Odunayo Ogundepo, Xinyu Zhang, Shuo Sun, Kevin Duh, Jimmy Lin

Multilinguality

Challenge:	Existing datasets for cross-lingual information retrieval are limited in many languages, especially those spoken in Africa.
Approach:	They propose to build a test collection for cross-lingual information retrieval in 15 diverse African languages.
Outcome:	AfriCLIRMatrix contains 6 million queries in English and 23 million relevance judgments automatically mined from Wikipedia inter-language links, covering many more African languages than any existing information retrieval test collection.

Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization (2024.findings-emnlp)

Copied to clipboard

Yixin Ji, Yang Xiang, Juntao Li, Qingrong Xia, Zi Ye, Xinyu Duan, Zhefeng Wang, Kehai Chen, Min Zhang

Have LLMs Reopened the Pandora’s Box of AI-Generated Fake News? (2025.naacl-long)

Challenge:	Large language models require a balance between efficiency and performance.
Approach:	They propose a low-rank compression technique that reduces non-essential parameters by decomposing weight matrices into products of two low-ranked matrici.
Outcome:	The proposed method outperforms existing pruning and low-rank compression techniques in maintaining model performance at the same compression ratio.

Copied to clipboard

Xinyu Wang, Wenbo Zhang, Sai Koneru, Hangzhi Guo, Bonam Mingole, S. Shyam Sundar, Sarah Rajtmajer, Amulya Yadav

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

Challenge:	Large language models (LLMs) are increasingly being used by fake news creators to generate deceptive and persuasive content at scale.
Approach:	They propose to use large language models to generate fake news at scale and to assess the ability of human annotators and AI models to detect it.
Outcome:	The results show that LLMs are 68% more effective at detecting real news than humans, compared to humans and AI models for fake news detection.

Copied to clipboard

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

CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task (2025.findings-emnlp)

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

Copied to clipboard

Haosi Mo, Xinyu Ma, Xuebo Liu, Derek F. Wong, Yu Li, Jie Liu, Min Zhang

Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective (2022.emnlp-main)

Challenge:	Existing benchmarks focus on isolated abilities, lacking a holistic framework for assessing LLM capabilities.
Approach:	They propose a Cognition-Domain-Task framework which measures a model’s capabilities across three dimensions.
Outcome:	The proposed framework improves performance on dataset evaluation and data selection, while achieving higher scores on general and specific benchmarks.

Copied to clipboard

Ping Yang, Junjie Wang, Ruyi Gan, Xinyu Zhu, Lin Zhang, Ziwei Wu, Xinyu Gao, Jiaxing Zhang, Tetsuya Sakai

Low-Resource NLP

Challenge:	Existing approaches to zero-shot learning are format-agnostic and can address new learning tasks without additional training.
Approach:	They propose a new paradigm for zero-shot learning that is format agnostic and compatible with any format and applicable to a list of language tasks.
Outcome:	The proposed model shows state-of-the-art performance on several benchmarks and produces satisfactory results on tasks such as text classification and commonsense reasoning.

IAG: Induction-Augmented Generation Framework for Answering Reasoning Questions (2023.emnlp-main)

Copied to clipboard

Zhebin Zhang, Xinyu Zhang, Yuanhang Ren, Saijiang Shi, Meng Han, Yongkang Wu, Ruofei Lai, Zhao Cao

Decoding-Unlearning: Fact Forgetting via Entropy-Guided Inference (2026.acl-long)

Challenge:	Existing approaches to QA using retrieval-augmented knowledge are limited by limited coverage and noisy information.
Approach:	They propose an induction-augmented generation framework that utilizes inductive knowledge along with retrieved documents for implicit reasoning.
Outcome:	The proposed framework outperforms RAG and ChatGPT on two Open-Domain QA tasks.

Copied to clipboard

Jingwen Pu, Mingjun Shi, Xinrui Ren, Yizhe Wang, Xinyu Zhang, Zhaokun Wang, Kun She

ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs (2025.acl-long)

Challenge:	Existing methods for large-scale modeling memorize sensitive information . however, they are limited in real-world scenarios and require updating parameters .
Approach:	They propose a training-free, plug-and-play inference-time unlearning strategy that uses a probe to detect queries involving forgettable concepts and applies entropy-guided decoding to suppress target knowledge.
Outcome:	Experiments on MUSE, RWKU, and WMDP datasets show that SEGUE outperforms existing methods.

Copied to clipboard

Zhenliang Zhang, Xinyu Hu, Huixuan Zhang, Junzhe Zhang, Xiaojun Wan

CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis (2025.findings-emnlp)

Challenge:	Existing methods for hallucination detection rely on static and isolated representations, overlooking their dynamic evolution across layers.
Approach:	They propose a method which captures the cross-layer evolution of hidden states and propose 'ICR Probe' which capture the evolution of the hidden states.
Outcome:	The proposed method achieves superior performance with significantly fewer parameters and ablation studies offer deeper insights into the underlying mechanism of the method, improving its interpretability.

Copied to clipboard

Xinyu Zhang, Pei Zhang, Shuang Luo, Jialong Tang, Yu Wan, Baosong Yang, Fei Huang

Training Language Model to Critique for Better Refinement (2025.findings-acl)

Challenge:	Cultural competence is defined as the ability to understand and adapt to multicultural contexts.
Approach:	They propose a framework that uses a hierarchical multilingual taxonomy and a Retrieval-Augmented Generation to synthesize culturally relevant question-answer pairs.
Outcome:	The proposed framework contains a hierarchical multilingual taxonomy covering 12 primary and 130 secondary topics and a Retrieval-Augmented Generation (RAG)-based methodology leveraging factual knowledge to synthesize culturally relevant question-answer pairs.

Copied to clipboard

Tianshu Yu, Chao Xiang, Mingchuan Yang, Pei Ke, Bosi Wen, Cunxiang Wang, Jiale Cheng, Li Zhang, Xinyu Mu, Chuxiong Sun, Minlie Huang

Glyph: Scaling Context Windows via Visual-Text Compression (2026.acl-long)

Challenge:	Large language models (LLMs) have remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks.
Approach:	They propose a framework to train critic models using refinement signals to generate feedback loops where critiques guide the model in refining its responses.
Outcome:	The proposed framework outperforms traditional methods and open-source models in terms of critique quality and refinement outcomes.

Copied to clipboard

Jiale Cheng, Yusen Liu, Xinyu Zhang, Yulin Fei, Wenyi Hong, Ruiliang Lyu, Weihan Wang, Zhe Su, Xiaotao Gu, Xiao Liu, Yushi Bai, Jie Tang, Hongning Wang, Minlie Huang

Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs (2025.emnlp-main)

Challenge:	Large language models (LLMs) traditionally represent text as sequences of discrete tokens . a long-context scaling problem requires processing more tokens more efficiently .
Approach:	They propose a framework that renders long texts into compact visual pages and processes them with a vision-language model.
Outcome:	The proposed framework renders long texts into compact visual pages and processes them with a vision-language model.

Copied to clipboard

Dingkun Zhang, Shuhan Qi, Xinyu Xiao, Kehai Chen, Xuan Wang

Diagram-Driven Course Questions Generation (2025.emnlp-main)

Challenge:	Recent advances in Multimodal Large Language Models (MLLMs) have enhanced their versatility as they integrate a growing number of modalities.
Approach:	They propose a simple MCL paradigm that addresses forgetting and misalignment . they propose 'MErge then ReAlign' to extend existing models to more modalities .
Outcome:	The proposed paradigm is easy to deploy and highly reusable in the MLLM community.

Copied to clipboard

Xinyu Zhang, Lingling Zhang, Yanrui Wu, Muye Huang, Wenjun Wu, Bo Li, Shaowei Wang, Basura Fernando, Jun Liu

Visual Data in NLP

Challenge:	Visual Question Generation (VQG) research focuses on natural images while neglecting diagrams, a critical component of educational materials.
Approach:	They propose a diagram-driven course questions generation task to generate diagram-relevant questions for specific courses.
Outcome:	The proposed framework outperforms existing models on DiagramQG while maintaining strong generalizability across natural image datasets.

Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification (2025.emnlp-main)

Copied to clipboard

Jikai Wang, Zhenxu Tian, Juntao Li, Qingrong Xia, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Min Zhang

Challenge:	Existing methods to accelerate autoregressive generation of large language models require training costs.
Approach:	They propose a training-free alignment-augmented speculative decoding algorithm . it leverages the output distribution obtained in the prefilling phase to provide more aligned draft candidates .
Outcome:	The proposed method increases the average generation score by 3.3 points for the LLaMA3 model.

Improving Knowledge Graph Completion with Structure-Aware Supervised Contrastive Learning (2024.emnlp-main)

Copied to clipboard

Jiashi Lin, Lifang Wang, Xinyu Lu, Zhongtian Hu, Wei Zhang, Wenxuan Lu

PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving (2026.findings-acl)

Challenge:	Existing contrastive methods focus on individual triples, overlooking the broader structural connectivities and topologies of KGs.
Approach:	They propose a new contrastive learning framework that incorporates four tasks specifically tailored to KG data: Vertex-level CL, Neighbor-level Cl, Path-levelCL, and Relation composition level CL.
Outcome:	The proposed framework achieves SOTA performance under standard supervised and low-resource settings.

Copied to clipboard

Yuxuan Dong, Xinyu Zhang, Lingling Zhang, Han Lai, Pengyu Li, Bifan Wei, Yaqiang Wu, Jun Liu

Subjective Topic meets LLMs: Unleashing Comprehensive, Reflective and Creative Thinking through the Negation of Negation (2024.emnlp-main)

Challenge:	Existing Large Language Models (LLMs) struggle with physics problem solving due to difficulties in decoding implicit constraints and maintaining physical consistency.
Approach:	They propose a Generative PRM that treats evaluation as a generative task . it produces fine-grained diagnoses comprising critiques, final judgments, and specific error types .
Outcome:	The proposed model improves performance across seven benchmarks in Best-of-N and critique refinement strategies.

Copied to clipboard

Fangrui Lv, Kaixiong Gong, Jian Liang, Xinyu Pang, Changshui Zhang

A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning (2024.naacl-long)

Challenge:	Large language models (LLMs) exhibit powerful reasoning capacity, but their evaluation still lacks comprehensiveness.
Approach:	They propose a framework grounded in the principle of the Negation of Negation (NeoN) to unleash the potential comprehensive, reflective, and creative thinking abilities of LLMs.
Outcome:	The proposed framework unleashes the potential comprehensive, reflective, and creative thinking abilities of large language models.

Copied to clipboard

Ruixin Hong, Hongming Zhang, Xinyu Pang, Dong Yu, Changshui Zhang

MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages (2023.tacl-1)

Challenge:	Existing models of large language models struggle with complex logical reasoning problems.
Approach:	They propose to use large language models to identify their own errors to improve their models' performance.
Outcome:	The proposed models can identify logical fallacies accurately and improve by themselves.

Copied to clipboard

Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin

Multilinguality

Challenge:	MIRACL is a multilingual dataset for ad hoc retrieval across 18 languages that collectively encompass over three billion native speakers around the world.
Approach:	They have gathered over 726k high-quality relevance judgments for 78k queries over Wikipedia in these languages, where all annotations have been performed by native speakers hired by their team.
Outcome:	MIRACL covers languages that are typologically close as well as distant from 10 language families and 13 sub-families, associated with varying amounts of publicly available resources.

GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models (2025.findings-acl)

Copied to clipboard

Mufan Qiu, Xinyu Hu, Fengwei Zhan, Sukwon Yun, Jie Peng, Ruichen Zhang, Bhavya Kailkhura, Jiekun Yang, Tianlong Chen

Structured Data in NLP

Challenge:	Foundation models for single-cell RNA sequencing ignore biological prior knowledge encoded in gene regulatory relationships and fail to leverage multi-omics signals.
Approach:	They propose a framework that integrates multi-scale gene regulatory networks into RNA foundation model training.
Outcome:	The proposed framework improves on state-of-the-art models on three downstream tasks . it integrates multi-scale gene regulatory networks (GRNs) from multi-omics data into training .

EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios (2026.acl-long)

Copied to clipboard

Bin Xu, Yu Bai, Huashan Sun, Yiguan Lin, Siming Liu, Xinyue Liang, Yaolin Li, Zhuangzhi Dong, Jingren Zhang, Yufan Deng, Xinyu Zou, Yang Gao, Heyan Huang

Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining (2023.emnlp-main)

Challenge:	Existing benchmarks that focus on knowledge-intensive tasks do not reflect diverse educational scenarios.
Approach:	They propose a benchmark that incorporates 9 major scenarios and 4,000 educational contexts.
Outcome:	The proposed model performs comparable to state-of-the-art large models on the test set.

Copied to clipboard

Jingcong Liang, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei

OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure (2025.tacl-1)

Challenge:	Recent studies have discussed its capability to assist language models for various applications.
Approach:	They propose a structure to organize arguments using the Hierarchical Argumentation Graph (Hi-ArG) and propose two approaches to exploit Hi-AarG, including a text-graph multi-modal model GreaseArR and a framework augmented with graph information.
Outcome:	The proposed structure supersedes existing language models on two argumentation tasks while incorporating graph information during further training improves vanilla language models.

Copied to clipboard

Jikai Wang, Yi Su, Juntao Li, Qingrong Xia, Zi Ye, Xinyu Duan, Zhefeng Wang, Min Zhang

Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning (2025.acl-long)

Challenge:	Autoregressive language models generate one token in one step, limiting inference efficiency . Existing methods do not adapt to different situations to maximize acceptance length . speculative decoding has shown great potential for lossless acceleration .
Approach:	They propose an algorithm to construct adaptive and scalable draft trees for autoregressive language models.
Outcome:	Experimental results show that OPT-Tree outperforms existing draft trees and achieves speed-up ratio of up to 3.2 compared with autoregressive decoding.

Copied to clipboard

Yongxin Xu, Ruizhe Zhang, Xinke Jiang, Yujie Feng, Yuzhen Xiao, Xinyu Ma, Runchuan Zhu, Xu Chu, Junfeng Zhao, Yasha Wang

Local Interpretation of Transformer Based on Linear Decomposition (2023.acl-long)

Challenge:	Existing methods for integrating internal and external knowledge lack effective control mechanisms for generating hallucinations and dealing with outdated knowledge.
Approach:	They propose a framework that decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness.
Outcome:	The proposed framework decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness.

Copied to clipboard

Sen Yang, Shujian Huang, Wei Zou, Jianbing Zhang, Xinyu Dai, Jiajun Chen

Explainability & Interpretability in NLP

Challenge:	Existing work on local explanation generation attempts to understand model dynamics on word-level or phraselevel by assigning importance scores on input features.
Approach:	They propose to interpret neural networks by linear decomposition by a Transformer model on a single input and a linear decomposing of the output to generate local explanations.
Outcome:	The proposed method achieves competitive performance in sentiment classification and machine translation, and fidelity of explanation.

Spacerini: Plug-and-play Search Engines with Pyserini and Hugging Face (2023.emnlp-demo)

Copied to clipboard

Christopher Akiki, Odunayo Ogundepo, Aleksandra Piktus, Xinyu Zhang, Akintunde Oladipo, Jimmy Lin, Martin Potthast

Evaluating Embedding APIs for Information Retrieval (2023.acl-industry)

Challenge:	a toolkit for reproducible information retrieval research is available for free.
Approach:	They present a tool that integrates Pyserini and Hugging Face to enable the seamless construction and deployment of interactive search engines.
Outcome:	The proposed tool makes state-of-the-art retrieval models more accessible to non-IR practitioners while minimizing deployment effort.

Copied to clipboard

Ehsan Kamalloo, Xinyu Zhang, Odunayo Ogundepo, Nandan Thakur, David Alfonso-hermelo, Mehdi Rezagholizadeh, Jimmy Lin

Generalized Supervised Attention for Text Generation (2021.findings-acl)

Challenge:	a growing number of language models are limiting their access to the community . we evaluate existing APIs for domain generalization and multilingual retrieval .
Approach:	They evaluate semantic embedding APIs in retrieval scenarios to assess their capabilities . they use BEIR and MIRACL to re-rank BM25 results using the APIs .
Outcome:	The proposed model is based on semantic embedding APIs that build vector representations of a given text.

Copied to clipboard

Yixian Liu, Liwen Zhang, Xinyu Zhang, Yong Jiang, Yue Zhang, Kewei Tu

Assimilation and Accommodation: Task-Adaptive Hierarchical Abstraction for Solving Web Tasks (2025.findings-acl)

Challenge:	Existing supervised attention methods that use human knowledge to learn better alignments are costly or infeasible.
Approach:	They propose a generalized supervised attention method based on quasi alignments that are easier to obtain than ideal alignments.
Outcome:	The proposed framework improves generation performance and is robust against errors in attention supervision.

Copied to clipboard

Xinyu Pang, Ruixin Hong, Hongming Zhang, Changshui Zhang

Revisit Self-Debugging with Self-Generated Tests for Code Generation (2025.acl-long)

Challenge:	Existing methods focus on summarizing workflows, i.e., common sub-routines, which introduce excessive low-level details that distract models.
Approach:	They propose a framework that derives task-adaptive hierarchical abstraction from experience to enhance web task reasoning.
Outcome:	The proposed framework improves performance with competitive cost-efficiency on Mind2web and Webarena.

Copied to clipboard

Xiancai Chen, Zhengwei Tao, Kechi Zhang, Changzhi Zhou, Xinyu Zhang, Wanli Gu, Yuanpeng He, Mengdi Zhang, Xunliang Cai, Haiyan Zhao, Zhi Jin

Programming Languages in NLP

Challenge:	Large language models (LLMs) have made significant advances in code generation, but they still face challenges when tackling complex programming tasks beyond their basic capabilities.
Approach:	They propose to integrate self-generated tests into the code generation process . they propose to use post-execution and in-exection self-debugging to mitigate test bias .
Outcome:	The proposed method improves the performance of large language models in code generation tasks by leveraging execution feedback from tests.

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Zhenyu Liu, Yunxin li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang

Beyond the Surface: Measuring Self-Preference in LLM Judgments (2025.emnlp-main)

Challenge:	Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation.
Approach:	They propose a unified speech and music generation model built upon a novel framework . they propose specialized MoE architectures and curated training strategies to tackle data imbalances .
Outcome:	The proposed model achieves state-of-the-art performance on major speech and music generation benchmarks.

Copied to clipboard

Zhi-Yuan Chen, Hao Wang, Xinyu Zhang, Enrui Hu, Yankai Lin

P3: Prompts Promote Prompting (2025.findings-acl)

Challenge:	Existing methods measure self-preference bias by comparing the scores a judge model assigns to its own responses with those assigned to other models.
Approach:	They propose to use gold judgments as proxies for the actual quality of responses . they propose to measure self-preference bias as the difference between the judge model's own and other models' scores .
Outcome:	The proposed method can assess self-preference bias across large language models . it uses gold judgments as proxies for the ground truth scores of the judge model .

Copied to clipboard

Xinyu Zhang, Yuanquan Hu, Fangchao Liu, Zhicheng Dou

Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference (2025.emnlp-main)

Challenge:	Recent advances in prompt optimization have shown effectiveness of using multiple components to optimize models . however, such unilateral approaches often yield suboptimal results due to interdependent nature of these components.
Approach:	They propose a self-improvement framework that optimizes both system and user prompts . they use offline optimized prompts to promote online prompt optimization .
Outcome:	The proposed framework improves performance on general and reasoning tasks.

Copied to clipboard

Zhuo Chen, Xinyu Wang, Yong Jiang, Zhen Zhang, Xinyu Geng, Pengjun Xie, Fei Huang, Kewei Tu

Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding (2022.coling-1)

Challenge:	Existing methods to detect the knowledge boundary of Vision Large Language Models (VLLMs) are expensive and require indiscriminate retrieval to address questions that require real-time information or are knowledge-intensive.
Approach:	They propose a method that fine-tunes a VLLM on an automatically constructed dataset for boundary identification.
Outcome:	The proposed method reduces indiscriminate retrieval while maintaining or improving the performance of a VLLM on an automatically constructed dataset.

Copied to clipboard

Zhaoye Fei, Yu Tian, Yongkang Wu, Xinyu Zhang, Yutao Zhu, Zheng Liu, Jiawen Wu, Dejiang Kong, Ruofei Lai, Zhao Cao, Zhicheng Dou, Xipeng Qiu

HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy (2026.acl-industry)

Challenge:	Existing methods to learn downstream tasks by stitches skill block lack rationality and interpretation.
Approach:	They propose a hierarchical framework with a coarse-to-fine paradigm for generalized text representations from the large-scale corpus.
Outcome:	The proposed model learns basic language properties from all tasks and boosts performance on relevant tasks.

Copied to clipboard

Fan Xu, Xinyu Hu, Zhenghan Yu, Li Lin, Xu Zhang, Yang Zhang, Wei Zhou, Jinjie Gu, Xiaojun Wan

Addressing Linguistic Bias through a Contrastive Analysis of Academic Writing in the NLP Domain (2023.emnlp-main)

Challenge:	relying on large language models for information has raised concerns about reliability and accuracy of outputs.
Approach:	They propose a hallucination taxonomy with 11 categories for various NLG tasks and propose HAllucination Detection models which integrate hallucinism detection, span-level identification, and correction into a single inference process.
Outcome:	The proposed models outperform baselines on HaluEval, FactCHD, and FaithBench, confirming their robustness and versatility.

Copied to clipboard

Robert Ridley, Zhen Wu, Jianbing Zhang, Shujian Huang, Xinyu Dai

AutoAlign: Get Your LLM Aligned with Minimal Annotations (2025.acl-demo)

Challenge:	a reviewer’s opinion of the nativeness of expression in an academic paper affects the likelihood of it being accepted for publication.
Approach:	They conduct a statistical analysis of paper abstracts from the natural language processing domain to identify how authors from different linguistic backgrounds differ in the lexical, morphological, syntactic and cohesive aspects of their writing.
Outcome:	The results suggest that there is potential for linguistic bias in the domain of natural language processing.

Copied to clipboard

Xinyu Lu, Dong Xu, Chunkang Zhang, Xinyan Guan, Junxiang Wang, Qingyu Zhang, Pengbo Wang, Yingzhi Mao, Hao Xiang, Xueru Wen, Zichao Li, Yaojie Lu, Hongyu Lin, Le Sun, Xianpei Han

STRICT: Stress-Test of Rendering Image Containing Text (2025.emnlp-main)

Challenge:	Automated Alignment (ALM) is a set of algorithms designed to align Large Language Models (LLMs) with human intentions and values while minimizing manual intervention.
Approach:	They propose an open-source toolkit that integrates mainstream automated algorithms through a consistent interface and an accessible workflow supporting one-click execution for prompt synthesis and automatic alignment signal construction.
Outcome:	The proposed framework enables easy reproduction of existing results through extensive benchmarks and facilitates the development of novel approaches via modular components.

Copied to clipboard

Tianyu Zhang, Xinyu Wang, Lu Li, Zhenghan Tai, Jijun Chi, Jingrui Tian, Hailin He, Suyuchen Wang

Probing Cross-modal Semantics Alignment Capability from the Textual Perspective (2022.findings-emnlp)

Challenge:	Despite the advances in diffusion models, the generation of coherent text remains a major bottleneck.
Approach:	They propose a benchmark to test the ability of diffusion models to render coherent text in images.
Outcome:	The proposed model fails to generate coherent and legible text in images despite its iterative nature . the model fails in both the maximum length of readable text and correctness and legibility of the generated text .

Copied to clipboard

Zheng Ma, Shi Zong, Mianzhi Pan, Jianbing Zhang, Shujian Huang, Xinyu Dai, Jiajun Chen

Multi-level Relevance Document Identifier Learning for Generative Retrieval (2025.acl-long)

Challenge:	In recent years, vision and language pre-training (VLP) models have advanced the state-of-the-art results in a variety of cross-modal downstream tasks.
Approach:	They propose a new probing method that is based on image captioning to first empirically study the cross-modal semantics alignment of VLP models.
Outcome:	The proposed method analyzes captions generated by five popular VLP models to reveal how well they align with visual words and how well these align with images.

Copied to clipboard

Fuwei Zhang, Xiaoyu Liu, Xinyu Jia, Yingfei Zhang, Shuai Zhang, Xiang Li, Fuzhen Zhuang, Wei Lin, Zhao Zhang

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation (2024.emnlp-demo)

Challenge:	Existing methods generate DocIDs based on textual content, which may result in weak semantic connections for similar documents due to variations in expression.
Approach:	They propose a new retrieval paradigm that generates unique document identifiers . they propose to use queries as a bridge to connect documents with varying relevance levels .
Outcome:	The proposed approach outperforms existing methods on multilingual e-commerce search datasets.

Copied to clipboard

Xuanwang Zhang, Yun-Ze Song, Yidong Wang, Shuyun Tang, Xinfeng Li, Zhengran Zeng, Zhen Wu, Wei Ye, Wenyuan Xu, Yue Zhang, Xinyu Dai, Shikun Zhang, Qingsong Wen

Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner (2025.emnlp-main)

Challenge:	Existing research on Retrieval Augmented Generation (RAG) does not address the problem of hallucinations and real-time updating of knowledge.
Approach:	They propose a modular open-source library to equip LLMs with external knowledge.
Outcome:	The proposed approach reduces the need for expensive open-source tools and lacks fair comparisons between novel RAG algorithms.

Copied to clipboard

Bolian Li, Yanran Wu, Xinyu Luo, Ruqi Zhang

Green & Sustainable NLP

Challenge:	Recent research has focused on test-time alignment, where additional compute is allocated during inference to enhance LLM safety and reasoning capabilities.
Approach:	They propose a reward-shifted speculative sampling algorithm that aligns a draft model with human preferences while the target model remains unchanged.
Outcome:	The proposed algorithm achieves superior gold reward scores at a significantly reduced inference cost in test-time weak-to-strong alignment experiments.

3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset (2024.lrec-main)

Copied to clipboard

Xinyu Ma, Xuebo Liu, Derek F. Wong, Jun Rao, Bei Li, Liang Ding, Lidia S. Chao, Dacheng Tao, Min Zhang

Machine Translation

Challenge:	Existing studies have shown that visual information in existing MMT datasets is insufficient, causing models to disregard it and overestimate their capabilities.
Approach:	They propose to use 3AM to create an ambiguity-aware multimodal machine translation dataset.
Outcome:	The proposed dataset includes more ambiguity and a greater variety of captions and images than other MMT datasets.

MemTR: Enhancing Tool-Calling Reliability via Uncertainty-Triggered FFN-Space Retracing (2026.findings-acl)

Copied to clipboard

Hongtao Duan, Lu Jiang, Minying Zhang, Xiaobing Zhu, Tianpeng Bu, Hao Jiang, Xinyu Wei, Lulu hu

BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026.acl-long)

Challenge:	Existing tool-calling methods rely on costly tool-use training data or only constrain syntax, leaving tool selection and argument value errors largely unsolved.
Approach:	They propose a method that decodes tool evidence from the tool library and mixes it into the output at the uncertain layer.
Outcome:	The proposed method reduces tool calling failures by 2%–9% with only 1%–2% runtime overhead.

Copied to clipboard

Zijian Chen, Xueguang Ma, Shengyao Zhuang, Ping Nie, Kai Zou, Sahel Sharifymoghaddam, Andrew Liu, Joshua Green, Kshama Patel, Ruoxi Meng, Mingyi Su, Yanxi Li, Haoran Hong, Xinyu Shi, Xuye Liu, Hosna Oyarhoseini, Nandan Thakur, Crystina Zhang, Luyu Gao, Wenhu Chen, Jimmy Lin

Aligning Generative Language Models with Human Values (2022.findings-naacl)

Challenge:	Existing benchmarks for deep search agents rely on blackbox web search APIs . dynamic and opaque web APIs hinder reproducibility and fair comparisons - authors .
Approach:	They propose a benchmark that employs a fixed corpus for controlled retrieval for deep search agents.
Outcome:	The new benchmark shows that agents that combine large language models with retrieval tools excel at complex, reasoning-intensive queries.

Copied to clipboard

Ruibo Liu, Ge Zhang, Xinyu Feng, Soroush Vosoughi

Logic-Regularized Verifier Elicits Reasoning from LLMs (2025.acl-long)

Challenge:	Existing methods for learning human values do not consider contextual and abstract nature of human values.
Approach:	They propose a reinforcement learning based method that embeds human values judgements into each step of language generation.
Outcome:	The proposed method improves on human values judgements and shows higher alignment performance.

Copied to clipboard

Xinyu Wang, Changzhi Sun, Lian Cheng, Yuanbin Wu, Dell Zhang, Xiaoling Wang, Xuelong Li

A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues (2023.acl-long)

Challenge:	Typical verifiers require resource-intensive supervised dataset construction, which is costly and faces limitations in data diversity.
Approach:	They propose an unsupervised verifier regularized by logical rules that uses internal activations and logical constraints on multiple reasoning paths.
Outcome:	Experiments on 10 datasets show that the proposed verifier outperforms baselines and is comparable to the supervised verifier.

Copied to clipboard

Yunxin Li, Baotian Hu, Chen Xinyu, Yuxin Ding, Lin Ma, Min Zhang

Redundancy Principles for MLLMs Benchmarks (2025.acl-long)

Challenge:	Existing methods for conditional inference on joint textual and visual clues lack multimodal context reasoning capability.
Approach:	They propose a multi-modal context reasoning approach that embeds textual semantics and objective image information into the pretrained language model to perform context reasoning.
Outcome:	The proposed approach improves on two data sets and shows 4.8% gain on the PMR.

Copied to clipboard

Zicheng Zhang, Xiangyu Zhao, Xinyu Fang, Chunyi Li, Xiaohong Liu, Xiongkuo Min, Haodong Duan, Kai Chen, Guangtao Zhai

Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix (2023.emnlp-main)

Challenge:	Rapid growth of Multi-modality Large Language Models has led to significant redundancy among benchmarks.
Approach:	They propose a framework to improve MLLM benchmark design by identifying redundancy at three levels: dimension, instance, and cross-benchmark redundancies.
Outcome:	The proposed framework streamlines evaluations and enhances reliability.

Copied to clipboard

Xinyu Ma, Xuebo Liu, Min Zhang

Multilinguality

Challenge:	Existing methods to cluster languages based on ancestral families can yield suboptimal results due to variations in the datasets employed during the model’s training phase.
Approach:	They propose a method that leverages the fisher information matrix to cluster language families anchored on the multilingual translation model's characteristics.
Outcome:	The proposed method improves performance over conventional language families in adapting a multilingual translation model to unfamiliar language pairs.

DAMON: A Dialogue-Aware MCTS Framework for Jailbreaking Large Language Models (2025.emnlp-main)

Copied to clipboard

Xu Zhang, Xunjian Yin, Dinghao Jing, Huixuan Zhang, Xinyu Hu, Xiaojun Wan

Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM (2024.findings-acl)

Challenge:	Existing methods for multi-turn attacks mainly utilize a predefined dialogue pattern, limiting their effectiveness in realistic situations.
Approach:	They propose a multi-turn jailbreak attack method that leverages Monte Carlo Tree Search to explore multi-turned conversational spaces and identifies sub-instruction sequences that induce harmful responses.
Outcome:	The proposed method can induce undesired behaviors across five LLMs and three datasets.

Copied to clipboard

Jingcong Liang, Rong Ye, Meng Han, Ruofei Lai, Xinyu Zhang, Xuanjing Huang, Zhongyu Wei

Challenge:	Recent studies have focused on short dialogues, but mainly on short debates.
Approach:	They propose to use Large Language Models to construct an automated debate judge to evaluate multi-turn debates.
Outcome:	The proposed system improves on the PanelBench benchmark, which compares its performance to actual debate outcomes.

Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering (2025.acl-long)

Copied to clipboard

Xinyu Tang, Xiaolei Wang, Zhihao Lv, Yingqian Min, Xin Zhao, Binbin Hu, Ziqi Liu, Zhiqiang Zhang

Enhancing LLM-Based Social Bot via an Adversarial Learning Framework (2025.emnlp-main)

Challenge:	Existing work finds that long CoT reasoning can be efficiently elicited by tuning on only a few examples and can easily transfer to other tasks.
Approach:	They propose a representation engineering method to unleash the general long CoT reasoning capabilities of LLMs.
Outcome:	The proposed method is effective in in-domain and cross-domain scenarios.

Copied to clipboard

Fanqi Kong, Xiaoyuan Zhang, Xinyu Chen, Yaodong Yang, Song-Chun Zhu, Xue Feng

Robustness in NLP

Challenge:	Social media platforms provide an ideal testbed for large language models that exhibit human-like behavior.
Approach:	They propose an LLM-based social **Bot that enhances human-like generative capabilities through an adversarial learning framework.
Outcome:	The proposed framework generates human-like content aligned with diverse user profiles . it exhibits strong social responsiveness, more accurately modeling opinion dynamics .

Solving Math Word Problems via Cooperative Reasoning induced Language Models (2023.acl-long)

Copied to clipboard

Xinyu Zhu, Junjie Wang, Lin Zhang, Yuxiang Zhang, Yongfeng Huang, Ruyi Gan, Jiaxing Zhang, Yujiu Yang

Dually Self-Improved Counterfactual Data Augmentation Using Large Language Model (2025.acl-long)

Challenge:	Large-scale pre-trained language models (PLMs) can be used to solve math word problems, but they lack fast adaptivity as humans.
Approach:	They propose a cooperative reasoning-induced PLM for solving the math word problem . they use system 1 as the generator and system 2 as the verifier to generate reasoning paths .
Outcome:	The proposed model improves on several mathematical reasoning datasets and achieves 9.6% improvement over baselines.

Copied to clipboard

Luhao Zhang, Xinyu Zhang, Linmei Hu, Dandan Song, Liqiang Nie

Physics Reasoner: Knowledge-Augmented Reasoning for Solving Physics Problems with Large Language Models (2025.coling-main)

Challenge:	Existing approaches to generate counterfactual data augmentation are limited due to imbalance and biases in real-world training data.
Approach:	They propose a self-improved method for generating high-quality counterfacts using large language models.
Outcome:	The proposed method generates high-quality counterfacts on the natural language inference task using lightweight and task-specific LLMs.

Copied to clipboard

Xinyu Pang, Ruixin Hong, Zhanke Zhou, Fangrui Lv, Xinwei Yang, Zhilong Liang, Bo Han, Changshui Zhang

Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving (2026.acl-long)

Challenge:	Existing large language models (LLMs) fail due to lack of knowledge or incorrect knowledge application.
Approach:	They propose a knowledge-augmented framework that constructs a formula set to provide explicit physics knowledge and utilizes checklists to guide effective knowledge application.
Outcome:	The proposed framework achieves state-of-the-art performance on SciBench with an average accuracy improvement of 5.8%.

Copied to clipboard

Xinyu Zhang, Yuchen Wan, Boxuan Zhang, Zesheng Yang, Lingling Zhang, Bifan Wei, Jun Liu

Text Clustering

Challenge:	Large Language Models (LLMs) struggle with structural ambiguity in optimization problems, where a single problem admits multiple related but conflicting modeling paradigms, hindering effective solution generation.
Approach:	They propose to use memory to leverage historical solutions in a training-free manner to enhance performance by leveraging generalizable guidance knowledge.
Outcome:	The proposed agent achieves an average performance improvement of 11%-21% over previous agents.

GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing (2025.naacl-long)

Copied to clipboard

Jinhao Duan, Xinyu Zhao, Zhuoxuan Zhang, Eunhye Grace Ko, Lily Boddy, Chenan Wang, Tianhao Li, Alexander Rasgon, Junyuan Hong, Min Kyung Lee, Chenxi Yuan, Qi Long, Ying Ding, Tianlong Chen, Kaidi Xu

Natural Language Interfaces

Challenge:	Large Language Models (LLMs) have demonstrated their effectiveness in human-guided dialogues, but tasks in the real world are more complex and require greater autonomy from LLMs.
Approach:	They propose to characterize LLM-guided conversation into three fundamental components: Goal Navigation, Context Management, Empathetic Engagement and implement an interviewing environment for the evaluation of LLMs.
Outcome:	The proposed LLM outperforms baseline LLMs in interviewing quality and autobiography generation quality.

VideoVista-CulturalLingo: 360° Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension (2025.acl-long)

Copied to clipboard

Xinyu Chen, Yunxin Li, Haoyuan Shi, Baotian Hu, Wenhan Luo, Yaowei Wang, Min Zhang

Visual Data in NLP

Challenge:	Existing video evaluation benchmarks focus on a single language, typically English, and feature videos rooted in Western cultural contexts.
Approach:	They propose a video evaluation benchmark designed to bridge cultural, linguistic, and domain divide in video comprehension.
Outcome:	The proposed video evaluation benchmark bridges cultural, linguistic, and domain divides . existing benchmarks only feature videos from YouTube, Shutterstock, or established video datasets based on cultural diversity .

GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration (2023.acl-demo)

Copied to clipboard

Aleksandra Piktus, Odunayo Ogundepo, Christopher Akiki, Akintunde Oladipo, Xinyu Zhang, Hailey Schoelkopf, Stella Biderman, Martin Potthast, Jimmy Lin

RaFe: Ranking Feedback Improves Query Rewriting for RAG (2024.findings-emnlp)

Challenge:	Using the mature and well-tested methods from the domain of Information Retrieval (IR) we propose to integrate Pyserini with Hugging Face to provide qualitative analysis tools for NLP researchers.
Approach:	They propose to integrate Pyserini with Hugging Face to provide qualitative analysis tools for NLP researchers.
Outcome:	The proposed tools can be integrated with the Hugging Face ecosystem of open-source AI libraries and artifacts.

Copied to clipboard

Shengyu Mao, Yong Jiang, Boli Chen, Xiao Li, Peng Wang, Xinyu Wang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

NavA3: Understanding Any Instruction, Navigating Anywhere, Finding Anything (2026.acl-long)

Challenge:	Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved to enhance document retrieval by reformulating queries.
Approach:	They propose a framework for training query rewriting models that leverages a reranker framework.
Outcome:	The proposed framework provides ranking feedback aligned well with the rewriting objectives without needing signals from annotations and supports both online and offline training models.

Copied to clipboard

Lingfeng Zhang, Xiaoshuai Hao, Yingbo Tang, Haoxiang Fu, Xinyu Zheng, Pengwei Wang, Zhongyuan Wang, Wenbo Ding, Shanghang Zhang

Bi-Tuning with Collaborative Information for Controllable LLM-based Sequential Recommendation (2025.acl-long)

Challenge:	Existing embodied navigation methods struggle with such tasks due to their limitations in comprehending high-level human instructions and localizing objects with an open vocabulary.
Approach:	They propose a hierarchical framework for long-horizon navigation that integrates human instructions with 3D scene views.
Outcome:	The proposed model achieves SOTA results and can complete long-horizon navigation tasks across different robot embodiments in real-world environments.

Copied to clipboard

Xinyu Zhang, Linmei Hu, Luhao Zhang, Wentao Cheng, Yashen Wang, Ge Shi, Chong Feng, Liqiang Nie

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

Challenge:	Existing approaches to optimize sequential recommendation systems rely on item ID sequences, but they lack collaborative knowledge and limited controllability.
Approach:	They propose a simple bi-tuning framework with collaborative information for controllable Large Language Model-based Sequential Recommendation (Laser) they incorporate learnable virtual tokens at prefix and suffix of input text to adapt LLMs with collaborative knowledge .
Outcome:	The proposed framework outperforms state-of-the-art recommendations on real-world datasets.

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.

ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs (2024.findings-emnlp)

Copied to clipboard

Jingming Zhuo, Songyang Zhang, Xinyu Fang, Haodong Duan, Dahua Lin, Kai Chen

HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing (2024.findings-emnlp)

Challenge:	Recent research has neglected instances-level prompt variations and their implications on subjective evaluations.
Approach:	They propose a framework to evaluate and comprehend prompt sensitivity in large language models.
Outcome:	The proposed framework evaluates and comprehends prompt sensitivity in large language models.

Copied to clipboard

Jing Chen, Xinyu Zhu, Cheng Yang, Chufan Shi, Yadong Xi, Yuxiang Zhang, Junjie Wang, Jiashu Pu, Tian Feng, Yujiu Yang, Rongsheng Zhang

Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)

Challenge:	Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in the realm of literary creation.
Approach:	They propose a framework for unleashing the creativity of large language models (LLMs) they assign LLMs to different roles involved in real-world scenario, they write .
Outcome:	The proposed framework outperforms baselines in terms of coherence, relevance, interestingness and overall quality on automatically generated screenplays.

Copied to clipboard

Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Lan Luo, Ke Zhan, Enrui Hu, Xinyu Zhang, Hao Jiang, Zhao Cao, Fan Yu, Xin Jiang, Qun Liu, Lei Chen

Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking (2022.emnlp-main)

Challenge:	Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance.
Approach:	They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents.
Outcome:	The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain.

Copied to clipboard

Minghan Li, Xinyu Zhang, Ji Xin, Hongyang Zhang, Jimmy Lin

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference (2025.acl-long)

Challenge:	In information retrieval, candidate set pruning is used to speed up two-stage relevance ranking but lacks accurate error control and empirical guarantees.
Approach:	They propose a method that guarantees the test error after pruning is controlled under a user-specified threshold with high probability.
Outcome:	The proposed method reduces the average set size from 1000 to 27, increasing reranking speed by about 37 times while keeping MRR@10 greater than a pre-specified value of 0.38 with about 90% empirical coverage.

Copied to clipboard

Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosongcao Maosongcao, Jiaqi Wang, Weiyun Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Hua Yang, Haodong Duan, Kai Chen