Papers by Bo Peng

AT²PO: Agentic Turn-based Policy Optimization via Tree Search (2026.acl-long)

Challenge:	Quantity Maxims dictates that human speakers aim for optimal quantity of information during conversation.
Approach:	They propose to use heuristic path-finding to enable decoder-only LLMs to travel among multiple "Q-alternatives" and search for optimal quantity in coordination with a conversation goal.
Outcome:	The proposed techniques are based on heuristic path-finding and can be used to construct human-like, user-centered conversation agents.

Copied to clipboard

Zefang Zong, Dingwei Chen, Yang Li, Qi Yi, Bo Zhou, Chengming Li, BO Qian, Peng Chen, Jie Jiang

Information Retrieval

Challenge:	Recent advances in large language models (LLMs) have catalyzed the development of autonomous agents capable of executing complex, multi-turn tasks.
Approach:	They propose a framework for agentic reinforcement learning that integrates turn-level tree search with tree search to address key challenges.
Outcome:	The proposed framework addresses key challenges: limited exploration diversity, sparse credit assignment, and misaligned policy optimization.

Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment (2025.findings-acl)

Copied to clipboard

Hongda Sun, Jiaren Peng, Wenzhong Yang, Liang He, Bo Du, Rui Yan

RWKV: Reinventing RNNs for the Transformer Era (2023.findings-emnlp)

Challenge:	Medical dialogue systems (MDS) struggle to identify relevant medical knowledge and generate accurate responses.
Approach:	They propose a medical dialogue system that integrates knowledge refining and dynamic prompt adjustment to improve medical knowledge and accuracy.
Outcome:	The proposed system outperforms state-of-the-art systems in both generation quality and medical entity accuracy.

Copied to clipboard

Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Stella Biderman, Huanqi Cao, Xin Cheng, Michael Chung, Leon Derczynski, Xingjian Du, Matteo Grella, Kranthi Gv, Xuzheng He, Haowen Hou, Przemyslaw Kazienko, Jan Kocon, Jiaming Kong, Bartłomiej Koptyra, Hayden Lau, Jiaju Lin, Krishna Sri Ipsit Mantri, Ferdinand Mom, Atsushi Saito, Guangyu Song, Xiangru Tang, Johan Wind, Stanisław Woźniak, Zhenyuan Zhang, Qinghua Zhou, Jian Zhu, Rui-Jie Zhu

EmbodiedBERT: Cognitively Informed Metaphor Detection Incorporating Sensorimotor Information (2024.findings-emnlp)

Challenge:	recurrent neural networks struggle to match the performance of Transformers due to limitations in parallelization and scalability.
Approach:	They propose a model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs.
Outcome:	The proposed model performs on par with similarly sized RNNs, suggesting future work can leverage this architecture to create more efficient models.

Copied to clipboard

Yu Li, Bo Peng, Yu-Yin Hsu, Chu-Ren Huang

UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation (2024.acl-long)

Challenge:	Existing methods for metaphor detection rely on heuristics such as Metaphor Identification Procedure (MIP) and Selection Preference Violation (SPV).
Approach:	They propose a cognitively motivated module that leverages the cognitive information of embodiment that can be derived from word embeddings and explicitly models the process of sensorimotor change that has been demonstrated as essential for metaphor processing.
Outcome:	The proposed module can improve metaphor detection compared with the heuristic MIP that has been applied previously.

Copied to clipboard

Xun Liang, Shichao Song, Simin Niu, Zhiyu Li, Feiyu Xiong, Bo Tang, Yezhaohui Wang, Dawei He, Cheng Peng, Zhonghao Wang, Haiying Deng

Grafting Pre-trained Models for Multimodal Headline Generation (2022.emnlp-industry)

Challenge:	Large language models (LLMs) produce hallucinated text, compromising their practical utility in professional contexts.
Approach:	They have developed an unconstrained hallucination generation evaluation benchmark that contains hallucines generated by large language models with minimal restrictions.
Outcome:	The proposed benchmarks are based on a Chinese-language dataset that is lacking in the field.

Copied to clipboard

Lingfeng Qiao, Chen Wu, Ye Liu, Haoyuan Peng, Di Yin, Bo Ren

Multimodality

Challenge:	Existing approaches to generate video headlines with pre-trained language models are labor intensive and impractical.
Approach:	They propose to graft the encoder from the pre-trained video-language model on the generative pre-trainer model and propose a consensus fusion mechanism for the integration of different components.
Outcome:	The proposed model achieves strong results on a brand-new dataset collected from real-world applications.

Be Helpful but Don’t Talk too Much - Enhancing Helpfulness in Conversations through Relevance in Multi-Turn Emotional Support (2024.emnlp-main)

Copied to clipboard

Junlin Li, Bo Peng, Yu-Yin Hsu, Chu-Ren Huang

CELLO: Causal Evaluation of Large Vision-Language Models (2024.emnlp-main)

Challenge:	a helpful speaker should maintain an "effect-effort" tradeoff for a conversation to help and support . a study aimed to cultivate the awareness of "optimal relevance" into the cognitive process of conversation agents .
Approach:	They integrate the "Cognitive Relevance Principle" into emotional support agents . they found that the "relevance principle" is effective in generating human-like, helpful, harmless conversations .
Outcome:	The proposed method improves human-likedness and support in multi-turn conversations . the source code will be available at https://github.com/CN-Eyetk/VLESA-ORL.git .

Copied to clipboard

Meiqi Chen, Bo Peng, Yan Zhang, Chaochao Lu

Multimodality

Challenge:	Recent advances in large vision-language models have improved causal reasoning abilities . however, current models struggle with tasks like causal reasoning .
Approach:	They propose a fine-grained and unified definition of causality involving interactions between humans and objects.
Outcome:	The proposed model surpasses traditional commonsense causality by including explicit causal graphs . it also shows that current LVLMs can benefit from a causally inspired prompting strategy .

Rethinking Depression Prediction from a Fine-Grained Subscore Modeling Perspective via Multi-Task Learning (2026.acl-long)

Copied to clipboard

Zhenguang Wang, Bo Li, Wenhui Tan, Peng Cao, Yang Wang, Jia Duan, Fei Wang, Osmar Zaiane

Facilitating Cross-lingual Transfer of Empathy through Language-independent Latent Diffusion: A Case Study in Chinese (2025.findings-emnlp)

Challenge:	Existing methods for depression assessment rely on standardized ratings, but they are time-consuming and subject to inter-rater variability.
Approach:	They propose a fine-grained model for subscore prediction via multi-task learning that can be used to predict depression severity using multiple tasks.
Outcome:	The proposed model outperforms baselines and Qwen3-14B direct scoring on the public E-DAIC dataset and to a large-scale private clinical dataset.

Copied to clipboard

Junlin Li, Peng Bo, Yu-Yin Hsu

Multilinguality

Challenge:	Existing human empathy data are limited to English . a new study examines the pragmatic transferability of empathy across languages .
Approach:	a team of researchers integrate language-independent diffusion processes to facilitate the cross-lingual transfer of empathy.
Outcome:	The proposed method demonstrates that empathy can be transferred across languages without compromising linguistic naturalness.

HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States (2025.acl-long)

Copied to clipboard

Yilei Jiang, Xinyan Gao, Tianshuo Peng, Yingshui Tan, Xiaoyong Zhu, Bo Zheng, Xiangyu Yue

M³GQA: A Multi-Entity Multi-Hop Multi-Setting Graph Question Answering Benchmark (2025.acl-long)

Challenge:	Existing studies focus on posthoc alignment techniques, but the underlying safety mechanisms within LVLMs remain unexplored.
Approach:	They propose a tuning-free framework that leverages internal activations to enhance safety.
Outcome:	The proposed framework outperforms state-of-the-art methods in detecting jailbreak attacks against large vision-language models.

Copied to clipboard

Boci Peng, Yongchao Liu, Xiaohe Bo, Jiaxin Guo, Yun Zhu, Xuanbo Fan, Chuntao Hong, Yan Zhang

Responsible & Trustworthy NLP

Challenge:	GraphRAG systems have achieved remarkable progress in enhancing performance and reliability of large language models.
Approach:	They propose a GraphRAG benchmark focusing on multi-entity queries with six settings for comprehensive evaluation.
Outcome:	The proposed method can construct diverse data with semantically correct ground-truth reasoning paths.

A Self-training Framework for Automated Medical Report Generation (2023.emnlp-main)

Copied to clipboard

Siyuan Wang, Zheng Liu, Bo Peng

Multimodality

Challenge:	Medical report generation is an important medical artificial intelligence task.
Approach:	They propose a framework for medical report generation that exploits unlabeled medical images and a reference-free evaluation metric.
Outcome:	The proposed framework performs better than previous fully-supervised models trained on entire training data.

Automatic Scene-based Topic Channel Construction System for E-Commerce (2022.emnlp-industry)

Copied to clipboard

Peng Lin, Yanyan Zou, Lingfei Wu, Mian Ma, Zhuoye Ding, Bo Long

Information Extraction & Text Mining

Challenge:	Recent scene marketing has proved effective for offline shopping.
Approach:	They propose a novel product form, scene-based topic channel, which consists of a list of diverse products belonging to the same usage scenario and a topic title that describes the scenario with marketing words.
Outcome:	The proposed system can be automated and tested on a real-world e-commerce recommendation platform.

Planning with Diffusion Models for Target-Oriented Dialogue Systems (2025.acl-long)

Copied to clipboard

Hanwen Du, Bo Peng, Xia Ning

Emstremo: Adapting Emotional Support Response with Enhanced Emotion-Strategy Integrated Selection (2024.lrec-main)

Challenge:	Existing methods for directing conversations toward specific targets generate dialogue plans in a step-by-step sequential manner and suffer from compounding errors and myopic actions.
Approach:	They propose a framework that leverages diffusion models to enable non-sequential dialogue planning.
Outcome:	The proposed framework performs non-myopic lookahead exploration and optimizes action strategies over a long horizon through non-sequential dialogue planning.

Copied to clipboard

Junlin Li, Bo Peng, Yu-Yin Hsu

Natural Language Interfaces

Challenge:	Emstremo aims to achieve strategic control of emotional alignment by perceiving and responding to the user’s emotions.
Approach:	They propose to integrate strategies and emotions into a conversational emotional support agent called Emstremo that aims to achieve strategic control of emotional alignment by perceiving and responding to the user’s emotions.
Outcome:	Emstremo achieves strategic control of emotional alignment by perceiving and responding to the user’s emotions.

FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction (2023.acl-long)

Copied to clipboard

Tianshuo Peng, Zuchao Li, Lefei Zhang, Bo Du, Hai Zhao

Information Extraction & Text Mining

Challenge:	Existing Universal Information Extraction models rely heavily on span boundaries in data during training, which does not reflect the reality of span annotation challenges.
Approach:	They propose a framework that uses fuzzy spans to model various IE tasks . they propose generative Universal Information Extraction (UIE) to unify various ie tasks based on fuzzy span boundaries .
Outcome:	The proposed framework improves on a series of main IE tasks with small amounts of data and training epochs.

A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential (2024.findings-acl)

Copied to clipboard

Wei Tang, Yixin Cao, Jiahao Ying, Bo Wang, Yuyue Zhao, Yong Liao, Peng Zhou

Information Retrieval

Challenge:	Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models.
Approach:	They propose a "generate-then-read" pipeline to replace retrieval stage with generation from the LLM itself.
Outcome:	The proposed framework outperforms single models in the base and chat versions and addresses safety and helpfulness post-adaptation challenges.

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models (2026.findings-acl)

Copied to clipboard

Chejian Xu, Wei Ping, Peng Xu, Zihan Liu, Boxin Wang, Mohammad Shoeybi, Bo Li, Bryan Catanzaro

Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study (2023.emnlp-main)

Challenge:	Long-context capabilities are essential for document and video understanding, in-contact learning, and inference-time scaling.
Approach:	They propose an efficient training recipe for building ultra-long context LLMs from aligned instruct model, pushing the boundaries of context lengths from 128K to 1M, 2M, and 4M tokens.
Outcome:	The proposed model extends the context window while maintaining short context capabilities while maintaining the performance of the existing model.

Copied to clipboard

Boxin Wang, Wei Ping, Peng Xu, Lawrence McAfee, Zihan Liu, Mohammad Shoeybi, Yi Dong, Oleksii Kuchaiev, Bo Li, Chaowei Xiao, Anima Anandkumar, Bryan Catanzaro

Fine-grained Medical Vision-Language Representation Learning for Radiology Report Generation (2023.emnlp-main)

Challenge:	a recent study shows that retrieval-augmented LMs can improve text generation quality and accuracy.
Approach:	They propose a model that reproduces RETRO parameters while retrieving a text corpus . they find RETRO outperforms GPT on text generation with less repetition .
Outcome:	The proposed model outperforms standard retrieval-augmented GPT and retrieval augmented GTP on text generation and accuracy tasks.

Copied to clipboard

Siyuan Wang, Bo Peng, Yichao Liu, Qi Peng

Visual Data in NLP

Challenge:	Existing methods to learn medical vision-language representations by contrasting images with entire reports are not effective.
Approach:	They propose a phenotype-driven medical vision-language representation learning framework to bridge the gap between visual and textual modalities for improved text-oriented generation.
Outcome:	The proposed framework bridges the gap between visual and textual modalities for improved radiology report generation.

Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference Optimization (2026.findings-acl)

Copied to clipboard

Yurui Pan, Ke Xu, Bo Peng

TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models (2021.acl-long)

Challenge:	Existing algorithms for supervised fine-tuning and reinforcement learning from human feedback (RLHF) do not constrain how hidden states move from a user prompt to an answer.
Approach:	They propose a topology-enhanced alignment framework that regularizes these trajectories using 0-dimensional persistent homology.
Outcome:	The proposed framework regularizes semantic trajectory in hidden space using 0-dimensional persistent homology.

Copied to clipboard

Jie He, Bo Peng, Yi Liao, Qun Liu, Deyi Xiong

NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism (2024.acl-long)

Challenge:	Using pretrained language models, we propose an error-annotated dataset for text generation . we use carefully selected prompt words to guide GPT-2 to generate candidate sentences .
Approach:	They propose an error-annotated dataset with multiple benchmark tasks for text generation from pretrained language models.
Outcome:	The proposed dataset covers 24 types of errors according to common sense and linguistics.

Copied to clipboard

Miao Li, Ming-Bin Chen, Bo Tang, ShengbinHou ShengbinHou, Pengyu Wang, Haiying Deng, Zhiyu Li, Feiyu Xiong, Keming Mao, Cheng Peng, Yi Luo

A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement (2026.acl-long)

Challenge:	a novel evaluation framework assesses the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism.
Approach:	They propose to use a benchmark dataset to assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism.
Outcome:	The proposed evaluation framework is based on a dataset of 1,267 test samples in 24 news domains.

Copied to clipboard

Shengji Tang, Jianjian Cao, Weihao Lin, Jiale Hong, Bo Zhang, Shuyue Hu, Lei Bai, Tao Chen, Wanli Ouyang, Peng Ye

Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL (2025.emnlp-main)

Challenge:	Existing multi-LLM collaboration systems often encounter scalability challenges when integrating new LLMs and tasks.
Approach:	They propose a Scalable Multi-LLM Collaboration System to coordinate multiple open-source LLMs.
Outcome:	The proposed system outperforms prevailing closed-source LLMs on eight mainstream benchmarks on multiple tasks.

Copied to clipboard

Jie Shi, Xi Cao, Bo Xu, Jiaqing Liang, Yanghua Xiao, Jia Chen, Peng Wang, Wei Wang

Programming Languages in NLP

Challenge:	Existing Text-to-SQL research focuses on specific database systems, limiting adaptability to different dialects.
Approach:	They propose a framework that employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap.
Outcome:	The proposed framework outperforms existing methods that generate SQL queries directly.

Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation (2020.emnlp-main)

Copied to clipboard

Xiuyi Chen, Fandong Meng, Peng Li, Feilong Chen, Shuang Xu, Bo Xu, Jie Zhou

M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)

Challenge:	Existing knowledge-grounded dialogue models lack prior and posterior knowledge selection . prior selection module may not learn to select knowledge properly because of lack of posterior information .
Approach:	They propose a knowledge distillation-based training strategy to remove the exposure bias of knowledge selection.
Outcome:	The proposed model improves on two knowledge-grounded dialogue datasets.

Copied to clipboard

Jiaheng Liu, Ken Deng, Congnan Liu, Jian Yang, Shukai Liu, He Zhu, Peng Zhao, Linzheng Chai, Yanan Wu, JinKe JinKe, Ge Zhang, Zekun Moore Wang, Guoan Zhang, Yingshui Tan, Bangyu Xiang, Zhaoxiang Zhang, Wenbo Su, Bo Zheng

Programming Languages in NLP

Challenge:	Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities .
Approach:	They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models.
Outcome:	The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree.

Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models (2022.findings-emnlp)

Copied to clipboard

Qihuang Zhong, Liang Ding, Li Shen, Peng Mi, Juhua Liu, Bo Du, Dacheng Tao

SAPIENT: Mastering Multi-turn Conversational Recommendation with Strategic Planning and Monte Carlo Tree Search (2025.naacl-long)

Challenge:	Existing methods for fine-tuning pretrained language models suffer from poor generalization . however, they add a perturbation to each model parameter equally, which is sub-optimal .
Approach:	They propose a sharpness-aware minimization optimization procedure that introduces a Fisher mask to improve the efficiency of SAM.
Outcome:	The proposed method outperforms the vanilla sharpness-aware minimization method on GLUE and SuperGLUE benchmarks.

Copied to clipboard

Hanwen Du, Bo Peng, Xia Ning

JI2S: Joint Influence‐Aware Instruction Data Selection for Efficient Fine‐Tuning (2025.emnlp-main)

Challenge:	Existing methods train RL-based agents with greedy action selection or sampling strategy and suffer from suboptimal conversational planning.
Approach:	They propose a Monte Carlo Tree Search-based CRS framework called SAPIENT . it consists of a conversational agent and a communication planner .
Outcome:	The proposed framework outperforms the state-of-the-art methods on four benchmark datasets.

Copied to clipboard

Jingyu Wei, Bo Liu, Tianjiao Wan, Baoyun Peng, Xingkong Ma, Mengmeng Guo

Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning? (2025.acl-long)

Challenge:	Prior selection strategies score samples using generalpurpose LLMs, leveraging their strong language understanding but introducing inherent biases that misalign with the target model’s behavior and yield unstable downstream performance.
Approach:	They propose a framework that jointly models marginal and combinatorial influences within sample groups and evaluate them on Open LLM Benchmarks, MTBench, and GPT4–judged pairwise comparisons.
Outcome:	The proposed framework outperforms fulldataset training and strong baselines on Open LLM Benchmarks, MTBench, and GPT4–judged pairwise comparisons.

Copied to clipboard

Yancheng He, Shilong Li, Jiaheng Liu, Weixun Wang, Xingyuan Bu, Ge Zhang, Z.y. Peng, Zhaoxiang Zhang, Zhicheng Zheng, Wenbo Su, Bo Zheng