Papers by Yiwei Liu

Code Models are Zero-shot Precondition Reasoners (2024.naacl-long)

Challenge:	High-quality scientific data is critical for advancing LLMs, yet academic literature remains underutilized.
Approach:	They construct a large-scale raw scientific corpus but identify a critical Learnability Gap . they develop a multi-stage pipeline featuring content cleaning and pedagogical augmentation .
Outcome:	The proposed approach boosts average performance by +2.12 (3B) and +2.95 (7B) on in-domain tasks.

Copied to clipboard

Lajanugen Logeswaran, Sungryull Sohn, Yiwei Lyu, Anthony Liu, Dong-Ki Kim, Dongsub Shim, Moontae Lee, Honglak Lee

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

Challenge:	Existing methods to reason about action preconditions are lacking for agent to complete tasks.
Approach:	They propose a method to reason about action preconditions using pre-trained code models.
Outcome:	The proposed approach improves few-shot policy learning approaches across task-oriented dialog and embodied textworld benchmarks.

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

Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts (2025.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

Baolong Bi, Shenghua Liu, Lingrui Mei, Yiwei Wang, Junfeng Fang, Pengliang Ji, Xueqi Cheng

Gated Differentiable Working Memory for Long-Context Language Modeling (2026.acl-long)

Challenge:	In-context knowledge editing (ICE) is currently the most effective method for knowledge editing, but it is constrained by the black-box modeling of LLMs and lacks interpretability.
Approach:	They propose a method to decode new knowledge by comparing logits with unedited knowledge to improve the accuracy of LLMs.
Outcome:	The proposed method improves the performance of LLaMA3-8B-instruct on MQuAKE by up to 219%.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Yuyao Ge, Baolong Bi, Jiayu Yao, Jun Wan, Ziling Yin, Jiafeng Guo, Xueqi Cheng

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)

Challenge:	Long contexts break transformers, attention scores dilute, model cannot adapt to novel patterns at inference time.
Approach:	They propose a framework that gates the memory consolidation process by estimating Contextual Utility . they propose GDWM to maintain a form of working memory with constant contexts .
Outcome:	The proposed framework achieves comparable or superior performance on sparse-information tasks with 4 fewer gradient steps compared to uniform baselines.

Copied to clipboard

Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong

Explainability & Interpretability in NLP

Challenge:	Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored.
Approach:	They propose a survey structured around the pipeline to identify and improve MI models.
Outcome:	The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency.

LPNL: Scalable Link Prediction with Large Language Models (2024.findings-acl)

Copied to clipboard

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Xueqi Cheng

Dangling-Aware Entity Alignment with Mixed High-Order Proximities (2022.findings-naacl)

Challenge:	Existing studies on graph learning with large language models have focused on the link prediction task on large graphs.
Approach:	They propose a framework for scalable link prediction on large-scale heterogeneous graphs based on large language models.
Outcome:	The proposed framework outperforms baselines in link prediction tasks on large graphs.

Copied to clipboard

Juncheng Liu, Zequn Sun, Bryan Hooi, Yiwei Wang, Dayiheng Liu, Baosong Yang, Xiaokui Xiao, Muhao Chen

Structured Data in NLP

Challenge:	Existing methods for dangling-aware entity alignment are underexplored but important problem.
Approach:	They propose a framework that uses high-order proximities to detect dangling entities and align matchable entities.
Outcome:	The proposed framework detects dangling entities and aligns matchable entities better than existing methods.

Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis (2022.naacl-main)

Copied to clipboard

Yiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Dayiheng Liu, Baosong Yang, Juncheng Liu, Bryan Hooi

Information Extraction & Text Mining

Challenge:	Existing studies rely on entity information for sentence-level relation extraction (RE) but this can leak superficial and spurious clues of relations.
Approach:	They propose to use entity mentions to extract relations from textual context . they use a causal graph to model dependencies between variables in RE models .
Outcome:	The proposed method yields significant gains on both effectiveness and generalization for RE.

TactfulToM: Do LLMs have the Theory of Mind ability to understand White Lies? (2025.emnlp-main)

Copied to clipboard

Yiwei Liu, Emma Jane Pretty, Jiahao Huang, Saku Sugawara

Linguistics & Cognitive NLP

Challenge:	Recent studies explore Large Language Models’ (LLMs) performance on Theory of Mind (ToM) reasoning tasks, but research on ToM abilities that require more nuanced social context is limited, such as white lies.
Approach:	They propose a novel English benchmark to evaluate Large Language Models’ ability to understand white lies within real-life conversations and reason about prosocial motivations behind them.
Outcome:	The proposed model outperforms state-of-the-art models on ToM reasoning tasks and reveals significant gaps between humans and LLMs.

a1: Steep Test-time Scaling Law via Environment Augmented Generation (2026.findings-acl)

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Yuyao Ge, Jun Wan, Yurong Wu, Xueqi Cheng

FormulaReasoning: A Dataset for Formula-Based Numerical Reasoning (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have made remarkable advances in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during complex multi-step tasks.
Approach:	They propose a framework that enhances LLM reasoning through real-time environmental feedback validating each reasoning step, dynamic branch exploration for investigating alternative solution paths when faced with errors, and experience-based learning from successful reasoning trajectories.
Outcome:	The proposed model outperforms comparable models by 24.4 percentage points across benchmarks while outperforming comparable models.

Copied to clipboard

Xiao Li, Bolin Zhu, Kaiwen Shi, Sichen Liu, Yin Zhu, Yiwei Liu, Gong Cheng

SLANG: New Concept Comprehension of Large Language Models (2024.emnlp-main)

Challenge:	Existing datasets for numerical reasoning often lack explicit knowledge of formulas . current datasets do not provide process supervision information, resulting in incomplete reasoning .
Approach:	They propose a benchmark for formula-based numerical reasoning with 5,324 questions . they provide annotations in English and Chinese and a formula database as an external knowledge source .
Outcome:	The proposed model includes 5,324 questions requiring calculations grounded in external physics principles.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Xueqi Cheng

Can Graph Descriptive Order Affect Solving Graph Problems with LLMs? (2025.acl-long)

Challenge:	Dynamic nature of language limits the adaptability of Large Language Models (LLMs) Traditionally, LLMs are trained on static data, which limits their adaptability .
Approach:	They propose a benchmark to integrate novel data and assess LLMs’ ability to comprehend emerging concepts, alongside a causal inference-based approach to enhance LLM comprehension of new phrases and their colloquial context.
Outcome:	The proposed model outperforms baseline models in terms of precision and relevance in the comprehension of Internet slang and memes.

Copied to clipboard

Yuyao Ge, Shenghua Liu, Baolong Bi, Yiwei Wang, Lingrui Mei, Wenjie Feng, Lizhe Chen, Xueqi Cheng

“Not Aligned” is Not “Malicious”: Being Careful about Hallucinations of Large Language Models’ Jailbreak (2025.coling-main)

Challenge:	Large language models (LLMs) have achieved significant success in reasoning tasks, including mathematical reasoning and logical deduction.
Approach:	They conduct the first comprehensive analysis of how the order of graph descriptions impacts LLM performance.
Outcome:	The results show that graph descriptions significantly improve LLMs’ comprehension of graph structures, and the robustness of LLM models to graph description order varies across different tasks.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Jiayi Mao, Xueqi Cheng

TOD-Flow: Modeling the Structure of Task-Oriented Dialogues (2023.emnlp-main)

Challenge:	“Jailbreak” is a major safety concern of Large Language Models (LLMs).
Approach:	They propose a benchmarking framework to evaluate "jailbreak" outputs . they propose specialized validation framework to ensure outputs are useful malicious instructions .
Outcome:	The proposed framework enhances existing benchmarks to ensure outputs are useful . it also aims to evaluate the true potential of jailbroken outputs to cause harm to human society.

Copied to clipboard

Sungryull Sohn, Yiwei Lyu, Anthony Liu, Lajanugen Logeswaran, Dong-Ki Kim, Dongsub Shim, Honglak Lee

Dialogue Systems & Conversational Agents

Challenge:	Recent advances in task-oriented dialogue systems have limitations regarding transparency and controllability.
Approach:	They propose to infer the TOD-flow graph from dialog data annotated with dialog acts and integrate it with any dialogue model to improve its prediction performance, transparency, and controllability.
Outcome:	The proposed approach improves dialog act classification and response generation performance in the MultiWOZ and SGD benchmarks.

InFoBench: Evaluating Instruction Following Ability in Large Language Models (2024.findings-acl)

Copied to clipboard

Yiwei Qin, Kaiqiang Song, Yebowen Hu, Wenlin Yao, Sangwoo Cho, Xiaoyang Wang, Xuansheng Wu, Fei Liu, Pengfei Liu, Dong Yu

How to Make Large Language Models Generate 100% Valid Molecules? (2025.emnlp-main)

Challenge:	Existing methods for evaluating Large Language Models (LLMs) ability to follow instructions have not been able to provide a detailed analysis of their compliance with instructions.
Approach:	They propose a new metric for evaluating Large Language Models' ability to follow instructions and a benchmark for DRFR.
Outcome:	The proposed metric and benchmark compared with traditional scoring methods and explores annotation sources including human experts, crowd-sourced workers, and GPT-4.

Copied to clipboard

Wen Tao, Jing Tang, Alvin Chan, Bryan Hooi, Baolong Bi, Nanyun Peng, Yuansheng Liu, Yiwei Wang

Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering (2025.acl-long)

Challenge:	Large language models (LLMs) can learn to perform a wide range of tasks, but generating valid molecules using representations like SMILES is challenging in few-shot settings.
Approach:	They propose a language framework that converts invalid SMILES to SELFIES and LLMs as post-hoc correctors to ensure that the molecules generated by LLM are 100% valid.
Outcome:	The proposed model performs worse with SELFIES than with SMILES and improves on other metrics.

Copied to clipboard

Rongzhi Zhu, Xiangyu Liu, Zequn Sun, Yiwei Wang, Wei Hu

Natural Language Interfaces

Challenge:	Empirical results show that ChainRAG consistently outperforms baselines in both effectiveness and efficiency.
Approach:	They propose a method which sequentially handles each sub-question by completing missing key entities and retrieving relevant sentences from a sentence graph for answer generation.
Outcome:	The proposed method outperforms baselines on three multi-hop QA datasets.

Generating Relevant and Coherent Dialogue Responses using Self-Separated Conditional Variational AutoEncoders (2021.acl-long)

Copied to clipboard

Bin Sun, Shaoxiong Feng, Yiwei Li, Jiamou Liu, Kan Li

Dialogue Systems & Conversational Agents

Challenge:	Conditional Variational AutoEncoders (CVAE) can enhance the diversity and informativeness of responses in open-domain dialogue generation tasks.
Approach:	They propose a Conditional Variational AutoEncoder (CVAE) that regularizes latent variables and introduces group information to regularize them.
Outcome:	Empirical results show that the proposed model can significantly boost responses in well-established open-domain dialogue datasets.

Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization (2025.findings-emnlp)

Copied to clipboard

Shuyang Hao, Yiwei Wang, Bryan Hooi, Jun Liu, Muhao Chen, Zi Huang, Yujun Cai

Robustness in NLP

Challenge:	HKVE selectively accepts gradient optimization results based on the distribution of attention scores across different layers, ensuring that every optimization step positively contributes to the attack.
Approach:	They propose a framework that selectively accepts gradient optimization results based on the distribution of attention scores across different layers and selectively takes them into account when calculating the attack success rate.
Outcome:	The proposed framework outperforms existing methods by achieving success rates of 75.08% on MiniGPT4, 85.84% on LLaVA and 81.00% on Qwen-VL.

DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning (2025.emnlp-main)

Copied to clipboard

Hang Wu, Hongkai Chen, Yujun Cai, Chang Liu, Qingwen Ye, Ming-Hsuan Yang, Yiwei Wang

Multimodality

Challenge:	DiMo-GUI is a training-free framework for GUI grounding that splits input into textual elements and iconic elements, allowing the model to reason over each modality independently using general-purpose vision-language models.
Approach:	They propose a training-free framework for GUI grounding that leverages two core strategies: dynamic visual grounding and modality-aware optimization.
Outcome:	The proposed framework splits the input into textual elements and iconic elements, allowing the model to reason over each modality independently using general-purpose vision-language models.

Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities (2024.findings-emnlp)

Copied to clipboard

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Hongcheng Gao, Yilong Xu, Xueqi Cheng

Challenge:	Existing methods to update parametric knowledge of large language models (LLMs) are outdated and incontext editing (KE) is not effective due to the substantial cost associated with retraining.
Approach:	They propose a new decoding technique that enhances in-context editing (ICE) they propose to use parametric knowledge to update the models' knowledge .
Outcome:	The proposed technique improves ICE performance while incurring only half the latency.

Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation (2025.emnlp-main)

Copied to clipboard

Jiayu Yao, Shenghua Liu, Yiwei Wang, Lingrui Mei, Baolong Bi, Yuyao Ge, Zhecheng Li, Xueqi Cheng

Information Retrieval

Challenge:	Existing RAG models are sensitive to the order in which evidence is presented, resulting in unstable performance and biased reasoning.
Approach:	They propose to quantify position bias in multimodal RAG systems by using position sensitivity index . they also develop a visualization framework to trace attention allocation patterns across decoder layers .
Outcome:	The proposed framework shows that multimodal interactions intensify position bias compared to unimodal settings and that this bias increases logarithmically with retrieval range.

NewsDialogues: Towards Proactive News Grounded Conversation (2023.findings-acl)

Copied to clipboard

Siheng Li, Yichun Yin, Cheng Yang, Wangjie Jiang, Yiwei Li, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, Yujiu Yang

Natural Language Interfaces

Challenge:	Hot news is one of the most popular topics in daily conversations.
Approach:	They propose a task where a dialogue system can lead the conversation based on key topics of the news.
Outcome:	The proposed method can lead conversations based on key topics of the news . it can also be used in information-seeking and chit-chat scenarios .

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks (2026.acl-long)

Copied to clipboard

Wenqi Zhang, Mengna Wang, Gangao Liu, Huixin Xu, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Jiajun Liu, Weiming Lu, Peng Li, Yueting Zhuang

MoEC: A Memory-Routed Mixture-of-Experts Controller for Adaptive Minecraft Control (2026.acl-long)

Challenge:	Recent advances in reasoning models have demonstrated remarkable capabilities on mathematical and coding tasks, but their effectiveness in embodied domains remains largely unexplored.
Approach:	They propose a reasoning model for interactive embodied tasks that synthesizes 9.3k coherent Observation-Thought-Action trajectories containing 64k ego-centric images and 90k diverse reasoning processes.
Outcome:	The proposed model outperforms existing visual reasoning models by +9%, 24%, and +13% on long-horizon tasks.

Copied to clipboard

Hui Wu, Chao Xu, Jianghui Wang, Ziqiong Liu, Dong Li, Yiwei Dai, Emad Barsoum

Responsible & Trustworthy NLP

Challenge:	Existing systems rely on a monolithic policy to execute subgoals across varying contexts, causing inconsistent outcomes and scaling only partially mitigates.
Approach:	They propose a memory-routed mixtureof-experts controller for Adaptive Minecraft Control that routes via a subgoal-indexed expert memory and regulates capacity through failure-triggered expert growth and redundancy-aware consolidation.
Outcome:	The proposed controller shows significant gains in adaptability, robustness, and execution consistency over strong baselines.

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router (2026.acl-long)

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Ruibin Yuan, Xueqi Cheng

T5Score: Discriminative Fine-tuning of Generative Evaluation Metrics (2023.findings-emnlp)

Challenge:	Current alignment approaches rely on refusal alignment to avoid harmful content . large language models are often overly cautious or overlook subtle harmful content.
Approach:	They propose a framework for fine-grained safe generation in Large Language Models that enables real-time, token-level harmfulness detection and redaction without loss in capability.
Outcome:	The proposed framework achieves over 90% in F1 score for detecting and redacting harmful content while preserving overall utility and informativeness of the model’s responses.

Copied to clipboard

Yiwei Qin, Weizhe Yuan, Graham Neubig, Pengfei Liu