Papers by Xiaoyang Wang

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026.acl-long)

Challenge:	Human preference judgments are important in large language models to produce outputs that align with human values.
Approach:	They conduct an in-depth examination of pairwise human judgments released by OpenAI . they find that most favored factors vary across tasks and genres .
Outcome:	The proposed model reveals that most favored factors vary across tasks and genres . the findings have implications on the construction of balanced datasets in human preference evaluations - crucial step in shaping behavior of future LLMs.

Copied to clipboard

Zheng Liu, Honglin Lin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, Zhuoshi Pan, Xiaoran Shang, Conghui He, Bin Cui, Wentao Zhang, Lijun Wu

Generating User-Engaging News Headlines (2023.acl-long)

Challenge:	Existing open-source vision language models lack high-quality training data for chart reasoning . current models are simplistic and repetitive, while associated QA pairs are prone to hallucinations .
Approach:	They propose a framework to synthesize complex charts and reliable reasoning data from scratch.
Outcome:	Experimental results show that ChartVerse-8B surpasses existing models in QA and difficulty . lack of high-quality training data hampers development of open-source models .

Copied to clipboard

Pengshan Cai, Kaiqiang Song, Sangwoo Cho, Hongwei Wang, Xiaoyang Wang, Hong Yu, Fei Liu, Dong Yu

DeFine: Decision-Making with Analogical Reasoning over Factor Profiles (2025.findings-acl)

Challenge:	Personalized news recommendation systems present the same headline to all users, making it difficult for them to understand the connection between their interests and the recommended article.
Approach:	They propose a framework that incorporates user profiling to generate personalized headlines and a combination of automated and human evaluation methods to determine user preference for personalized headline generation.
Outcome:	The proposed framework can generate personalized headlines that meet the needs of a diverse audience.

Copied to clipboard

Yebowen Hu, Xiaoyang Wang, Wenlin Yao, Yiming Lu, Daoan Zhang, Hassan Foroosh, Dong Yu, Fei Liu

Reasoning

Challenge:	Large language models are ideal for decision-making, but they can be difficult to process when they are verbose and include repetition, hedging, and vagueness.
Approach:	They propose a framework that constructs probabilistic factor profiles from complex scenarios and integrates them with analogical reasoning to guide LLMs in making decisions in new situations.
Outcome:	The proposed framework separates the tasks of quantifying uncertainty and incorporating it into LLM decision-making.

Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints (2020.acl-main)

Copied to clipboard

Zhenyi Wang, Xiaoyang Wang, Bang An, Dong Yu, Changyou Chen

RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models (2025.findings-acl)

Challenge:	Existing methods for text generation ignore faithfulness between generated text and table . current methods ignore faithfulity, leading to generated information that goes beyond table content .
Approach:	They propose a Transformer-based generation framework to enforce faithfulness between generated text and table . they propose metric to evaluate faithfulness and automatic metric for automatic generating .
Outcome:	The proposed framework outperforms state-of-the-art methods in automatic evaluations and human evaluations.

Copied to clipboard

Junjie Li, Nan Zhang, Xiaoyang Qu, Kai Lu, Guokuan Li, Jiguang Wan, Jianzong Wang

Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination (2022.emnlp-main)

Challenge:	Object navigation is a fundamental task in embodied artificial intelligence.
Approach:	They propose a region-aware Termination-Enhanced method that incorporates visual language models and exploration rates to enable efficient termination.
Outcome:	The proposed method achieves a success rate of 67.8% and an SPL of 31.3% on the HM3D dataset.

Copied to clipboard

Yue Yang, Wenlin Yao, Hongming Zhang, Xiaoyang Wang, Dong Yu, Jianshu Chen

MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation (2026.acl-long)

Challenge:	Large-scale pretrained language models suffer from reporting bias, describing the lack of explicit commonsense knowledge in written text.
Approach:	They propose to endow language models with visual imagination capabilities by recalling existing images and synthesizing nonexistent images via text-to-image generation.
Outcome:	The proposed model improves the performance of existing language models across a diverse set of language tasks.

Copied to clipboard

Dawei Wang, Di Zhao, Xinyuan Liu, Marci Chi Ma, Xiaoyang Liu, Chengming Zhou, Gary Ushaw, Richard Davison

Robustness in NLP

Challenge:	Embodied AI systems are open, where agents may leave or enter mid-task due to hardware failures or task-related errors.
Approach:	They propose a framework that reformulates credit assignment as a rank aggregation problem using contribution-based pairwise comparisons among agents generated by large multimodal models.
Outcome:	The proposed framework can guide agents toward effective cooperation in complex tasks of different types.

Tracing the Light of Thought: A Probabilistic Self- and Cross-Consistency Verification Mechanism Improving Mathematical Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Xiaoyang Liu, Dawei Wang, Tian Li, Huizhi Liang, Gary Ushaw, Richard Davison

Reasoning

Challenge:	Existing methods for evaluating reasoning paths are not efficient, but they are prone to errors.
Approach:	They propose a probabilistic self- and cross-consistency framework for mathematical reasoning that employs an accept-reject mechanism to encourage high-quality reasoning paths.
Outcome:	The proposed framework improves on 9 LLMs across 4 challenging benchmarks.

From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning (2024.naacl-long)

Copied to clipboard

Xuansheng Wu, Wenlin Yao, Jianshu Chen, Xiaoman Pan, Xiaoyang Wang, Ninghao Liu, Dong Yu

SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs (2024.acl-long)

Challenge:	Large Language Models (LLMs) have achieved remarkable success in aligning with user intentions.
Approach:	They develop local and global explanation methods and a feed-forward-based method for input-output attribution to investigate the impact of instruction tuning on user intentions.
Outcome:	The proposed method compares explanations from pre-trained and instruction-tuned models . it empowers LLMs to recognize the instruction parts of user prompts, it encourages response generation .

Copied to clipboard

Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Hassan Foroosh, Dong Yu, Fei Liu

Numerical Reasoning

Challenge:	Large language models can handle text and data, but blending text and numerical data presents significant challenges.
Approach:	They propose four tasks to evaluate the numerical reasoning and information fusion capabilities of large language models in sports data analytics.
Outcome:	The proposed tasks evaluate the numerical reasoning and information fusion capabilities of large language models in sports data analytics.

OASum: Large-Scale Open Domain Aspect-based Summarization (2023.findings-acl)

Copied to clipboard

Xianjun Yang, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Xiaoman Pan, Linda Petzold, Dong Yu

Summarization

Challenge:	Existing generic summarization methods generate only one summary for all different requests which is not optimal for diverse demands.
Approach:	They use crowd-sourced knowledge on Wikipedia to create a large-scale open-domain aspect-based summarization dataset with 1 million different aspects on 2 million Wikipedia pages.
Outcome:	The proposed model can generate diverse aspect-based summarizations on Wikipedia with zero/few-shot and fine-tuning on seven downstream datasets.

Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning (2025.acl-long)

Copied to clipboard

Ziqi Jia, Anmin Wang, Xiaoyang Qu, Xiaowen Yang, Jianzong Wang

Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching (2025.coling-main)

Challenge:	Existing continual learning setups for embodied intelligence focus on executing low-level actions, neglecting the ability to learn high-level planning and multi-level knowledge.
Approach:	They propose a Hierarchical Embodied Continual Learning Setups (HEC) that divides the agent’s continual learning process into two layers: high-level instructions and low-level actions.
Outcome:	The proposed method reduces the forgetting of old tasks compared to other methods, while orthogonally training the remaining parts.

Copied to clipboard

Tianshu Wang, Xiaoyang Chen, Hongyu Lin, Xuanang Chen, Xianpei Han, Le Sun, Hao Wang, Zhenyu Zeng

More Than Spoken Words: Nonverbal Message Extraction and Generation (2023.emnlp-main)

Challenge:	Entity matching (EM) is a critical step in entity resolution (ER).
Approach:	They propose a method that incorporates record interactions from different perspectives.
Outcome:	The proposed framework improves on 8 ER datasets and 10 LLMs and achieves higher efficiency and effectiveness.

Copied to clipboard

Dian Yu, Xiaoyang Wang, Wanshun Chen, Nan Du, Longyue Wang, Haitao Mi, Dong Yu

Information Extraction & Text Mining

Challenge:	Existing studies focus on extracting NMs from small-scale well-structured corpora such as movie scripts wherein NM is enclosed in parentheses by scriptwriters, which greatly decreases the difficulty of extraction.
Approach:	They propose to extract nonverbal messages (NMs) from written text and NMs from spoken text by using a semi-supervised learning algorithm.
Outcome:	The extracted NMs can generate more relevant, valid, and factually consistent NM than the purely supervised generator.

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

MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts (2025.acl-long)

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

Wei Tao, Haocheng Lu, Xiaoyang Qu, Bin Zhang, Kai Lu, Jiguang Wan, Jianzong Wang

Green & Sustainable NLP

Challenge:	Existing approaches to optimize large language models for long-context inference are inefficient and consume memory.
Approach:	They propose a mixed-precision quantization method via mixture of experts that inputs tokens into router chunk by chunk to reduce inference overhead.
Outcome:	The proposed method outperforms state-of-the-art KV cache quantization methods on multiple benchmark datasets.

MMAPG: A Training-Free Framework for Multimodal Multi-hop Question Answering via Adaptive Planning Graphs (2025.emnlp-main)

Copied to clipboard

Yiheng Hu, Xiaoyang Wang, Qing Liu, Xiwei Xu, Qian Fu, Wenjie Zhang, Liming Zhu

Towards Abstractive Grounded Summarization of Podcast Transcripts (2022.acl-long)

Challenge:	Existing multimodal question answering models rely on sequential retrieval and reasoning, but this single-path paradigm makes them vulnerable to errors due to misleading intermediate steps.
Approach:	They propose a multimodal multi-hop question answering framework guided by an Adaptive Planning Graph . they propose modality-specific strategies that dynamically adapt to distinct data types .
Outcome:	The proposed framework outperforms existing models that rely on training.

Copied to clipboard

Kaiqiang Song, Chen Li, Xiaoyang Wang, Dong Yu, Fei Liu

HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection (2025.emnlp-main)

Challenge:	Podcast summarization is of practical benefit to content providers and consumers . however, podcast summarizing faces significant challenges including factual inconsistencies . speech recognizers induce transcription errors and abstractive summarisation models may hallucinate .
Approach:	They propose a method to generate podcast summaries while grounding segments in specific regions of the transcript to allow full inspection of summary details.
Outcome:	The proposed method can produce an abstractive summary while grounding segments in specific regions of the transcript to allow full inspection of summary details.

Copied to clipboard

Yiheng Jing, Mingming Zhang, Yong Zhuang, Jiacheng Guo, Juan Wang, Xiaoyang Xu, Wenzhe Yi, Keyan Guo, Hongxin Hu

Salience Allocation as Guidance for Abstractive Summarization (2022.emnlp-main)

Challenge:	Existing methods for hateful video detection rely on unimodal analysis or feature fusion . Existing tools struggle to capture cross-modal interactions and reason through implicit hate in sarcasm and metaphor .
Approach:	They propose a reasoning-based hateful video detection framework with multimodal large language models . they integrate Chain-of-Thought reasoning to enhance multimodal interaction modeling .
Outcome:	The proposed framework outperforms existing tools on two public datasets covering English and Chinese.

Copied to clipboard

Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen, Dong Yu

Skills-in-Context: Unlocking Compositionality in Large Language Models (2024.findings-emnlp)

Challenge:	Abstractive summarization models implicitly learn to capture the salient information from scratch.
Approach:	They propose a method that uses salience expectation to guide abstractive summarization by averaging salient content to a fixed threshold.
Outcome:	The proposed method can be easily adapted to documents with various abstractiveness and achieves high performance.

Copied to clipboard

Jiaao Chen, Xiaoman Pan, Dian Yu, Kaiqiang Song, Xiaoyang Wang, Dong Yu, Jianshu Chen

TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models (2025.findings-emnlp)

Challenge:	eliciting compositional generalization capabilities in large language models is challenging for advanced LLMs because they lack foundational skills and compositional examples in the same prompt context.
Approach:	They propose to use compositional generalization capabilities in large language models to elicit compositional skills in a prompt context.
Outcome:	The proposed structure enables LLMs to tackle more challenging problems with as few as two exemplars and unlocks their latent potential.

Copied to clipboard

Yiran Zhang, Mo Wang, Xiaoyang Li, Kaixuan Ren, Chencheng Zhu, Usman Naseem

Proactive Guidance of Multi-Turn Conversation in Industrial Search (2025.acl-industry)

Challenge:	Existing benchmarks focus on single-turn or single-step tasks, failing to capture iterative reasoning in real-world settings.
Approach:	They propose a benchmark that evaluates multi-turn, multi-step reasoning through an interactive code-breaking task inspired by the "Turing Machine Board Game" the best model achieves 84% accuracy in Classic mode, but performance drops to 18% in Nightmare mode.
Outcome:	The new benchmark evaluates multi-turn, multi-step reasoning through an interactive code-breaking task inspired by the "Turing Machine Board Game" the best model achieves 84% accuracy in Classic mode, but performance drops to 18% in Nightmare mode.

Copied to clipboard

Xiaoyu Li, Xiao Li, Li Gao, Yiding Liu, Xiaoyang Wang, Shuaiqiang Wang, Junfeng Wang, Dawei Yin

Natural Language Interfaces

Challenge:	Large Language Models (LLMs) have advanced multi-turn conversation systems, emphasizing the need for proactive guidance to enhance users’ interactions.
Approach:	They propose a goal-adaptive supervised fine-tuning framework that generates proactive guidance for users to click for the next turn of the conversation.
Outcome:	The proposed framework achieves 86.10% accuracy in offline evaluation (+23.95% over baseline) and 25.28% CTR in online deployment (149.06% relative improvement).

MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning (2024.naacl-long)

Copied to clipboard

Fuxiao Liu, Xiaoyang Wang, Wenlin Yao, Jianshu Chen, Kaiqiang Song, Sangwoo Cho, Yaser Yacoob, Dong Yu

From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration (2026.acl-long)

Challenge:	Existing large language models have limited ability to perform tasks effectively.
Approach:	They propose a large-scale multimodal chart instruction dataset with 600k instances supporting diverse tasks and chart types.
Outcome:	The proposed LMM achieves state-of-the-art performance on existing chart QA benchmarks.

Copied to clipboard

Jiaqi Shi, Xulong Zhang, Yuechan Li, Xiaoyang Qu, Jianzong Wang

Visual Data in NLP

Challenge:	Existing acceleration strategies suffer from severe "backbone dependency" Existing strategies such as token pruning or layer sparsity suffer from this .
Approach:	They propose a framework that decouples visual redundancy into IVR and architecture-dependent secondary saturation redundancies.
Outcome:	The proposed framework outperforms existing frameworks on Qwen25-VL and Qwa25-LL.

HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning (2025.emnlp-main)

Copied to clipboard

Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, Liming Zhu, Wenjie Zhang

Toward Unifying Text Segmentation and Long Document Summarization (2022.emnlp-main)

Challenge:	Current RAG system retrieves evidence from knowledge graphs and text documents but has limitations in multi-hop reasoning, multi-entity questions, and source verification.
Approach:	They propose a training-free framework that unifies graph topology, document semantics, and source reliability to support deep, faithful reasoning in large language models.
Outcome:	The proposed framework outperforms the current hybrid model-based model-driven system by 20.3% and 30.1% on seven benchmark datasets.

Copied to clipboard

Sangwoo Cho, Kaiqiang Song, Xiaoyang Wang, Fei Liu, Dong Yu

Information Extraction & Text Mining

Challenge:	Abstractive strategies produce more condensed summaries, but they suffer from hallucinations and factual errors, which pose a more difficult generation challenge.
Approach:	They propose a method that learns robust sentence representations by performing summarization and segmentation simultaneously, which is further enhanced by an optimization-based regularizer to promote selection of diverse summary sentences.
Outcome:	The proposed model achieves state-of-the-art performance on publicly available benchmarks and better cross-genre transferability when equipped with text segmentation.

Router-Tuning: A Simple and Effective Approach for Dynamic Depth (2025.emnlp-main)

Copied to clipboard

Shwai He, Tao Ge, Guoheng Sun, Bowei Tian, Xiaoyang Wang, Dong Yu

Green & Sustainable NLP

Challenge:	Existing methods to improve computational efficiency are under-explored and face several critical challenges.
Approach:	They propose a method that selectively activates only a subset of the model's layers, skipping those deemed less important.
Outcome:	The proposed method significantly improves performance on Attention layers and MoE layers while reducing redundant computation and memory usage.

EMO-RL: Emotion-Rule-Based Reinforcement Learning Enhanced Audio-Language Model for Generalized Speech Emotion Recognition (2025.findings-emnlp)

Copied to clipboard

Pengcheng Li, Botao Zhao, Zuheng Kang, Junqing Peng, Xiaoyang Qu, Yayun He, Jianzong Wang