Papers by Zihan Zhang

GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs (2026.acl-long)

Challenge:	Existing discriminative approaches suffer from "confident but wrong" failure mode, blindly adapting to OOD noise leading to error accumulation.
Approach:	They propose a TTA framework that harmonizes the robustness of generative diffusion models with the efficiency of discriminative regression networks via Bayesian Diffusion Distillation (BDD).
Outcome:	The proposed framework reduces MAE from 0.6872 to 0.5673 and boosts binary accuracy by 5.81 percentage points (reaching 57.33%) it also reduces the MAE of the MOSI to SIMS shift and achieves an 11.18-point gain over the baseline.

Copied to clipboard

Weidong Tang, Jierui Li, Yueling Hou, Zihan Mei, Can Zhang, Xinyan Wan, Zhiyuan Liang, Pengfei Zhou, Yang You, Wangbo Zhao

Linguistics & Cognitive NLP

Challenge:	Existing models for general intelligence fail to model how mental states interact and crystallize into group-level outcomes.
Approach:	They propose a multimodal benchmark for group-level Theory of Mind (ToM) to probe nonlinear collective behavior.
Outcome:	The proposed model performs significantly below human levels, exposing blind spots in modeling social structures and nonlinear collective behavior.

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

Copied to clipboard

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

ReportLogic: Evaluating Logical Quality in Deep Research Reports (2026.acl-long)

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

Copied to clipboard

Jujia Zhao, Zhaoxin Huan, Zihan Wang, Xiaolu Zhang, Jun Zhou, Suzan Verberne, Zhaochun Ren

Robustness in NLP

Challenge:	Existing evaluation frameworks that evaluate large language models for Deep Research largely ignore this requirement.
Approach:	They propose a benchmark that quantifies report-level logical quality through a reader-centric lens of auditability.
Outcome:	The proposed model quantifies logical quality through a reader-centric lens of auditability.

Efficient Continue Training of Temporal Language Model with Structural Information (2023.findings-emnlp)

Copied to clipboard

Zhaochen Su, Juntao Li, Zikang Zhang, Zihan Zhou, Min Zhang

From Detection to Understanding: Multi-Turn Reasoning for Video Misinformation Analysis (2026.acl-long)

Challenge:	Existing temporal language models are limited by the superficial temporal information brought by timestamps, which fails to learn the inherent changes of linguistic components.
Approach:	They propose a method that captures syntactically changed tokens and captures the relationship between the time prefix and tokens.
Outcome:	The proposed method outperforms existing temporal language models on two datasets and three tasks.

Copied to clipboard

Zhi Zeng, Jiaying Wu, Minnan Luo, Di Zhang, Yifei Yang, Xiangzheng Kong, Herun Wan, Zihan Ma

Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry (2026.acl-long)

Challenge:	Existing benchmarks focus on binary veracity judgments and do not evaluate process-level justifications for misinformation models.
Approach:	They propose a video misinformation analysis benchmark that assesses reasoning in video misinterpretation.
Outcome:	The proposed framework improves reasoning accuracy and explanation quality compared to existing models . it covers 12 fine-grained deception categories and progresses from perceptual attribution to intent and persuasion analysis.

Copied to clipboard

Han Zhang, Zihan Gu, Zhiyuan Wang, Tianyi Ma, Jiacheng Lu, Xinyan Zhang, Yuhao Wei, Cheng Hua

Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark (2026.acl-long)

Challenge:	Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, but it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns.
Approach:	They propose a benchmark that combines a constructionist Out-of-Sample dataset with reverse understanding probes to evaluate large-scale large-format models.
Outcome:	The proposed model performs well on classical Chinese poetry benchmarks, but a performance gap persists . the model can complete famous couplets and can be used to understand a variety of texts.

Copied to clipboard

Zihan Zhang, Yu Bao, Xiao Ding, Tianyi Jiang, Kai Xiong

Challenge:	Existing benchmarks for EEG2Text have neglected EEG instability, a problem that has confounded inference and sparked debate.
Approach:	They propose to use a 128-channel high-density EEG cap to evaluate EEG2Text models . they find existing benchmarks have neglected EEG instability, a flaw that has confounded inferences and sparked debate .
Outcome:	The proposed benchmarks provide key evidence for teacher-forcing-free decoding of EEG2Text models.

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

Copied to clipboard

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

LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System (2025.emnlp-demos)

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

Yu Chao, Siyu Lin, Xiaorong Wang, Zhu Zhang, Zihan Zhou, Haoyu Wang, Shuo Wang, Jie Zhou, Zhiyuan Liu, Maosong Sun

Challenge:	Generating high-quality long-form survey articles poses significant challenges to AI Agent systems.
Approach:	They propose a hierarchically modular agent system for long-form survey generation . they use atomic models to implement skeleton initialization, digest construction, and skelet refinement . human evaluations demonstrate system surpasses representative baselines .
Outcome:	The proposed system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning.

SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition (2025.acl-long)

Copied to clipboard

Shuangrui Ding, Zihan Liu, Xiaoyi Dong, Pan Zhang, Rui Qian, Junhao Huang, Conghui He, Dahua Lin, Jiaqi Wang

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

Challenge:	Creating lyrics and melodies in symbolic format requires expert knowledge of melody and an advanced understanding of lyrics.
Approach:	They introduce SongComposer, a music-specialized large language model that can create symbolic lyrics and melodies following instructions.
Outcome:	The proposed model outperforms existing models in symbolic song composition tasks.

Copied to clipboard

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

ClusterLLM: Large Language Models as a Guide for Text Clustering (2023.emnlp-main)

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

Copied to clipboard

Yuwei Zhang, Zihan Wang, Jingbo Shang

Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving (2025.findings-emnlp)

Challenge:	Extensive experiments on 14 datasets show that ClusterLLM consistently improves clustering quality, at an average cost of $0.6 per dataset.
Approach:	They propose a text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT.
Outcome:	Extensive experiments on 14 datasets show that ClusterLLM consistently improves clustering quality, at an average cost of $0.6 per dataset.

Copied to clipboard

Shunfeng Zheng, Yudi Zhang, Meng Fang, Zihan Zhang, Zhitan Wu, Mykola Pechenizkiy, Ling Chen

DeepMed: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference (2026.findings-acl)

Challenge:	a new study examines the potential of retrieval-augmented generation (RAG) with foundation models to enhance expert-level reasoning.
Approach:	They introduce PhoPile, a high-quality multimodal dataset specifically designed for Olympiad-level physics.
Outcome:	The proposed model can be used to solve Olympiad-level physics problems.

Copied to clipboard

Zihan Wang, Hao Wang, Shi Feng, Xiaocui Yang, Daling Wang, Yiqun Zhang, Jinghao Lin, Xiaozhong Ji, Haihua Yang

How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances (2023.emnlp-main)

Challenge:	Medical reasoning models are constrained by parametric knowledge and can induce hallucinations and spurious attributions.
Approach:	They propose a model that uses a multi-hop med-search QA synthesis method to apply the DR paradigm in medical contexts.
Outcome:	The proposed model outperforms larger medical reasoning models on medical benchmarks.

Copied to clipboard

Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad, Jun Wang

Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning (2025.acl-long)

Challenge:	Large language models (LLMs) are impressive in solving tasks, but they can quickly be outdated after deployment.
Approach:	They provide a review of recent advances in aligning deployed large language models with the ever-changing world knowledge.
Outcome:	The proposed models can be used to perform various tasks directly through in-context learning or for further fine-tuning for domain-specific uses.

Copied to clipboard

Zhu Xu, Zhiqiang Zhao, Zihan Zhang, Yuchi Liu, Quanwei Shen, Fei Liu, Yu Kuang, Jian He, Conglin Liu

Challenge:	Large language models (LLMs) use tokenization methods but often obscure internal character structures within tokens.
Approach:	They propose a method that improves models’ ability to capture character positions within tokens by training them on reverse character prediction tasks using the tokenizer’s vocabulary.
Outcome:	Experiments show that the proposed method improves position prediction accuracy in large language models, enabling more precise identification of target characters in original text.

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods? (2026.findings-acl)

Copied to clipboard

Zihan Chen, Yiming Zhang, Hengguang Zhou, Zenghui Ding, Yining Sun, Cho-Jui Hsieh

Challenge:	Existing benchmarks for reinforcement learning for large language models do not accurately assess generalization.
Approach:	They propose three core principles for designing more faithful benchmarks: sufficient difficulty, balanced evaluation, and distributional robustness.
Outcome:	The proposed benchmarks do not accurately assess generalization across distribution shifts, difficulty levels, and counterfactual scenarios.

Learn from Failure: Fine-tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving (2024.acl-long)

Copied to clipboard

Chenyang An, Zhibo Chen, Qihao Ye, Emily First, Letian Peng, Jiayun Zhang, Zihan Wang, Sorin Lerner, Jingbo Shang

RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering (2024.findings-acl)

Challenge:	Recent advances in Automated Theorem Proving have shown the effectiveness of leveraging a (large) language model that generates tactics (i.e. proof steps) to search through proof states.
Approach:	They propose to use a large language model that generates tactics to search through proof states.
Outcome:	The proposed model solves more unseen theorems with lower trial searches than the current model, which only learns from failed attempts.

Copied to clipboard

Zihan Zhang, Meng Fang, Ling Chen

EMCompress: Video-LLMs with Endomorphic Multimodal Compression (2026.findings-acl)

Challenge:	Existing methods for assessing retrieval of relevant information are understudied . previous studies have neglected to evaluate ARAG methods .
Approach:	They propose a benchmark to evaluate existing ARAG methods that use threshold tuning to adjust retrieval for queries instead of indiscriminate retrieval.
Outcome:	The proposed method can be used to evaluate existing ARAG methods without calibration or training.

Copied to clipboard

Zheyu Fan, Jiateng Liu, Yuji Zhang, Zihan Wang, Yi R. Fung, Manling Li, Heng Ji

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

Challenge:	Static, sparse frame sampling either dilutes evidence across task-irrelevant segments at significant cost or misses fine-grained temporal semantics altogether.
Approach:	They propose a novel task that compresses multimodal input while preserving answer invariance across reasonable downstream models.
Outcome:	The proposed task surpasses prior methods by 0.40 F-1 with competitive query rewriting.

Copied to clipboard

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

Exploiting Sentiment and Common Sense for Zero-shot Stance Detection (2022.coling-1)

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

Copied to clipboard

Yun Luo, Zihan Liu, Yuefeng Shi, Stan Z. Li, Yue Zhang

Sentiment Analysis

Challenge:	Existing stance detection models use sentiment and commonsense knowledge to classify stance toward documents and topics . obtaining rich annotated data in stance detector is time-consuming and laborintensive .
Approach:	They propose to use sentiment and commonsense knowledge to boost transferability of stance detection model by using sentiment and similar knowledge.
Outcome:	The proposed model outperforms the state-of-the-art methods on the zero-shot and few-shot benchmark datasets.

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

Copied to clipboard

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

MUSE: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles (2025.findings-acl)

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

Copied to clipboard

Zihan Wang, Xiaocui Yang, YongKang Liu, Shi Feng, Daling Wang, Yifei Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing research focuses solely on text, leaving a gap with practical applications.
Approach:	They propose to synthesize a multimodal conversational recommendation dataset using multimodal large language models to automatically synthesized data from 7,000 conversations in the Clothing domain.
Outcome:	The proposed dataset contains 83,148 utterances from 7,000 conversations centered around the Clothing domain.

Pre-training Language Model as a Multi-perspective Course Learner (2023.findings-acl)

Copied to clipboard

Beiduo Chen, Shaohan Huang, Zihan Zhang, Wu Guo, Zhenhua Ling, Haizhen Huang, Furu Wei, Weiwei Deng, Qi Zhang

MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning (2024.emnlp-main)

Challenge:	Experimental results show that our method significantly improves ELECTRA’s average performance by 2.8% and 3.2% absolute points respectively on GLUE and SQuAD 2.0 benchmarks.
Approach:	They propose a multi-perspective course learning method to fetch many degrees and visual angles for sample-efficient pre-training and to fully leverage the relationship between generator and discriminator.
Outcome:	The proposed method improves ELECTRA's performance on GLUE and SQuAD 2.0 benchmarks and overshadows recent advanced ELECL-style models under the same settings.

Copied to clipboard

Yufei Ma, Zihan Liang, Huangyu Dai, Ben Chen, Dehong Gao, Zhuoran Ran, Wang Zihan, Linbo Jin, Wen Jiang, Guannan Zhang, Xiaoyan Cai, Libin Yang

ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline (2024.findings-emnlp)

Challenge:	Recent advances in open-source Large Language Models (LLMs) have achieved notable successes in natural language processing.
Approach:	They propose a Parameter Efficient Fine-Tuning paradigm for improved fine-tuning and parameter efficiency in multi-task learning.
Outcome:	The proposed model outperforms existing methods on multi-task learning while reducing training costs by over 80% without losing general capability.

Copied to clipboard

Yifan Xu, Xiao Liu, Xinghan Liu, Zhenyu Hou, Yueyan Li, Xiaohan Zhang, Zihan Wang, Aohan Zeng, Zhengxiao Du, Zhao Wenyi, Jie Tang, Yuxiao Dong

Numerical Reasoning

Challenge:	Large language models (LLMs) have shown excellent mastering of human language but struggle in real-world applications that require mathematical problem-solving.
Approach:	They propose a pipeline to train a general Math-Critique model from the LLM itself to provide feedback signals and employ rejective fine-tuning and direct preference optimization over the Llm's own generations for data collection.
Outcome:	The proposed pipeline outperforms existing LLMs that could be two times larger.

Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification (2026.acl-long)

Copied to clipboard

Zihan Gu, TianYi Zhang, Xinyan Zhang, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu, Tianyi Ma, Xingsheng Zhang, Hua Zhang, Yue Hu

Challenge:	Existing methods to update large language models (LLMs) without expensive retraining are fragile under single-edit evaluation protocols.
Approach:	They propose a framework that characterizes activation-based editing as a constrained intervention on intermediate representations.
Outcome:	The proposed method reveals local knowledge conflicts invisible to existing benchmarks.

E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning (2025.emnlp-main)

Copied to clipboard

Zihan Liao, Jun Wang, Hang Yu, Lingxiao Wei, Jianguo Li, Jun Wang, Wei Zhang

A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization (2026.acl-long)

Challenge:	Considerable efforts have been and are still being put into increasing the context length of Large Language Models (LLMs)
Approach:	They propose an approach that divides long contexts into chunks, compresses each into soft prompts using a pretrained text encoder, and aligns these representations with a decoder-only LLM via an adapter.
Outcome:	The proposed approach outperforms 8 state-of-the-art methods in effectiveness and efficiency for document summarization and question answering, and achieves the best performance on LongBench v2 among models of comparable size.

Copied to clipboard

Ziqing Wang, Kexin Zhang, Zihan Zhao, Yibo Wen, Abhishek Pandey, Han Liu, Kaize Ding

DR-HM: Distill-then-Reinforce Training with Cognition-Aware Data Synthesis for Harmful Meme Detection (2026.findings-acl)

Challenge:	Large language models (LLMs) are introducing a paradigm shift in molecular discovery by enabling text-guided interaction with chemical spaces through natural language and symbolic notations.
Approach:	They analyze the current LLM learning paradigms to tackle four critical evaluation dimensions that have emerged as critical dimensions in recent studies.
Outcome:	The proposed models are able to interact with chemical spaces through natural language and symbolic notations, and have emerging extensions to incorporate multi-modal inputs.

Copied to clipboard

Zihan Cheng, Jianxiang Ma, Xiaocui Yang, Peidong Wang, Wen Zhang, Shi Feng, Daling Wang, Yifei Zhang, Mingfu Zhang

Sinkhorn Distance Minimization for Knowledge Distillation (2024.lrec-main)

Challenge:	Current methods for harmful meme detection lack the knowledge required to identify such hate . current methods lack the ability to identify cultural stereotypes and visual metaphors .
Approach:	They propose a framework that decomposes meme analysis into a human-inspired reasoning process . they propose DR-HM to transfer knowledge from closed-source models while mitigating biases .
Outcome:	The proposed framework outperforms existing methods on three benchmark datasets.

Copied to clipboard

Xiao Cui, Yulei Qin, Yuting Gao, Enwei Zhang, Zihan Xu, Tong Wu, Ke Li, Xing Sun, Wengang Zhou, Houqiang Li

Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics (2022.naacl-main)

Challenge:	Existing knowledge distillation methods investigate divergence measures but fail to deliver effective supervision when few distribution overlap exists between teacher and student.
Approach:	They propose a knowledge distillation method that exploits the Sinkhorn distance to ensure a nuanced assessment of the disparity between teacher and student distributions.
Outcome:	The proposed method outperforms state-of-the-art methods on all kinds of LLMs with encoder-only, encoder decoder, and decoded architectures.

Copied to clipboard

Zihan Zhang, Meng Fang, Ling Chen, Mohammad Reza Namazi Rad

Information Extraction & Text Mining

Challenge:	Recent work incorporates pre-trained word embeddings into Neural Topic Models (NTMs), generating highly coherent topics.
Approach:	They conduct thorough experiments to investigate whether embeddings directly with an appropriate word selection method can generate more coherent and diverse topics than NTMs.
Outcome:	The proposed model generates more coherent and diverse topics than traditional NTMs, achieving higher efficiency and simplicity.

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

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.

Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification (2026.acl-long)

Copied to clipboard

Jiayu Zhang, Shuo Ye, Qilang Ye, Zihan Song, Jiajian Huang, Zitong YU

PromptBERT: Improving BERT Sentence Embeddings with Prompts (2022.emnlp-main)

Challenge:	Recent audio-visual question answering methods lack effective mechanisms for handling missing modalities, leading to performance degradation in real-world scenarios with data interruptions.
Approach:	They propose a framework that shifts the paradigm of missing modality handling to retrieval-based recovery . they leverage cross-modal retrieval via unified semantic embeddings to acquire missing domain-specific knowledge.
Outcome:	The proposed framework improves AVQA and enhances robustness in modal-incomplete scenarios.

Copied to clipboard

Ting Jiang, Jian Jiao, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Denvy Deng, Qi Zhang

Mere Contrastive Learning for Cross-Domain Sentiment Analysis (2022.coling-1)

Challenge:	Existing research shows that BERT and RoBERTa are poor in sentence embeddings due to static token embeddable bias and ineffective BERT layers.
Approach:	They propose a novel contrastive learning method for better sentence embeddings by using a template denoising technique.
Outcome:	The proposed method achieves 2.29 and 2.58 points of improvement compared to SimCSE and RoBERTa in the unsupervised setting.

Copied to clipboard

Yun Luo, Fang Guo, Zihan Liu, Yue Zhang

Dual-Alignment Pre-training for Cross-lingual Sentence Embedding (2023.acl-long)

Challenge:	Existing approaches to cross-domain sentiment analysis are labor-intensive and time-consuming.
Approach:	They propose a modified contrastive objective with in-batch negative samples to allow sentence representations from the same class to be pushed closer while those from the different classes become further apart in the latent space.
Outcome:	The proposed model can achieve state-of-the-art in cross-domain and multi-domain sentiment analysis tasks while transferring knowledge learned in the source domain to the target domain.

Copied to clipboard

Ziheng Li, Shaohan Huang, Zihan Zhang, Zhi-Hong Deng, Qiang Lou, Haizhen Huang, Jian Jiao, Furu Wei, Weiwei Deng, Qi Zhang

Enhancing Learning-Based Binary Code Similarity Detection Model through Adversarial Training with Multiple Function Variants (2024.findings-emnlp)

Challenge:	Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding.
Approach:	They propose a dual-alignment pre-training framework that incorporates both sentence-level and token-level alignment.
Outcome:	The proposed framework improves cross-lingual sentence embedding on three cross-linguistic benchmarks.

Copied to clipboard

Lichen Jia, Chenggang Wu, Bowen Tang, Peihua Zhang, Zihan Jiang, Yang Yang, Ning Liu, Jingfeng Zhang, Zhe Wang

CITB: A Benchmark for Continual Instruction Tuning (2023.findings-emnlp)

Challenge:	Existing Learning-Based Binary Code Similarity Detection (LB-BCSD) methods exhibit lower accuracy in recognizing functions with the same functionality but different implementations.
Approach:	They propose a gradient-guided adversarial attack method based on critical code called FuncFooler which perturbs critical code to generate multiple variants of the same function.
Outcome:	The proposed method increases the accuracy of the current Learning-Based Binary Code Similarity Detection (LB-BCSD) model by 5%-7%.

Copied to clipboard

Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad

Enhancing the General Agent Capabilities of Low-Paramter LLMs through Tuning and Multi-Branch Reasoning (2024.findings-naacl)

Challenge:	Existing methods for instruction tuning do not leverage the rich natural language instructions.
Approach:	They propose to use a benchmark to study how instruction tuning works in CL tasks.
Outcome:	The proposed method can achieve similar or better results than existing CL methods.

Copied to clipboard

Qinhao Zhou, Zihan Zhang, Xiang Xiang, Ke Wang, Yuchuan Wu, Yongbin Li

Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation (2024.emnlp-main)

Challenge:	Open-source pre-trained Large Language Models exhibit strong language understanding and generation capabilities, making them highly successful in a variety of tasks.
Approach:	They propose a method to construct agent-specific data using GPT-4 and supervised fine-tuning . they find that supervised tunning can significantly reduce hallucination outputs and formatting errors in agent tasks .
Outcome:	The proposed method improves on five agent tasks of AgentBench.

Copied to clipboard

Yuanjie Lyu, Zihan Niu, Zheyong Xie, Chao Zhang, Tong Xu, Yang Wang, Enhong Chen

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

Challenge:	Large language models (LLMs) often produce factual errors due to limited internal knowledge.
Approach:	They propose a retrieval-augmented generation framework that generates plan tokens to guide subsequent generation.
Outcome:	The proposed framework improves the accuracy of large language models with external knowledge sources.

Copied to clipboard

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

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

The Sonar Moment: An Audio Geo-Localization Benchmark for Audio-Language Models (2026.findings-acl)

Copied to clipboard

Ruixing Zhang, Zihan Liu, Leilei Sun, Tongyu Zhu, Weifeng Lv

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement (2025.acl-long)

Challenge:	AGL1K is the first audio geo-localization benchmark for audio language models (ALMs) it is based on a crowd-sourced platform and is available in 72 countries and territories.
Approach:	They propose a benchmark for audio geo-localization that quantifies the informativeness of each recording and a metric that quantizes the information of each audio clip.
Outcome:	The proposed benchmarks cover 72 countries and territories and can be used to improve audio geo-localization.

Copied to clipboard

Boyi Kang, Xinfa Zhu, Zihan Zhang, Zhen Ye, Mingshuai Liu, Ziqian Wang, Yike Zhu, Guobin Ma, Jun Chen, Longshuai Xiao, Chao Weng, Wei Xue, Lei Xie

WebSRC: A Dataset for Web-Based Structural Reading Comprehension (2021.emnlp-main)

Challenge:	Recent advances in language models have demonstrated strong capabilities in semantic understanding and contextual modeling.
Approach:	They propose a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
Outcome:	The proposed language model outperforms prior task-specific discriminative and generative models in acoustic enhancement tasks.

Copied to clipboard

Xingyu Chen, Zihan Zhao, Lu Chen, JiaBao Ji, Danyang Zhang, Ao Luo, Yuxuan Xiong, Kai Yu

RoChBert: Towards Robust BERT Fine-tuning for Chinese (2022.findings-emnlp)

Challenge:	Using a web page and a question, a machine can't understand the contents of web pages.
Approach:	They propose a novel dataset for web-based structural reading comprehension that consists of 400K question-answer pairs and a dataset of 6.4K web pages.
Outcome:	The proposed dataset consists of 400K question-answer pairs, collected from 6.4K web pages with corresponding HTML source code, screenshots, and metadata.

Copied to clipboard

Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang

InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning (2025.acl-long)

Challenge:	Pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts.
Approach:	They propose to fuse Chinese phonetic and glyph features into pre-trained models by using a more comprehensive adversarial graph.
Outcome:	The proposed framework outperforms existing methods in significant ways on a wide range of tasks while remaining accurate on benign texts.

Copied to clipboard

Zifu Wan, Yaqi Xie, Ce Zhang, Zhiqiu Lin, Zihan Wang, Simon Stepputtis, Deva Ramanan, Katia P. Sycara

DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents (2026.acl-long)

Challenge:	Large multimodal foundation models perceive objects as indivisible, overlooking the components that constitute them.
Approach:	They propose a novel benchmark for large multimodal foundation models comprising hand-labeled part segmentation annotations and task-oriented instructions to evaluate their performance.
Outcome:	The proposed benchmark improves performance of current models in understanding and executing part-level tasks within everyday contexts.

Copied to clipboard

JunShuo Zhang, Chengrui Huang, Feng Guo, Zihan Li, Ke Shi, Menghua Jiang, Jiguo Yu, Shuo Shang, Shen Gao

CIRAG: Construction–Integration Retrieval and Adaptive Generation for Multi-hop Question Answering (2026.acl-long)

Challenge:	Existing approaches to large language model (LLM) agents that follow the sequential "reason-then-act" paradigm suffer from limited exploration and incomplete environmental understanding as they interact with only a single environment per step.
Approach:	They propose a paradigm that enables an agent to interact with multiple environments simultaneously and share cross-trajectory experiences.
Outcome:	The proposed paradigm achieves state-of-the-art (SOTA) success rates while maintaining comparable efficiency to strong sequential baselines.

Copied to clipboard

Zili Wei, Yilin Wang, Xiaocui Yang, Shi Feng, Weidong Bao, Daling Wang, Zihan Wang, Yifei Zhang

ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrieval (2025.emnlp-main)

Challenge:	Existing methods for iterative retrieval-augmented generation (iRAG) suffer from greedy single-path expansion and granularity–demand mismatch .
Approach:	They propose a model that constructs candidate triples and history-conditionally integrates them to distill core triples to generate the next-hop query.
Outcome:	The proposed model mitigates the greedy single-path expansion and granularity–demand mismatch by preserving multiple plausible evidence chains.

Copied to clipboard

Zihan Chen, Lei Shi, Weize Wu, Qiji Zhou, Yue Zhang

Information Extraction & Text Mining

Challenge:	Large language models (LLMs) are increasingly used to solve the entity recognition task.
Approach:	They propose a framework to select the most informative and representative samples for LLM in-context learning.
Outcome:	The proposed framework outperforms baselines on three specialized domain datasets.

Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns (2022.findings-acl)

Copied to clipboard

Zihan Wang, Jiuxiang Gu, Jason Kuen, Handong Zhao, Vlad Morariu, Ruiyi Zhang, Ani Nenkova, Tong Sun, Jingbo Shang

MedINST: Meta Dataset of Biomedical Instructions (2024.findings-emnlp)

Challenge:	Adaptive Axis Attention learns different attention patterns for each task and model layer . sparse attention patterns do not improve the run time of the models but they reduce model memory requirements .
Approach:	They propose a method that learns different attention patterns for each Transformer layer . they propose 'adaptive axis attention' method that identifies important tokens .
Outcome:	The proposed method does not require pre-training to accommodate sparse attention patterns.

Copied to clipboard

Wenhan Han, Meng Fang, Zihan Zhang, Yu Yin, Zirui Song, Ling Chen, Mykola Pechenizkiy, Qingyu Chen

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

Challenge:	Medical data and tasks require extensive preprocessing and standardization for effective use in training LLMs.
Approach:	They propose to use MedINST as a meta-dataset to evaluate LLMs' generalization ability.
Outcome:	The meta-dataset of biomedical instruction measures the generalization ability of LLMs across multiple open-domain tasks.

Copied to clipboard

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

CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (D19-1)

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

Copied to clipboard

Tao Yu, Rui Zhang, Heyang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, Youxuan Jiang, Michihiro Yasunaga, Sungrok Shim, Tao Chen, Alexander Fabbri, Zifan Li, Luyao Chen, Yuwen Zhang, Shreya Dixit, Vincent Zhang, Caiming Xiong, Richard Socher, Walter Lasecki, Dragomir Radev

Programming Languages in NLP

Challenge:	CoSQL is a corpus for building cross-domain, general-purpose database querying dialogue systems.
Approach:	They present a corpus for building cross-domain, general-purpose database querying dialogue systems . they use a Wizard-of-Oz collection of 3k turns plus 10k+ annotated SQL queries .
Outcome:	The proposed corpus is based on a Wizard-of-Oz dataset of 3k dialogues querying 200 complex DBs spanning 138 domains.

Turn-Level Active Learning for Dialogue State Tracking (2023.emnlp-main)

Copied to clipboard

Zihan Zhang, Meng Fang, Fanghua Ye, Ling Chen, Mohammad-Reza Namazi-Rad

MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings (2026.acl-long)

Challenge:	Existing approaches to annotate dialogues require supervised training, which requires human workers to manually annotates dialogues.
Approach:	They propose a turn-level active learning framework to actively select dialogue turns to annotate . their approach can achieve comparable performance to traditional training approaches .
Outcome:	The proposed model achieves comparable performance to existing training approaches with significantly less annotated data.

Copied to clipboard

Yiqun Zhang, Hao Li, Zihan Wang, Shi Feng, Xiaocui Yang, Daling Wang, Bo Zhang, Lei Bai, Shuyue Hu

Natural Language Processing in Support of Evidence-based Medicine: A Scoping Review (2025.findings-acl)

Challenge:	Multi-turn, long-horizon tasks require dozens of sequential model calls per episode.
Approach:	They propose a cost-aware multi-turn LLM routing tool which encodes interaction history and candidate models into joint history–model embeddings and learns an outcome estimator from logged trajectories to predict turn-level model utility.
Outcome:	The proposed model reduces cost and performance by 58.7% on ScienceWorld and on Humanity’s Last Exam (HLE) and even reduces costs for held-out tasks.

Copied to clipboard

Zihan Xu, Haotian Ma, Yihao Ding, Gongbo Zhang, Chunhua Weng, Yifan Peng

Decompose, Prioritize, and Eliminate: Dynamically Integrating Diverse Representations for Multimodal Named Entity Recognition (2024.lrec-main)

Challenge:	Evidence-based medicine (EBM) is at the forefront of modern healthcare, emphasizing the use of the best available scientific evidence to guide clinical decisions.
Approach:	They propose to investigate the use of Natural Language Processing (NLP) techniques to identify, appraise, synthesize, apply, and disseminate evidence in EBM.
Outcome:	The proposed methods support the five fundamental steps of EBM—Ask, Acquire, Appraise, Apply, and Assess.

Copied to clipboard

Zihao Zheng, Zihan Zhang, Zexin Wang, Ruiji Fu, Ming Liu, Zhongyuan Wang, Bing Qin

The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs (2026.acl-long)

Challenge:	Existing research on multi-modal Named Entity Recognition (MNER) does not integrate all multi-modal representations to provide rich contextual information to improve NER.
Approach:	They propose an iterative reasoning framework that integrates all the diverse multi-modal representations following the strategy of "decompose, prioritize, and eliminate" . they propose to use hierarchically connected fusion layers to prioritize transitions from "easy-to-hard" and "coarse-to fine"
Outcome:	The proposed framework integrates all the diverse multi-modal representations following the strategy of "decompose, prioritize, and eliminate".

Copied to clipboard

Zihan Chen, Yiming Zhang, Wenxiang Geng, Zenghui Ding, Yining Sun

Answer is All You Need: Instruction-following Text Embedding via Answering the Question (2024.acl-long)

Challenge:	Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) exhibit a critical failure mode: they exhibit brittle reasoning capabilities on out-of-distribution tasks.
Approach:	They propose a framework bridging Structural Causal Models and the Information Bottleneck principle to explain this paradox.
Outcome:	The proposed framework bridges the framework between SCM and IB principles to explain the problem.

Copied to clipboard

Letian Peng, Yuwei Zhang, Zilong Wang, Jayanth Srinivasa, Gaowen Liu, Zihan Wang, Jingbo Shang