Papers by Bo An

Removing Prompt-template Bias in Reinforcement Learning from Human Feedback (2025.findings-acl)

Copied to clipboard

Chaojie Wang, Haonan Shi, Long Tian, Bo An, Shuicheng Yan

Challenge:	Reinforcement Learning from Human Feedback (RLHF) has shown promise for enhancing pre-trained large language models to generate responses that align with human preferences and societal values.
Approach:	They propose a method to estimate prompt-template bias term during reward modeling and use it to calibrate reward scores.
Outcome:	The proposed method can be flexibly combined with existing algorithms of removing length bias, leading to a further improvement in the aspect of enhancing the quality of generated responses.

Enhancing Neural Models with Vulnerability via Adversarial Attack (2020.coling-main)

Copied to clipboard

Rong Zhang, Qifei Zhou, Bo An, Weiping Li, Tong Mo, Bo Wu

Robustness in NLP

Challenge:	Existing work on adversarial attack to improve performance of NLSM tasks has not been done.
Approach:	They propose a general two-stage training framework to enhance neural models with Vulnerability via adversarial attack.
Outcome:	The proposed framework improves neural models with Vulnerability via adversarial attack on NLSM datasets.

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification (2026.acl-long)

Copied to clipboard

Penghui Yang, Cunxiao Du, Fengzhuo Zhang, Haonan Wang, Tianyu Pang, Chao Du, Bo An

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) can process extremely long contexts, requiring efficient inference over extended inputs.
Approach:	They propose a model that uses a constant-sized key-value cache to train long-context models.
Outcome:	Experimental results show that LongSpec achieves 3.26x speedup over strong Flash Attention baselines and 2.34x wall clock time on four math reasoning tasks.

Musical Score Understanding Benchmark: Evaluating Large Language Models’ Comprehension of Complete Musical Scores (2026.acl-long)

Copied to clipboard

Congren Dai, Yue Yang, Krinos Li, Huichi Zhou, Shijie Liang, Zhang Bo, Enyang Liu, Ge Jin, Hongran An, Haosen Zhang, Peiyuan Jing, KinHei Lee, Zhenxuan Zhang, Xiaobing Li, Maosong Sun

Language Models

Challenge:	Existing benchmarks for musical score understanding are narrow in scope, focusing on isolated fragments, short excerpts, or multiple-choice formulations, rather than supporting holistic reasoning over entire scores.
Approach:	They propose a benchmark for score-level musical understanding across textual and visual modalities.
Outcome:	The musical score understanding benchmark contains 1,800 question-answer pairs from works by Bach, Beethoven, Chopin, Debussy, and others.

Semi-Supervised Lexicon Learning for Wide-Coverage Semantic Parsing (C18-1)

Copied to clipboard

Bo Chen, Bo An, Le Sun, Xianpei Han

Multimodality

Challenge:	Semantic parsers rely on accurate and high-coverage lexicons, but they often use annotated logical forms to learn the lexic.
Approach:	They propose a semi-supervised learning framework that makes use of large text corpora and lexical resources.
Outcome:	The proposed framework improves on two benchmarks: Webquestions and Free917.

Model-Free Context-Aware Word Composition (C18-1)

Copied to clipboard

Bo An, Xianpei Han, Le Sun

Semantic Text Processing

Challenge:	Word composition models do not take ambiguity of words and context into consideration for learning representations, and thus suffer from the inaccurate representation of semantics.
Approach:	They propose a model-free context-aware word composition model which takes the latent semantic information as global context for learning representations.
Outcome:	The proposed model improves on existing composition models at different granularities and shows that it can be used to learn semantics.

C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs (2026.findings-acl)

Copied to clipboard

Xuan Feng, Bo An, Tianlong Gu, Liang Chang, Fengrui Hao, Peipeng Yu, Shuai Zhao

Responsible & Trustworthy NLP

Challenge:	Existing approaches to solve large language models address stereotypical and structural biases in isolation . however, prior paradigms address these in isolation, often at the expense of exacerbating the other .
Approach:	They propose a framework to tackle latent spurious feature correlations within input that drive erroneous reasoning shortcuts.
Outcome:	The proposed framework mitigates stereotypical and structural biases while preserving robust general reasoning capabilities.

AgentOCR: Reimagining Agent History via Optical Self-Compression (2026.acl-long)

Copied to clipboard

Lang Feng, Fuchao Yang, Feng Chen, Xin Cheng, Haiyang Xu, Zhenglin Wan, Ming Yan, Bo An

Visual Data in NLP

Challenge:	Recent advances in large language models (LLMs) have enabled agentic systems trained with reinforcement learning over multi-turn interaction, but practical deployment is bottlenecked by rapidly growing textual histories that inflate token and memory costs.
Approach:	They propose a framework that represents the accumulated observation-action history as a compact rendered image.
Outcome:	The proposed framework preserves over 95% of text-based agent performance while significantly reducing token consumption (>50%), yielding consistent token and memory efficiency.

Skill-Based Few-Shot Selection for In-Context Learning (2023.emnlp-main)

Copied to clipboard

Shengnan An, Bo Zhou, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Weizhu Chen, Jian-Guang Lou

Semantic Text Processing

Challenge:	Existing methods based on pre-trained embeddings can be easily biased by surface features that are not important for the target task.
Approach:	They propose a skill-based few-shot selection method for in-context learning . it generates skill-specific descriptions for each test case and candidate example .
Outcome:	The proposed method significantly outperforms existing methods in five cross-domain semantic parsing datasets and six backbone models.

EUSP: An Easy-to-Use Semantic Parsing PlatForm (D19-3)

Copied to clipboard

Bo An, Chen Bo, Xianpei Han, Le Sun

Semantic Text Processing

Challenge:	Semantic parsing aims to map natural language utterances into structured meaning representations.
Approach:	They propose a modular platform that allows developers to build semantic parser from scratch.
Outcome:	The proposed platform achieves competitive performance on semantic parsing task and improves performance of a business search engine.

SeDev: Structured Semantic Exploration for LLM-Driven Code Generation (2026.acl-long)

Copied to clipboard

Ronghui Yang, Jie Liu, Jiajie Zeng, Jiexin Wang, Jiuchuan Jiang, Bo An, Yi Cai, Mengchen Zhao

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities in automating code generation, but they suffer from insufficient exploration of the vast solution space.
Approach:	They propose a large-scale LLM-driven code generation framework that efficiently finds high-quality solutions in only a few iterations.
Outcome:	The proposed framework outperforms baselines while maintaining reasonable time and computational costs.

Accurate Text-Enhanced Knowledge Graph Representation Learning (N18-1)

Copied to clipboard

Bo An, Bo Chen, Xianpei Han, Le Sun

Semantic Text Processing

Challenge:	Existing representation learning methods for knowledge graph representation do not consider the ambiguity of relations and entities.
Approach:	They propose a text-enhanced knowledge graph representation learning method which exploits the entity descriptions and triple-specific relation mention to enhance representations.
Outcome:	The proposed method outperforms existing representation learning models on link prediction and triple classification tasks and significantly outperformed existing models.