Papers by Xiaobo Zhang
LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment (2026.findings-acl)
Copied to clipboard
Shipeng Li, Zhiqin Yang, Shikun Li, Xiaobo Xia, Hengyu Liu, Xinghua Zhang, Gaode Chen, Dong Fang, Ying Tai, Zhe Peng
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) is a key technique for enhancing LLMs’ reasoning abilities, yet its data inefficiency remains a major bottleneck. |
| Approach: | They propose a gradient-alignment-based method which intelligently selects the learnable and representative training reasoning data for RLVR post-training. |
| Outcome: | Experiments on five reasoning benchmarks show that the proposed method significantly reduces training data requirements while improving performance. |
Dynamic and Efficient Inference for Text Generation via BERT Family (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve performance of pre-trained language models are limited due to large-scale parameters and the universal autoregressive decoding paradigm. |
| Approach: | They propose a novel fine-tuning method which can make a single pre-trained model support Dynamic and Efficient infERence and achieve an adaptive trade-off between model performance and latency. |
| Outcome: | The proposed method achieves higher BLEU scores than the strong autoregressive Transformer model on translation tasks with 3 12 times speedup and faster inference speed compared with the BART model on four GLGE benchmark tasks. |
MMA: Cross-Domain Knowledge Integration via Mixture of Multi-Domain Agents (2025.findings-emnlp)
Copied to clipboard
| Challenge: | achieving synergistic improvements between generalization and domain specialization remains a challenge in pre-training and post-training. |
| Approach: | They propose a test-time cross-domain knowledge integration method that integrates general-purpose and domain-specific models to enhance their performance on complex, domainspecific tasks. |
| Outcome: | The proposed method combines the outputs of general-purpose and domain-specific models to improve their performance on complex, domainspecific tasks. |
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning (2026.acl-long)
Copied to clipboard
Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Xiangyu Zhang, Heung-Yeung Shum
| Challenge: | Parallel Coordinated Reasoning (PaCoRe) overcomes a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window. |
| Approach: | They propose a training-and-inference framework to overcome a central limitation of language models: their inability to scale test-time compute (TTC) under a fixed context window. |
| Outcome: | The proposed model scales to multi-million-token effective TTC without exceeding context limits. |
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct (2025.findings-acl)
Copied to clipboard
Run Luo, Haonan Zhang, Longze Chen, Ting-En Lin, Xiong Liu, Yuchuan Wu, Min Yang, Yongbin Li, Minzheng Wang, Pengpeng Zeng, Lianli Gao, Heng Tao Shen, Yunshui Li, Hamid Alinejad-Rokny, Xiaobo Xia, Jingkuan Song, Fei Huang
| Challenge: | a new framework for image-text instruction data evolution improves MLLM performance . lack of high-quality instruction data remains a major bottleneck in ML modeling . |
| Approach: | They propose a multimodal instruction data evolution framework that iteratively enhances data quality through fine-grained perception, cognitive reasoning, and interaction evolution. |
| Outcome: | The proposed approach improves MLLM performance in nine vision-language tasks while using significantly less data. |
From What to Why: Improving Relation Extraction with Rationale Graph (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing neural relation extraction models are limited by entity type and textual context. |
| Approach: | They propose a novel RAtionale Graph to organize co-occurrence constraints among entity types, triggers and relations in a holistic graph view. |
| Outcome: | The proposed method outperforms baselines significantly and achieves state-of-the-art performance on document-level and sentence-level RE benchmarks. |
Recontextualizing Revitalization: A Mixed Media Approach to Reviving the Nüshu Language (2025.emnlp-main)
Copied to clipboard
| Challenge: | Nüshu is an endangered language from Jiangyong County, Hunan, China, and the world’s only known writing system created and used exclusively by women. |
| Approach: | They propose to use NüshuStrokes to record all 397 Unicode Nü Shu characters in sequential handwriting by an expert calligrapher. |
| Outcome: | Evaluating five state-of-the-art Chinese Optical Character Recognition systems on NüshuVision lowers CER to 0.67, a modest but meaningful improvement over previous datasets. |
DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward (2026.acl-long)
Copied to clipboard
Xiaobo Liang, Wanfu Wang, Qipeng Huang, Yuyang Ding, Zecheng Tang, Yixin Ji, Qianben Chen, Zhe Zhao, Kehai Chen, Juntao Li, Min Zhang
| Challenge: | Existing preference-based reward modeling methods face a recursive dependency where each verifier requires a meta-verifier, leading to continuous and costly dependence on human annotation. |
| Approach: | They propose a dual RM that couples discriminative and generative reward models under a non-parametric meta-reward. |
| Outcome: | The proposed model achieves strong performance across major preference benchmarks and even when trained exclusively on language modality, it exhibits robust cross-modal transfer on Omni-RewardBench. |
Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve the mathematical reasoning capabilities of Large Language Models (LLMs) are limited due to the proprietary nature of the data. |
| Approach: | They propose a data synthesis method that generates large-scale mathematical reasoning datasets using lightweight 7B-scale models. |
| Outcome: | The proposed method outperforms existing open-source datasets in both in-domain and out-of-domain evaluations and shows improvements in code reasoning tasks. |
Generative Reward Modeling via Synthetic Criteria Preference Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Generative Reward Models (GenRMs) leverage synthesized Chains of Thought (CoT) but this approach introduces risks of overoptimization due to the inability to guarantee the correctness of the CoTs. |
| Approach: | They propose a criteria-based preference tree for GenRMs that uses chain of thought to generate reasoning . they show that synthesized data can be learned using a long CoT format . |
| Outcome: | The proposed model shows significant improvements over baselines on multiple human preference benchmarks. |
One-Shot Learning as Instruction Data Prospector for Large Language Models (2024.acl-long)
Copied to clipboard
Yunshui Li, Binyuan Hui, Xiaobo Xia, Jiaxi Yang, Min Yang, Lei Zhang, Shuzheng Si, Ling-Hao Chen, Junhao Liu, Tongliang Liu, Fei Huang, Yongbin Li
| Challenge: | Contemporary practices in instruction tuning often hinge on enlarging data scaling without a clear strategy for ensuring data quality. |
| Approach: | They propose a method that leverages one-shot learning to discern and select high-quality instruction data from extensive datasets. |
| Outcome: | Nuggets outperforms existing methods on MT-Bench and Alpaca-Eval benchmarks. |
A Contrastive Framework for Learning Sentence Representations from Pairwise and Triple-wise Perspective in Angular Space (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning sentence representations focus on constitution of positive and negative representation pairs and do not focus on training objective. |
| Approach: | They propose a new method to learn sentence representations using BERT-like pre-trained models . they use a pairwise discriminating power and a model to model the entailment relation of triplet sentences . |
| Outcome: | The proposed method outperforms the previous state-of-the-art on diverse sentence related tasks. |
JANUS: Joint Autoregressive and Non-autoregressive Training with Auxiliary Loss for Sequence Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to train autoregressive and non-autoregressive models only consider relevance of model parameters, ignoring correlations between the two manners. |
| Approach: | They propose a joint autoregressive and non-autoregressive training method using aUxiliary losS to enhance the model performance in both AR and NAR manners simultaneously. |
| Outcome: | The proposed method improves the model performance in both AR and NAR manners and reduces the inference latency. |
RoBGuard: Enhancing LLMs to Assess Risk of Bias in Clinical Trial Documents (2025.coling-main)
Copied to clipboard
Changkai Ji, Bowen Zhao, Zhuoyao Wang, Yingwen Wang, Yuejie Zhang, Ying Cheng, Rui Feng, Xiaobo Zhang
| Challenge: | Existing approaches to assess the risk of bias in RCTs focus on manually crafted prompts and a restricted set of simple questions, limiting their accuracy and generalizability. |
| Approach: | They propose a framework for enhancing Large Language Models to assess the risk of bias in RCTs by reformulation, document parsing and multi-expert collaboration. |
| Outcome: | The proposed framework outperforms existing methods on the RoB-Item and RoB domains. |
Dunhuang-Bench: How Well Do MLLMs Understand Cultural Heritage? (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Multimodal Large Language Models (MLLMs) have led to extensive evaluations on Chinese cultural benchmarks. |
| Approach: | They construct a large-scale benchmark comprising 486 images and 22,970 QA pairs to evaluate MLLMs' cultural understanding. |
| Outcome: | The proposed benchmark incorporates three task formats to evaluate MLLMs’ cultural understanding: Question Answering with Text Description, Multi-turn Dialogue, and Question Answers with Choices. |
Document-level Relation Extraction with Dual-tier Heterogeneous Graph (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods focus on extracting relations from single sentence . document-level relation extraction requires a comprehension of the whole document . |
| Approach: | They propose a graph-based model with Dual-tier Heterogeneous Graph (DHG) for document-level relation extraction. |
| Outcome: | The proposed model achieves state-of-the-art performance on two widely used datasets. |
GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labeling (2025.findings-acl)
Copied to clipboard
Hao Fang, Yuejie Zhang, Rui Feng, Yingwen Wang, Qing Wang, Wen He, Xiaobo Zhang, Tao Zhang, Shang Gao
| Challenge: | Document-level relation extraction (DocRE) solves problems of document quality . number of entities and entity-pair relations increases, causing incomplete annotations . |
| Approach: | a framework that reduces the problem space using a graph-enhanced Transformer-based model is proposed . GLiM leverages large language models for reasoning to reduce the problem-space . |
| Outcome: | GLiM boosts average recall and F1 scores on biomedical datasets . compared with existing models, GLim outperforms existing models on biomedicine benchmarks compared to existing models . |
Tool learning via Inference-time Scaling and Cycle Verifier (2025.findings-acl)
Copied to clipboard
| Challenge: | In inference-time scaling, Chain-of-Thought (CoT) data is scarce or even unavailable. |
| Approach: | They propose a method which establishes an inference cycle to synthesize user queries and CoT data. |
| Outcome: | The proposed method achieves a 75.4% pass rate and a 79.6% win rate using small models in StableToolBench. |
Unlocking Recursive Thinking of LLMs: Alignment via Refinement (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for recursive reasoning are limited due to lack of expert-curated data. |
| Approach: | They propose a method that unlocks the potential of Large Language Models for recursive reasoning through long-form Chain of Thought. |
| Outcome: | The proposed method outperforms preference optimization methods on the openAI o1-series models by 20% on 3k synthetic samples. |
Large Language Models are Complex Table Parsers (2023.emnlp-main)
Copied to clipboard
| Challenge: | Extensive experiments and results on Complex Table QA datasets, i.e., the open-domain dataset HiTAB and the aviation domain dataset AIT-QA show that our approach significantly outperforms previous work on both datasets. |
| Approach: | They propose to incorporate Generative Pre-trained Transformer 3.5 to address the specific challenges posed by Complex Table QA by reconstructing tables into tuples and using prompt templates to create dialogues. |
| Outcome: | The proposed approach outperforms previous work on complex table parsing datasets and leads to state-of-the-art (SOTA) performance. |
Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection (2026.acl-long)
Copied to clipboard
Linxuan Du, Guangquan Xue, Xiaobo Liang, Qipeng Huang, Yuyang Ding, Xinyu Shi, Zhang Yijun, Ji Qi, Wenpeng Zhu, Juntao Li, Min Zhang
| Challenge: | Existing methods for multi-turn self-reflection are limited by the Echo Trap problem . the model is limited by its inherent capabilities and repeats earlier reflections to preserve reward signals . |
| Approach: | They propose a tree-structured extension of GRPO for multi-turn self-reflection which enables more accurate advantage estimation. |
| Outcome: | The proposed method mitigates behavior collapse and improves performance across benchmarks. |
From Awareness to Adaptability: Enhancing Tool Utilization for Scientific Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches enhance reasoning through Chain-of-Thought, Program-ofThough, and Tool-Integration. |
| Approach: | They propose a tool-awareness training method that leverages both forward and backward data generation strategies to strengthen the model’s conscious and selective tool utilization in multi-step reasoning tasks. |
| Outcome: | The proposed method improves the model's tool utilization capabilities, including proactivity and execution success rates. |
Cross-Domain NER using Cross-Domain Language Modeling (P19-1)
Copied to clipboard
| Challenge: | Existing methods for named entity recognition (NER) use labeled data for both source and target domains. |
| Approach: | They propose to use language modeling as a bridge between NER domains to perform cross-domain and cross-task knowledge transfer. |
| Outcome: | The proposed method extracts domain differences from cross-domain LM contrast, allowing unsupervised domain adaptation while giving state-of-the-art results among supervised domain adapters. |
Open-ended Long Text Generation via Masked Language Modeling (2023.acl-long)
Copied to clipboard
| Challenge: | Pre-trained autoregressive language models have dominated OPen-ended Long Text Generation (Open-LTG) however, the low inference efficiency of AR impedes their usability. |
| Approach: | They propose a representative iterative non-autoregressive (NAR) decoding strategy to improve inference efficiency for Open-LTG. |
| Outcome: | The proposed model can generate short text and collapse for long text modeling. |