Papers by Yang Lyu

Out-of-Distribution Generalization in Natural Language Processing: Past, Present, and Future (2023.emnlp-main)

Challenge:	Existing training-free methods are vulnerable to the attention sink phenomenon . Existing methods include contrastive decoding and auxiliary expert models .
Approach:	They propose a training-free attention intervention that constructs a PAD map to identify semantically core visual regions and applies per-head Median Absolute Deviation Scaling to adaptively control the intervention strength.
Outcome:	The proposed intervention improves visual grounding and reduces hallucinations on multiple LVLMs and benchmarks.

Copied to clipboard

Linyi Yang, Yaoxian Song, Xuan Ren, Chenyang Lyu, Yidong Wang, Jingming Zhuo, Lingqiao Liu, Jindong Wang, Jennifer Foster, Yue Zhang

Responsible & Trustworthy NLP

Challenge:	Existing literature on the generalization of machine learning models to out-of-distribution data is lacking.
Approach:	They propose to present the first comprehensive review of recent progress, methods, and evaluations on the generalization challenge from an OOD perspective in natural language understanding.
Outcome:	The proposed survey provides the first comprehensive review of recent progress, methods, and evaluations on the generalization challenge from an OOD perspective in natural language understanding.

Visual Goal-Step Inference using wikiHow (2021.emnlp-main)

Copied to clipboard

Yue Yang, Artemis Panagopoulou, Qing Lyu, Li Zhang, Mark Yatskar, Chris Callison-Burch

LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models (2024.emnlp-main)

Challenge:	Past work in NLP examined the task of goal-step inference for textual goals . wikiHow dataset shows that goal-step inference is challenging for state-of-the-art models .
Approach:	They propose a task where a model is given a textual goal and must choose which of four images represents a plausible step towards that goal.
Outcome:	The proposed task is challenging for state-of-the-art multimodal models and can be transferred to other datasets.

Copied to clipboard

Yuxuan Wan, Wenxuan Wang, Yiliu Yang, Youliang Yuan, Jen-tse Huang, Pinjia He, Wenxiang Jiao, Michael Lyu

Privacy Risks of Intermediate Representations: Attribute Inference in Distributed LLM Inference (2026.findings-acl)

Challenge:	LogicAsker examines and improves the reasoning abilities of large language models such as ChatGPT and GPT-4.
Approach:	They propose a set of atomic reasoning skills grounded in propositional and predicate logic to examine and improve the reasoning abilities of large language models such as ChatGPT and GPT-4.
Outcome:	The proposed approach improves reasoning abilities in large language models such as ChatGPT and GPT-4 by up to 5%.

Copied to clipboard

Yang Lyu, Jin Cao, Yang Xiao, Zhe Sun, Ben Niu, Fenghua Li, Hui LI

Responsible & Trustworthy NLP

Challenge:	Distributed LLMs avoid raw inputs by transmitting intermediate hidden states, a practice widely assumed to preserve privacy.
Approach:	They propose a distributed inference framework that transmits intermediate hidden states to avoid sending raw inputs by exposing sensitive user attributes.
Outcome:	The proposed approach achieves Top-1 accuracy of 0.997 on CMS, 0.980 on Skytrax, and 0.986 on ECHR.

UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging (2025.emnlp-main)

Copied to clipboard

Cheryl Lee, Chunqiu Steven Xia, Longji Yang, Jen-tse Huang, Zhouruixing Zhu, Lingming Zhang, Michael R. Lyu

Cognitive Modeling

Challenge:	Existing LLMs focus on isolated steps and struggle with complex bugs.
Approach:	They propose a framework for unified debugging through multi-agent synergy . it mimics the entire cognitive processes of developers with each agent specialized as a particular component of this process .
Outcome:	The proposed framework outperforms state-of-the-art methods on repo-level benchmarks.

Tree-of-Code: A Self-Growing Tree Framework for End-to-End Code Generation and Execution in Complex Tasks (2025.findings-acl)

Copied to clipboard

Ziyi Ni, Yifan Li, Ning Yang, Dou Shen, Pin Lyu, Daxiang Dong

Programming Languages in NLP

Challenge:	Effectively and efficiently handling complex realworld problems has become a key focus across industry and academia.
Approach:	They propose a tree-of-code framework that generates nodes through self-supervision and combines prompt and model exploration in a GT-free setting.
Outcome:	Experiments on two datasets with ten popular zero-shot LLMs show that Tree-of-Code boosts accuracy by nearly 20% over CodeAct with fewer than 1/4 turns.

Exploiting Rich Textual User-Product Context for Improving Personalized Sentiment Analysis (2023.findings-acl)

Copied to clipboard

Chenyang Lyu, Linyi Yang, Yue Zhang, Yvette Graham, Jennifer Foster

Sentiment Analysis

Challenge:	Typical approaches do not exploit the potential of historical reviews or do not make full use of user/product associations.
Approach:	They propose to use historical reviews to initialize user and product representations and incorporate textual associations via a user-product cross-context module.
Outcome:	The proposed method outperforms existing state-of-the-art models on IMDb, Yelp and Longformer benchmarks.

FactTrack: Time-Aware World State Tracking in Story Outlines (2025.naacl-long)

Copied to clipboard

Zhiheng Lyu, Kevin Yang, Lingpeng Kong, Dan Klein

DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation (2025.findings-acl)

Challenge:	Existing language models still struggle to reason over long context windows . et al., 2022, show that long context generation is a challenge for LLMs .
Approach:	They propose a method for tracking atomic facts and addressing factual contradictions . they use a four-step pipeline to update a world state data structure for each new event .
Outcome:	The proposed method outperforms a baseline and fair method on story outlines.

Copied to clipboard

Xinglin Lyu, Wei Tang, Yuang Li, Xiaofeng Zhao, Ming Zhu, Junhui Li, Yunfei Lu, Min Zhang, Daimeng Wei, Hao Yang, Min Zhang

Text Generation

Challenge:	Document-level context is crucial for speech translation due to noise from ASR . incorporating document-level contextual information into ST remains a challenge .
Approach:	They develop an online framework that integrates document-level context into machine translation . they use document-based modules to integrate document- level context into ST .
Outcome:	The proposed framework outperforms baselines in sentence and discourse metrics . it can correct ASR transcription errors and improve translation performance .

Information Aggregation for Multi-Head Attention with Routing-by-Agreement (N19-1)

Copied to clipboard

Jian Li, Baosong Yang, Zi-Yi Dou, Xing Wang, Michael R. Lyu, Zhaopeng Tu

Multi-Head Attention with Disagreement Regularization (D18-1)

Challenge:	Existing studies focus on extracting informative or distinct partial-representations from different subspaces, while few studies have paid attention to the aggregation of the extracted partial-Representations.
Approach:	They propose to use a routing-by-agreement algorithm to improve multi-head attention by iteratively updating the proportion of how much a part should be assigned to a whole based on agreement between parts and wholes.
Outcome:	The proposed algorithm improves the information aggregation for multi-head attention over the standard linear transformation on linguistic probing and machine translation tasks.

Copied to clipboard

Jian Li, Zhaopeng Tu, Baosong Yang, Michael R. Lyu, Tong Zhang

Modeling Consistency Preference via Lexical Chains for Document-level Neural Machine Translation (2022.emnlp-main)

Challenge:	Existing methods to encourage diversity among multi-head attention are limited.
Approach:	They propose a disagreement regularization term to encourage diversity among attention heads . they validated their approach on EnglishGerman and ChineseEnglish translation tasks .
Outcome:	The proposed approach improves translation performance across language pairs on English-German and Chinese-English translation tasks.

Copied to clipboard

Xinglin Lyu, Junhui Li, Shimin Tao, Hao Yang, Ying Qin, Min Zhang

Machine Translation

Challenge:	Experimental results show that consistency preference for lexical chains reduces lexical translation inconsistency . Lexical translation consistency is a common discourse phenomenon .
Approach:	They propose a consistency-aware model which captures consistency context . they then define consistency-tailored latent variables which guide translation of corresponding sentences .
Outcome:	The proposed model significantly improves translation performance in ChineseEnglish and FrenchEnglish translation tasks.

Retrieval-Augmented Language Models are Mimetic Theorem Provers (2025.findings-emnlp)

Copied to clipboard

Wenjie Yang, Ruiyuan Huang, Jiaxing Guo, Zicheng Lyu, Tongshan Xu, Shengzhong Zhang, Lun Du, Da Zheng, Zengfeng Huang

Reasoning

Challenge:	Large language models often fail to provide rigorous proof-based reasoning for research-level mathematics.
Approach:	They propose a simple yet effective RAG framework that augments retrieved proofs with queries and document contexts to improve retrieval performance.
Outcome:	The proposed framework improves retrieval performance by 34.19% . dual RAG can be used to prove research-level theorems in theoretical machine learning .

Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage (2026.acl-long)

Copied to clipboard

Xueting Li, Qi Liu, Chenghao Xu, Xu Yang, Guangtao Lyu, Jiahua Li, Cheng Deng

Explainability & Interpretability in NLP

Challenge:	Existing visual token pruning methods leverage simple metrics derived from human experience, such as attention or similarity, to rank and select tokens within a highly entangled feature space.
Approach:	They propose a novel visual token pruning method that uses a concept-driven paradigm to quantify the Marginal Semantic Gain of each token's contribution to uncovered concepts.
Outcome:	The proposed method outperforms state-of-the-art methods in a concept-driven model while maintaining semantic completeness.

Chain-of-Thought Reasoning in Tabular Language Models (2023.findings-emnlp)

Copied to clipboard

Mingyu Zheng, Hao Yang, Wenbin Jiang, Zheng Lin, Yajuan Lyu, Qiaoqiao She, Weiping Wang

Reasoning

Challenge:	Existing approaches to extend chain-of-thought reasoning into large language models are not viable in the scenario of privatization deployment or limited resources.
Approach:	They propose a framework that extends chain-of-thought reasoning into tabular language models . framework coordinates two TaLMs responsible for CoT generation and answer inference .
Outcome:	The proposed framework outperforms the state-of-the-art ChatGPT on the TABMWP dataset by 9.55% (82.60%92.15% in accuracy) with less parameters (0.8B).

DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators (2024.emnlp-main)

Copied to clipboard

Xinglin Lyu, Junhui Li, Yanqing Zhao, Min Zhang, Daimeng Wei, Shimin Tao, Hao Yang, Min Zhang

Text Generation

Challenge:	Concatenating large language models are adapted to context-aware neural machine translation in a concatenated way . a recent paradigm shift has been witnessed in discourse-related challenges such as zero pronoun translation .
Approach:	They propose an alternative adaptation approach to make large language models discriminately model and utilize inter- and intra-sentence contexts.
Outcome:	The proposed approach outperforms concatenation mode and improves performance in discourse modeling.

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

Copied to clipboard

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

Information Retrieval

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.

IM-TQA: A Chinese Table Question Answering Dataset with Implicit and Multi-type Table Structures (2023.acl-long)

Copied to clipboard

Mingyu Zheng, Yang Hao, Wenbin Jiang, Zheng Lin, Yajuan Lyu, QiaoQiao She, Weiping Wang

Structured Data in NLP

Challenge:	Existing benchmarks only evaluate model performance on tables with explicit table structures, which means headers are explicitly annotated and treated as model input during inference.
Approach:	They propose a new Table Question Answering (TQA) dataset with implicit and multi-type table structures that requires the model to understand tables without directly available header annotations.
Outcome:	The proposed framework outperforms baselines on a dataset with implicit and multi-type table structures and can handle multi-table tables including previously neglected complex tables.

AwarenessBench: Assessing Cognitive Capabilities of Language Models (2026.acl-long)

Copied to clipboard

Xiaojian Li, Rongwu Xu, Tianyun Zhang, Yue Wang, Shuo Chen, Qiner Lyu, Briana Zhang, Peiran Yang, Kyle Xue Chen, Haoyuan Shi, Yu Wang, Wei Xu

Can Multimodal LLMs See Materials Clearly? A Multimodal Benchmark on Materials Characterization (2025.findings-emnlp)

Challenge:	Language models exhibit increasingly consciousness-like behaviors, requiring a baseline to evaluate their cognitive abilities.
Approach:	They propose a benchmark to assess the cognitive abilities of language models (LMs) they compare 18 state-of-the-art LMs to human models in metacognition, self-awareness, social awareness and situational awareness .
Outcome:	Evaluating 18 state-of-the-art LMs, they find they consistently surpass baselines . but most models fall short in metacognition and self-awareness, the study finds .

Copied to clipboard

Zhengzhao Lai, Youbin Zheng, Zhenyang Cai, Haonan Lyu, Jingpu Yang, Hong-Qing Liang, Yan Hu, Benyou Wang

Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data (2022.acl-long)

Challenge:	characterization imaging data is fundamental to acquiring materials information.
Approach:	a team of researchers develop a benchmark for materials characterization imaging data . the goal is to bridge this gap by addressing 1,500 questions that require expert-level expertise.
Outcome:	a new benchmark for materials characterization imaging data is presented . the benchmark reveals that MLLMs perform poorly when addressing higher-level questions .

Copied to clipboard

Shuyan Zhou, Li Zhang, Yue Yang, Qing Lyu, Pengcheng Yin, Chris Callison-Burch, Graham Neubig

LLM Knows Body Language, Too: Translating Speech Voices into Human Gestures (2024.acl-long)

Challenge:	Existing work has treated procedures as shallow structures without modeling the parent-child relation.
Approach:	They propose to construct an open-domain hierarchical knowledge-base (KB) of procedures based on wikiHow . they link steps in an article to other articles with similar goals, recursively building the KB .
Outcome:	The proposed method significantly outperforms baselines according to automatic evaluation, human judgment, and application to downstream tasks such as instructional video retrieval.

Copied to clipboard

Chenghao Xu, Guangtao Lyu, Jiexi Yan, Muli Yang, Cheng Deng

Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement (2025.acl-long)

Challenge:	despite advances in the generation of realistic human gestures, the process often includes unintended, meaningless, or non-realistic gestures.
Approach:	They propose a framework that leverages large language models to generate human gestures . the primary stage employs a transformer-based auto-encoder network to encode human gesture into discrete symbols .
Outcome:	The proposed framework has demonstrated state-of-the-art performance on public TED and TED-Expressive datasets.

Copied to clipboard

Yichen Dong, Xinglin Lyu, Junhui Li, Daimeng Wei, Min Zhang, Shimin Tao, Hao Yang

Machine Translation

Challenge:	Recent research has shown that large language models (LLMs) can enhance translation quality through self-refinement.
Approach:	They propose to extend translation refinement from sentence-level to document-level by using document-to-document (Doc2Doc) translations.
Outcome:	The proposed method improves translation quality across ten translation tasks with LLaMA-3-8B-Instruct and Mistral-Nemo-Instru.

Revisiting Modularized Multilingual NMT to Meet Industrial Demands (2020.emnlp-main)

Copied to clipboard

Sungwon Lyu, Bokyung Son, Kichang Yang, Jaekyoung Bae

Multilinguality

Challenge:	Currently, the complete sharing of parameters for multilingual translation (1-1) is the most popular approach because of its compactness.
Approach:	They propose to use a multilingual neural machine translation model that only shares modules among the same languages as 1-1 to satisfy industrial requirements.
Outcome:	The proposed model can enjoy the benefits of multi-way training without the capacity bottleneck and low maintainability.

MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework (2025.findings-emnlp)

Copied to clipboard

Yupeng Qi, Ziyu Lyu, Min Yang, Yanlin Wang, Lu Bai, Lixin Cui

Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension (P19-1)

Challenge:	Recent studies address safety-constrained online and offline preferences optimizations, but offline methods perform poorly in adaptively balancing safety and helpfulness.
Approach:	They propose a mixture of experts framework for safety-helpfulness dual Preference Optimization . they combine a single-preference enhanced direct preference optimization approach with a dynamic routing mechanism .
Outcome:	The proposed framework outperforms state-of-the-art methods in safety and helpfulness.

Copied to clipboard

An Yang, Quan Wang, Jing Liu, Kai Liu, Yajuan Lyu, Hua Wu, Qiaoqiao She, Sujian Li

Fisher-Driven Adaptive Locating for Knowledge Editing in Large Language Models (2026.acl-long)

Challenge:	Recent results show pre-trained language models (LMs) can improve machine reading comprehension (MRC) Experimental results indicate that KT-NET offers significant and consistent improvements over BERT .
Approach:	They propose a method that leverages external knowledge bases to improve machine reading comprehension (MRC) KT-NET employs an attention mechanism to select desired knowledge from KBs and fuses selected knowledge with BERT to enable context- and knowledge-aware predictions.
Outcome:	The proposed model outperforms baseline models on ReCoRD and SQuAD1.1 benchmarks and ranks 1st on the ReCoDR and SQUAD1.1 leaderboards.

Copied to clipboard

Chenghao Xu, Jiexi Yan, Guangtao Lyu, Qi Liu, Muli Yang, Cheng Deng

Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)

Challenge:	Existing methods for locating and editing static knowledge are costly and risk catastrophic forgetting or error.
Approach:	They propose a Fisher-driven adaptation-aware locating strategy that dynamically identifies which model components should be edited for a given knowledge update.
Outcome:	Experiments on standard benchmarks show that FiDAL improves editing effectiveness and knowledge preservation across multiple editing methods.

Copied to clipboard

Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun