Papers by Libo Zhang

Python is Not Always the Best Choice: Embracing Multilingual Program of Thoughts (2024.emnlp-main)

Copied to clipboard

Xianzhen Luo, Qingfu Zhu, Zhiming Zhang, Libo Qin, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che

Challenge:	Program of Thoughts (PoT) is an approach characterized by its executable intermediate steps, which ensure the accuracy of the logical calculations in the reasoning process.
Approach:	They propose a task and model agnostic approach which harnesses strength and diversity from various languages to achieve better performance across all tasks.
Outcome:	The proposed approach outperforms Python Self-Consistency in almost all tasks and models and achieves comparable or superior performance on ChatGPT.

CSTree-SRI: Introspection-Driven Cognitive Semantic Tree for Multi-Turn Question Answering over Extra-Long Contexts (2025.acl-long)

Copied to clipboard

Zhaowen Wang, Xiang Wei, Kangshao Du, Yiting Zhang, Libo Qin, Yingjie Xia, Li Kuang

Question Answering

Challenge:	Large Language Models (LLMs) have achieved remarkable success in natural language processing (NLP), particularly in single-turn question answering (QA) on short-text.
Approach:	They propose a framework that captures logical correlations across chunks of ELC and maintains coherence of multi-turn Questions.
Outcome:	The proposed framework is able to capture logical correlations across chunks of ELC and maintain coherence of multi-turn Questions.

Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs (2026.acl-long)

Copied to clipboard

Libo Zhang, Zhaoning Zhang, null Hongwanyang, Peng Qiao, Dongsheng Li

Visual Data in NLP

Challenge:	Existing speculative decoding models face performance collapse due to key-value cache explosion and context window mismatches.
Approach:	They propose a framework that offloads visual computation to the target model by using hidden state reuse.
Outcome:	The proposed framework achieves an average speedup of 2.82x even with 25k visual tokens .

M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought (2024.acl-long)

Copied to clipboard

Qiguang Chen, Libo Qin, Jin Zhang, Zhi Chen, Xiao Xu, Wanxiang Che

Multimodality

Challenge:	MCoT requires models to leverage knowledge from both textual and visual modalities for step-by-step reasoning.
Approach:	They propose a benchmark to address the challenges of MCoT, and evaluate it using vision large language models.
Outcome:	The proposed benchmark addresses the above challenges and shows that current models still struggle to reason in M3CoT.

GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-Distribution Generalization Perspective (2023.findings-acl)

Copied to clipboard

Linyi Yang, Shuibai Zhang, Libo Qin, Yafu Li, Yidong Wang, Hanmeng Liu, Jindong Wang, Xing Xie, Yue Zhang

Robustness in NLP

Challenge:	Pre-trained language models (PLMs) have improved generalization performance but the out-of-distribution (OOD) generalization problem remains a challenge in many NLP tasks.
Approach:	They propose to create a benchmark for evaluating out-of-distribution (OOD) generalization in NLP models.
Outcome:	The proposed benchmarks highlight the importance of OOD robustness and provide insights on how to measure it and improve it.

Multi-Objective Forward Reasoning and Multi-Reward Backward Refinement for Product Review Summarization (2024.lrec-main)

Copied to clipboard

Libo Sun, Siyuan Wang, Meng Han, Ruofei Lai, Xinyu Zhang, Xuanjing Huang, Zhongyu Wei

Text Generation

Challenge:	Product review summarization aims to generate a concise summary based on product reviews . factual accuracy, aspect comprehensiveness, and content relevance are challenges .
Approach:	They propose an FB-Thinker framework to improve product review summarization ability . they propose two Chinese product review summary datasets for instruction-tuning and evaluation .
Outcome:	The proposed framework improves product review summarization with forward reasoning and backward refinement.

CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention (2025.acl-long)

Copied to clipboard

Zekai Ye, Qiming Li, Xiaocheng Feng, Libo Qin, Yichong Huang, Baohang Li, Kui Jiang, Yang Xiang, Zhirui Zhang, Yunfei Lu, Duyu Tang, Dandan Tu, Bing Qin

Reasoning

Challenge:	Large Vision-Language Models (LVLMs) have impressive multimodal abilities but remain prone to multilingual object hallucination.
Approach:	They propose a cross-lingual attention intervention method to mitigate multilingual object hallucination in LVLMs by aligning attention patterns.
Outcome:	The proposed method improves 13.56% (up to 30%) on the POPE and 21.75% on the hallucination subsets across languages.

Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog (2020.acl-main)

Copied to clipboard

Libo Qin, Xiao Xu, Wanxiang Che, Yue Zhang, Ting Liu

Dialogue Systems & Conversational Agents

Challenge:	Recent studies show remarkable success in end-to-end task-oriented dialog systems . however, most models rely on large training data, which is difficult to scalable for new domains with limited labeled data.
Approach:	They propose a shared-private network which exploits the relevance between the target domain and each domain.
Outcome:	The proposed model outperforms existing methods on multi-domain dialogue by 13.9% on average.

Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference (2025.emnlp-main)

Copied to clipboard

Libo Zhang, Zhaoning Zhang, null Xubaizhou, Rui Li, Zhiliang Tian, Songzhu Mei, Dongsheng Li

Green & Sustainable NLP

Challenge:	Large language models (LLMs) are demanding more memory and computational resources . however, these devices typically feature weaker GPUs and stronger CPUs .
Approach:	They propose a lossless inference acceleration method that leverages the characteristics of heterogeneous devices and the advantages of speculative decoding.
Outcome:	The proposed method achieves speedups ranging from 1.79 to 10.1 across different devices . it uses a draft model on the GPU to perform preliminary predictions, while a target model on CPU validates these outputs .

AI-Press: A Multi-Agent News Generating and Feedback Simulation System Powered by Large Language Models (2025.coling-demos)

Copied to clipboard

Xiawei Liu, Shiyue Yang, Xinnong Zhang, Haoyu Kuang, Libo Sun, Yihang Yang, Siming Chen, Xuanjing Huang, Zhongyu Wei

Semantic Text Processing

Challenge:	We introduce AI-Press, an automated news drafting and polishing system based on multi-agent collaboration and Retrieval-Augmented Generation.
Approach:	They introduce AI-Press, an automated news drafting and polishing system based on multi-agent collaboration and Retrieval-Augmented Generation.
Outcome:	The proposed system generates public responses considering demographic distributions.

A Structure-Aware Argument Encoder for Literature Discourse Analysis (2022.coling-1)

Copied to clipboard

Yinzi Li, Wei Chen, Zhongyu Wei, Yujun Huang, Chujun Wang, Siyuan Wang, Qi Zhang, Xuanjing Huang, Libo Wu

Semantic Text Processing

Challenge:	Existing research for argument representation learning treats tokens in sentences equally and ignores the implied structure information of argumentative context.
Approach:	They propose to separate tokens into two groups to capture structural information of arguments and to incorporate paragraph-level position information into the model.
Outcome:	The proposed model captures structural information of arguments and is able to identify arguments automatically.

Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information (2024.findings-emnlp)

Copied to clipboard

Yongheng Zhang, Qiguang Chen, Jingxuan Zhou, Peng Wang, Jiasheng Si, Jin Wang, Wenpeng Lu, Libo Qin

Reasoning

Challenge:	Chain-of-Thought (CoT) is a key technique for enhancing the performance of Large Language Models.
Approach:	They propose a framework that optimizes outputs by utilizing wrong information and multi-perspective verification.
Outcome:	The proposed framework surpasses all baselines on 8 datasets and 5 LLMs.

Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits (2025.coling-main)

Copied to clipboard

Bohan Li, Jiannan Guan, Longxu Dou, Yunlong Feng, Dingzirui Wang, Yang Xu, Enbo Wang, Qiguang Chen, Bichen Wang, Xiao Xu, Yimeng Zhang, Libo Qin, Yanyan Zhao, Qingfu Zhu, Wanxiang Che

Language Models

Challenge:	Existing data on MBTI personality detection are based on self-reported labels and fail to capture the full range of population personality traits.
Approach:	They construct a manually annotated MBTI personality detection dataset with soft labels under the guidance of psychologists and use them to identify the task.
Outcome:	The MBTIBench is the first manually annotated MBti personality detection dataset with soft labels under the guidance of psychologists.

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer (2025.findings-naacl)

Copied to clipboard

Pengzhou Cheng, Wei Du, Zongru Wu, Fengwei Zhang, Libo Chen, Zhuosheng Zhang, Gongshen Liu

Responsible & Trustworthy NLP

Challenge:	Existing attacks are classified into end-to-end and pre-training types based on the attack phase . Existing backdoor attacks are based upon perplexity, fine-pruning, and maxEntropy.
Approach:	They propose an entropy-based poisoning filter that mitigates backdoor attacks . they propose an invisible and universal task-agnostic backdoor attack via syntactic transfer .
Outcome:	The proposed attack can transfer backdoors to various downstream tasks while preserving pre-trained language models' pre-training capabilities.

End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions (2023.emnlp-main)

Copied to clipboard

Libo Qin, Wenbo Pan, Qiguang Chen, Lizi Liao, Zhou Yu, Yue Zhang, Wanxiang Che, Min Li

Dialogue Systems & Conversational Agents

Challenge:	End-to-end task-oriented dialogue (EToD) can generate responses in an end-to end fashion without modular training, which attracts escalating popularity.
Approach:	They present a systematic review of EToD and propose a unified perspective to summarize existing approaches and recent trends.
Outcome:	The proposed approaches can generate responses in an end-to-end fashion without modular training, which attracts escalating popularity.

MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System (2023.findings-acl)

Copied to clipboard

Libo Qin, Shijue Huang, Qiguang Chen, Chenran Cai, Yudi Zhang, Bin Liang, Wanxiang Che, Ruifeng Xu

Multimodality

Challenge:	Existing benchmarks for multi-modal sarcasm detection have some shortcomings . a new framework can leverage multi-grained cues from multiple perspectives for multimodal detection .
Approach:	They propose a correction dataset that removes spurious cues and re-annotates the unreasonable samples.
Outcome:	The proposed framework outperforms the existing benchmarks in multi-modal sarcasm detection.

MAGNET: Towards Adaptive GUI Agents with Memory-Driven Knowledge Evolution (2026.acl-long)

Copied to clipboard

Libo Sun, Jiwen Zhang, Siyuan Wang, Zhongyu Wei

Challenge:	Mobile GUI agents powered by large foundation models can perform tasks autonomously, but frequent updates that alter UI appearance and reorganize workflows cause agents trained on historical data to fail.
Approach:	They propose a memory-driven adaptive agent framework with stationary memory that links visual features to stable functional semantics and procedural memory that captures stable task intents across varying workflows.
Outcome:	The proposed framework improves performance over memory-augmented baselines and offline benchmarks on AndroidWorld.

CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models (2025.acl-long)

Copied to clipboard

Yongheng Zhang, Xu Liu, Ruoxi Zhou, Qiguang Chen, Hao Fei, Wenpeng Lu, Libo Qin

Reasoning

Challenge:	Existing studies on hallucinations in large language models are limited to a single scenario, either cross-lingual or cross-modal.
Approach:	They propose a joint Cross-lingual and Cross-modal hallucinations benchmark to fill this gap . they incorporate cross-lingual, cross-modal scenarios to assess hallucinic capabilities .
Outcome:	The proposed benchmark incorporates both cross-lingual and cross-modal hallucination scenarios to assess the cross-linguistic and crossmodal capabilities of LLMs.

Extractive Medical Entity Disambiguation with Memory Mechanism and Memorized Entity Information (2024.findings-emnlp)

Copied to clipboard

Guobiao Zhang, Xueping Peng, Tao Shen, Guodong Long, Jiasheng Si, Libo Qin, Wenpeng Lu

Challenge:	Existing methods focus on local optimal while ignoring sole-mention disambiguation boosted by richer context from other mentions’ disambiguating processes.
Approach:	They propose an approach to extracting medical entity disambiguation using memory mechanism and memorized entity information (M3E) they use a memory mechanism module that performs memory caching, retrieval, fusion and cross-network residual to aid the disambiguations of remaining mentions.
Outcome:	The proposed method outperforms state-of-the-art methods on two benchmark datasets.

Boundary Matters: Leveraging Structured Text Plots for Long Text Outline Generation (2025.findings-emnlp)

Copied to clipboard

Yuanchi Ma, Jiamou Liu, Hui He, Libo Zhang, Haoyuan Li, Zhendong Niu

Challenge:	Existing methods for generating readable outlines are inability to segment long texts .
Approach:	They propose an unsupervised framework to guide large language model outline generation . framework ensures each structured plot encapsulates complete causality by accurately identifying plot boundaries.
Outcome:	The proposed framework ensures that each structured plot encapsulates complete causality by accurately identifying plot boundaries.

AutoCAP: Towards Automatic Cross-lingual Alignment Planning for Zero-shot Chain-of-Thought (2024.findings-acl)

Copied to clipboard

Yongheng Zhang, Qiguang Chen, Min Li, Wanxiang Che, Libo Qin

Low-Resource NLP

Challenge:	Existing approaches to cross-lingual chain-of-thought integrate reasoning knowledge from different languages, but they still rely on manual language specification and weight allocation.
Approach:	They propose an automatic cross-lingual alignment planning framework that integrates reasoning knowledge from different languages.
Outcome:	The proposed framework surpasses existing methods that require manual effort to integrate languages.

CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning (2025.acl-long)

Copied to clipboard

Yangfan Ye, Xiaocheng Feng, Zekun Yuan, Xiachong Feng, Libo Qin, Lei Huang, Weitao Ma, Yichong Huang, Zhirui Zhang, Yunfei Lu, Xiaohui Yan, Duyu Tang, Dandan Tu, Bing Qin

Multilinguality

Challenge:	Existing fine-tuning approaches that focus on English-centric training corpora often introduce implicit cross-lingual alignment, overlooking the potential for more profound, latent-level cross-linguistic interactions.
Approach:	They propose a multilingual fine-tuning paradigm that explicitly establishes a cross-lingual connection mechanism at the latent level.
Outcome:	The proposed model outperforms vanilla SFT and offers a strong latent-level alternative to data-level augmentation methods.

A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)

Copied to clipboard

Keke Lian, Wang Bin, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Quan Jiazheng, Yilu Zhong, Chenhao He, Chen Zichuan, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui LI, Dong Zhang

Programming Languages in NLP

Challenge:	Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows .
Approach:	They propose a repository-level evaluation benchmark to assess security of AI-generated code.
Outcome:	The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation.

Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework (2026.acl-long)

Copied to clipboard

Chenyuan Zhang, Qiguang Chen, Xie Chen, Zhuotao Tian, Bowen Xing, Meishan Zhang, Libo Qin, Baotian Hu, Min Zhang

Multilinguality

Challenge:	Existing methods for cross-lingual chain-of-thought (XCoT) with self-consistency are costly due to extensive sampling of full trajectories across languages.
Approach:	They propose a cross-lingual chain-of-thought framework that minimizes redundancy in token usage and latency.
Outcome:	Experiments on polymath show that UL-XCoT reduces decoding token costs and latency by 50% . UL XCot also aggregates remaining high-quality reasoning paths via voting .