Papers by Rui Song

The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents (2025.emnlp-main)

Challenge:	Large language models (LLMs) perform well on Out-of-Distribution tasks, but performance degrades as distribution shift becomes more severe.
Approach:	They propose a demonstration search framework that incorporates an OOD proxy to approximate the inaccessible target domain and guide the retrieval process.
Outcome:	The proposed framework enhances robustness in out-of-distribution tasks by incorporating an OOD proxy to approximate the inaccessible target domain and guide the retrieval process.

Copied to clipboard

Yuhan Liu, Zirui Song, Juntian Zhang, Xiaoqing Zhang, Xiuying Chen, Rui Yan

Iterative Document Representation Learning Towards Summarization with Polishing (D18-1)

Challenge:	Existing studies assume fake news is inherently existing rather than exploring its gradual formation.
Approach:	They propose a Large Language Model-based simulation approach explicitly focusing on fake news evolution from real news.
Outcome:	The proposed framework captures fake news evolution patterns and accurately reproduces known fake news, aligning closely with human evaluations.

Copied to clipboard

Xiuying Chen, Shen Gao, Chongyang Tao, Yan Song, Dongyan Zhao, Rui Yan

Information Extraction & Text Mining

Challenge:	Existing summarization methods read through document only once to generate a document representation, resulting in a sub-optimal representation.
Approach:	They propose an iterative model for supervised extractive text summarization which polishes the document representation on many passes through the document.
Outcome:	The proposed model outperforms state-of-the-art extractive systems on CNN/DailyMail and DUC2002 datasets.

Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems (2025.emnlp-main)

Copied to clipboard

Song Jin, Juntian Zhang, Yuhan Liu, Xun Zhang, Yufei Zhang, Guojun Yin, Fei Jiang, Wei Lin, Rui Yan

Challenge:	Existing platforms lack a mechanism for user actions to dynamically reshape the environment.
Approach:	They propose a novel agent-based simulation platform for recommender systems with a robust interaction mechanism.
Outcome:	The proposed platform improves the credibility of the simulation and replicates the Matthew Effect and Brand Loyalty.

From Phrases to Subgraphs: Fine-Grained Semantic Parsing for Knowledge Graph Question Answering (2025.findings-acl)

Copied to clipboard

Yurun Song, Xiangqing Shen, Rui Xia

CLEAN–EVAL: Clean Evaluation on Contaminated Large Language Models (2024.findings-naacl)

Challenge:	Existing approaches to knowledge graph question answering (KGQA) face semantic misalignment and reasoning noise.
Approach:	They propose a fine-grained semantic parsing framework for KGQA that maps natural language queries to executable logical forms.
Outcome:	The proposed framework achieves 18.5% performance improvement over the SOTA on a multi-hop CWQ dataset.

Copied to clipboard

Wenhong Zhu, Hongkun Hao, Zhiwei He, Yun-Ze Song, Jiao Yueyang, Yumeng Zhang, Hanxu Hu, Yiran Wei, Rui Wang, Hongyuan Lu

Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey (2025.findings-emnlp)

Challenge:	Existing methods to evaluate large language models are prone to data contamination.
Approach:	They propose a method which parses contaminated data and back-translates it into a candidate set.
Outcome:	The proposed method reduces data contamination and evaluates the LLMs more cleanly.

Copied to clipboard

Zirui Song, Bin Yan, Yuhan Liu, Miao Fang, Mingzhe Li, Rui Yan, Xiuying Chen

Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip? (2025.findings-emnlp)

Challenge:	specialized LLMs are often limited in domain-specific applications that require specialized knowledge.
Approach:	They provide a comprehensive overview of four key methods to enhance large language models by integrating domain-specific knowledge.
Outcome:	The proposed methods are categorized into four key approaches: dynamic knowledge injection, static knowledge embedding, modular adapters, and prompt optimization.

Copied to clipboard

Xiaochen Wang, Heming Xia, Jialin Song, Longyu Guan, Qingxiu Dong, Rui Li, Yixin Yang, Yifan Pu, Weiyao Luo, Yiru Wang, Xiangdi Meng, Wenjie Li, Zhifang Sui

Interactive Semantic Parsing with Reinforcement Learning for Knowledge Graph Reasoning (2026.findings-acl)

Challenge:	Large Multimodal Models have demonstrated strong performance on vision-language benchmarks, yet current evaluations focus on single-image reasoning.
Approach:	STRIPCIPHER is a benchmark designed to evaluate model ability on understanding implicit narratives in silent comics.
Outcome:	STRIPCIPHER is a high-quality, human-annotated dataset featuring fine-grained annotations and comprehensive coverage of varying difficulty levels.

Copied to clipboard

Yurun Song, Xiangqing Shen, Jianfei Yu, Rui Xia

A Sequence-to-Structure Approach to Document-level Targeted Sentiment Analysis (2023.findings-emnlp)

Challenge:	Existing approaches to improve LLM reliability rely on factual hallucinations . Existing methods rely only on graph traversal, resulting in imprecise retrieval and heavy post-processing burdens.
Approach:	They propose a framework that integrates knowledge Graphs as structured, high-fidelity buffers to enhance LLM reliability.
Outcome:	The proposed framework allows logical constraints to be dynamically interleaved with graph search while optimizing via reinforcement learning with only final answer feedback eliminates the need for gold program annotations.

Copied to clipboard

Nan Song, Hongjie Cai, Rui Xia, Jianfei Yu, Zhen Wu, Xinyu Dai

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis (ABSA) has received wide attention in NLP for nearly two decades . previous studies focused on sentence-level ABSA, but document-level research has not received enough attention.
Approach:	They propose a Sequence-to-Structure approach to address the document-level targeted sentiment analysis task, which aims to extract the opinion targets consisting of multi-level entities from a review document and predict their sentiments.
Outcome:	The proposed approach outperforms baselines on six domains on the document-level targeted sentiment analysis task.

Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering (2025.emnlp-main)

Copied to clipboard

Zixin Chen, Sicheng Song, KaShun Shum, Yanna Lin, Rui Sheng, Weiqi Wang, Huamin Qu

Model Surgery: Modulating LLM’s Behavior Via Simple Parameter Editing (2025.naacl-long)

Challenge:	Misleading visualizations can distort perception and lead to incorrect conclusions.
Approach:	They propose a large-scale multimodal dataset to evaluate MLLMs on misleading chart reasoning.
Outcome:	The proposed framework evaluates MLLMs on misleading chart reasoning on a large-scale multimodal dataset spanning 21 misleader types and 10 chart types . it contains 3,026 curated examples spanning standard chart code, CSV data, multiple-choice questions, and labeled explanations, validated through iterative MLML checks and exhausted expert human review.

Copied to clipboard

Huanqian Wang, Yang Yue, Rui Lu, Jingxin Shi, Andrew Zhao, Shenzhi Wang, Shiji Song, Gao Huang

Challenge:	Current approaches for detoxification or preventing jailbreaking involve fine-tuning billions of parameters through gradient descent with substantial computational cost.
Approach:	They propose to use supervised fine-tuning and Reinforcement Learning from human feedback to modify LLMs' behavior by directly editing a small subset of parameters.
Outcome:	Experiments show that editing a small subset of parameters can modulate specific behaviors of LLMs, such as detoxification and resistance to jailbreak, with only inference-level computational resources.

A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese (2026.tacl-1)

Copied to clipboard

Yikang Liu, Yeting Shen, Hongao Zhu, Lilong Xu, Zhiheng Qian, Siyuan Song, Kejia Zhang, Jialong Tang, Pei Zhang, Baosong Yang, Rui Wang, Hai Hu

Distilling the Essence, Discarding the Dross: Improving Fairness in Multimodal Large Language Models via Historical Reflection-Guided Prompt Optimization (2026.findings-acl)

Challenge:	Using sub-linear length normalized log-probabilities (SLLN-LP), we find unequal lengths of sentences in minimal pairs difficult for LMs even up to 32B parameters.
Approach:	They propose to use ZhoBLiMP as a linguistic minimal pair benchmark for Chinese language models to mitigate biases.
Outcome:	The proposed metric mitigates biases in Chinese language models with over 100 paradigms . Anaphor, Quantifiers, and Ellipsis are difficult for LMs even up to 32B parameters .

Copied to clipboard

Juncheng Hu, Jiming Yu, Rui Song, Kedi Lyu, Yingji Li, Zheli Liu

High-Order Semantic Alignment for Unsupervised Fine-Grained Image-Text Retrieval (2024.lrec-main)

Challenge:	Existing approaches to debiase MLLMs rely on handcrafted prompts that are brittle and difficult to generalize across tasks and bias types.
Approach:	They propose an adaptive self-debiasing framework that optimizes task-specific debiasers to suppress stereotypical outputs.
Outcome:	The proposed framework suppresses stereotypical outputs while maintaining performance.

Copied to clipboard

Rui Gao, Miaomiao Cheng, Xu Han, Wei Song

Data-Centric Explainable Debiasing for Improving Fairness in Pre-trained Language Models (2024.findings-acl)

Challenge:	Existing studies focus on learning global or local correspondence, but lack fine-grained local-global alignment.
Approach:	They propose a High Order Semantic Alignment (HOSA) model that can provide complementary and comprehensive semantic clues to infer correlation scores.
Outcome:	The proposed model outperforms state-of-the-art models in retrieving the most relevant results.

Copied to clipboard

Yingji Li, Mengnan Du, Rui Song, Xin Wang, Ying Wang

A Dual-Mind Framework for Strategic and Expressive Negotiation Agent (2025.acl-long)

Challenge:	Existing data-centric debiasing strategies mainly leverage explicit bias words for counterfactual data augmentation to balance the training data.
Approach:	They propose a method which uses an explainability method to search for implicit bias words to assist in debiasing PLMs.
Outcome:	Extensive results show that the proposed method achieves state-of-the-art debiasing performance and strong generalization while maintaining predictive abilities.

Copied to clipboard

Yutong Liu, Lida Shi, Rui Song, Hao Xu

Challenge:	Existing approaches to negotiation dialogue focus on only one aspect, ignoring the synergistic effect of their combined synergies.
Approach:	They propose a dual-mind negotiation agent framework that integrates an intuitive and a deliberative module for slow, expression optimization.
Outcome:	The proposed framework achieves state-of-the-art on negotiation datasets showing that it improves negotiation ability.

Knowledge-Aware Co-Reasoning for Multidisciplinary Collaboration (2025.emnlp-main)

Copied to clipboard

Xurui Li, null Wanghaijiao, Kaisong Song, Rui Zhu, Haixu Tang

Reasoning

Challenge:	Existing multi-agent paradigms rely on prompt engineering and lack of knowledge integration.
Approach:	They propose a framework that integrates structured knowledge reasoning into multidisciplinary collaboration by using clinical knowledge graphs to guide dynamic discipline determination.
Outcome:	Extensive experiments on academic and real-world datasets demonstrate the effectiveness of the proposed framework.

Enhancing Multimodal Large Language Models for Ancient Chinese Character Evolution Analysis via Glyph-Driven Fine-Tuning (2026.acl-long)

Copied to clipboard

Rui Song, Lida Shi, Ruihua Qi, Yingji Li, Hao Xu

Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training (D18-1)

Challenge:	Existing studies have explored the evolutionary analysis of ancient scripts, with particular attention to the transformation of character forms from oracle bone inscriptions to regular script.
Approach:	They propose a benchmark framework that leverages MLLMs to analyze the evolution of ancient Chinese scripts.
Outcome:	The proposed framework improves performance on core tasks and character recognition and evolutionary reasoning tasks while limiting performance on other tasks.

Copied to clipboard

Juntao Li, Yan Song, Haisong Zhang, Dongmin Chen, Shuming Shi, Dongyan Zhao, Rui Yan

Robustness in NLP

Challenge:	Existing models for automatic poetry generation lack term novelty and thematic consistency.
Approach:	They propose a conditional variational autoencoder with adversarial training for classical Chinese poem generation.
Outcome:	The proposed model outperforms existing models on a large poetry corpus on 'classical Chinese' . it generates poems with novel terms and learns their thematic consistency with their titles.

CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs (2026.findings-acl)

Copied to clipboard

Xingcheng Zhou, Hao Guo, Rui Song, Walter Zimmer, Mingyu Liu, André Schamschurko, Hu Cao, Alois Knoll

Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning (2024.findings-naacl)

Challenge:	Existing Vision-language models are prone to hallucinating nonexistent entities or events and missing subtle but critical visual cues.
Approach:	They propose a Traffic VideoQA Benchmark that enforces a single structured decision pattern over each video question quadruple and provides actionable diagnostics that decompose failures into positive omission, positive swap, negative hallucination, mutual-exclusivity violation.
Outcome:	The proposed model detects true hazards when an accident occurs, and rejects plausible-but-false hypotheses under near-identical counterfactual scenes.

Copied to clipboard

Yinger Zhang, Hui Cai, Xierui Song, Yicheng Chen, Rui Sun, Jing Zheng

From Fake to Real: Mitigating Out-of-Distribution Bias in In-Context Learning via Feedback Supervision from Large Language Models (2026.findings-acl)

Challenge:	Existing approaches to enable large language models to implement function calling are limited in their tool-use capabilities.
Approach:	They propose a controllable, target-driven approach to empower LLMs to operate external APIs only via prompts.
Outcome:	The proposed approach limits LLMs to executing simple tasks, e.g., API Selection and Argument Completion.

Copied to clipboard

Rui Song, Yingji Li, Jian Li, Fausto Giunchiglia, Hao Xu

Graph Neural Network Enhanced Retrieval for Question Answering of Large Language Models (2025.naacl-long)

Challenge:	In-Context Learning (ICL) is one of the most common methods for complex Natural Language Understanding tasks.
Approach:	They propose a method that uses model confidence and perturbation perplexity to enhance the quality of pseudo-labels.
Outcome:	The proposed method reduces OOD biases by avoiding direct use of source data.

Copied to clipboard

Zijian Li, Qingyan Guo, Jiawei Shao, Lei Song, Jiang Bian, Jun Zhang, Rui Wang

Natural Language Interfaces

Challenge:	Existing retrieval methods divide reference documents into passages, treating them in isolation. Existing methods only use contiguous passages or keywords.
Approach:	They propose a retrieval method that leverages graph neural networks to exploit relatedness between passages to enhance retrieval.
Outcome:	The proposed method improves retrieval by exploiting the relatedness between passages.

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Copied to clipboard

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen

ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA (2025.emnlp-main)

Challenge:	Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach:	They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome:	The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.

Copied to clipboard

Zhao Xinjie, Fan Gao, Xingyu Song, Yingjian Chen, Rui Yang, Yanran Fu, Yuyang Wang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

A Simple Contrastive Learning Framework for Interactive Argument Pair Identification via Argument-Context Extraction (2022.emnlp-main)

Challenge:	Multi-hop question answering (QA) is a central challenge in natural language processing . early mistakes can cause errors and undermine the final result, authors say .
Approach:	They propose a reversible multi-agent reasoning framework that backtracks to earlier valid states when conflicts arise.
Outcome:	Empirical evaluation shows that the framework improves on forward-only benchmarks by 6% . the approach enables agents to backtrack to valid states when conflicts arise .

Copied to clipboard

Lida Shi, Fausto Giunchiglia, Rui Song, Daqian Shi, Tongtong Liu, Xiaolei Diao, Hao Xu

Locally Aggregated Feature Attribution on Natural Language Model Understanding (2022.naacl-main)

Challenge:	Existing work on argument mining uses context-based methods to identify whether two arguments are interactively related.
Approach:	They propose a contrastive learning framework to extract valuable information from the context.
Outcome:	The proposed framework achieves state-of-the-art performance on the benchmark dataset and visually displays more compact representations.

Copied to clipboard

Sheng Zhang, Jin Wang, Haitao Jiang, Rui Song

Beyond Benchmarks: A Capability-Based Maturity Model for Systematic AI Integration in Hospitals (2026.findings-acl)

Challenge:	a growing popularity of deep-learning models makes model understanding more important . feature attribution methods have shown promising results in computer vision but are not trivial .
Approach:	They propose a gradient-based feature attribution method that smooths gradients by aggregating similar reference texts derived from language model embeddings.
Outcome:	The proposed method outperforms existing methods on public datasets and key words detection tasks.

Copied to clipboard

Rui Li, Xiaofen WU, Mingqian Liu, Xiaoxia Song, Xu Xiangjun, Jiacheng Qiao, Zhuang Boqin, Xu Chen

Challenge:	Current Large Language Models (LLMs) excel in standardized tests focused on medical knowledge recall, but not in real-world healthcare scenarios.
Approach:	They propose a "capability-based hospital AI Maturity Model" framework that categorizes capabilities into distinct maturity levels . medical artificial intelligence is currently at a critical transition stage from technical verification to deep clinical integration .
Outcome:	The proposed model provides a clear, stepwise evolutionary path for hospitals from foundational infrastructure construction to ubiquitous intelligence.

STINMatch: Semi-Supervised Semantic-Topological Iteration Network for Financial Risk Detection via News Label Diffusion (2023.emnlp-main)

Copied to clipboard

Xurui Li, Yue Qin, Rui Zhu, Tianqianjin Lin, Yongming Fan, Yangyang Kang, Kaisong Song, Fubang Zhao, Changlong Sun, Haixu Tang, Xiaozhong Liu

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection (2026.acl-long)

Challenge:	Commercial news provides rich semantics and timely information for automated financial risk detection.
Approach:	They propose a semi-supervised Semantic-Topological Iteration Network, STINMatch, along with a news-enterprise knowledge graph to endorse the risk detection enhancement.
Outcome:	The proposed model outperforms existing models in terms of generalization and semantics and annotation.

Copied to clipboard

Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen

Robustness in NLP

Challenge:	Personalized MGT detection remains largely underexplored due to personalization challenges . large language models (LLMs) can imitate personal writing styles, but they can generate fake news and misinformation.
Approach:	They propose a benchmark to evaluate detector robustness under personalization . they attribute this limitation to a feature-inversion trap that flips the effect in personalized contexts .
Outcome:	The proposed framework predicts detector robustness under personalization with an 85% correlation to actual results.

Efficient Data Labeling by Hierarchical Crowdsourcing with Large Language Models (2025.coling-main)

Copied to clipboard

Haodi Zhang, Junyu Yang, Jinyin Nie, Peirou Liang, Kaishun Wu, Defu Lian, Rui Mao, Yuanfeng Song

ACSE: An Ancient Character Semantic-Aware Embedding for Large Language Models (2026.findings-acl)

Challenge:	Large language models (LLMs) have been gaining attention for their impressive performance in in-context dialogues.
Approach:	They propose a hierarchical framework that leverages multiple LLMs for efficient data labeling under budget constraints.
Outcome:	The proposed framework outperforms human labelers and GPT-4 in terms of accuracy and efficiency.

Copied to clipboard

Zhihan Zhou, Daqian Shi, Lida Shi, Rui Song, Peiqiang Qiu, Xiaolei Diao, Hao Xu

Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness (2024.findings-emnlp)

Challenge:	Existing studies on pre-Qin documents are insufficient to understand ancient characters . ancient characters have a low level of digitization and training corpora are extremely scarce .
Approach:	They propose a semantic-aware embedding for ancient Chinese characters that integrates glyphs and lexicality into modern Chinese semantic space.
Outcome:	The proposed model integrates glyph and lexicality of ancient characters and maps them to the modern Chinese semantic space.

Copied to clipboard

Jian Li, Haojing Huang, Yujia Zhang, Pengfei Xu, Xi Chen, Rui Song, Lida Shi, Jingwen Wang, Hao Xu

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain (2026.acl-long)

Challenge:	Recent studies have focused on replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs).
Approach:	They propose a self-supervised preference optimization framework that replaces the reward model with a preference loss and alignment loss to improve LLMs' ability to understand human preferences.
Outcome:	The proposed framework can be integrated with existing preference optimization methods and significantly boost their performance.

Copied to clipboard

Song Jin, Juntian Zhang, Xun Zhang, Zeying Tian, Fei Jiang, Guojun Yin, Wei Lin, Yong Liu, Rui Yan

Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks (2020.acl-main)

Challenge:	Existing vision-language models lack fine-grained classification, single-view imagery, and inaccurate metadata.
Approach:	They propose a hierarchical, multi-view benchmark to evaluate VLMs across three levels of cognitive complexity.
Outcome:	The proposed benchmark evaluates vision-language models across three levels of complexity . it systematically identifies five primary failure modes . the proposed benchmarks are available on https://github.com/meituan/DiningBench.

Copied to clipboard

Yiping Song, Zequn Liu, Wei Bi, Rui Yan, Ming Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing methods for training generative models with minimal corpus are difficult . fine-tuning distinguishes tasks from parameter perspective but ignores model-structure perspective .
Approach:	They propose an algorithm that can customize a unique dialogue model for each task in the few-shot setting.
Outcome:	The proposed method outperforms baselines on two datasets in task consistency, response quality, diversity and consistency.

Knowledge-guided Open Attribute Value Extraction with Reinforcement Learning (2020.emnlp-main)

Copied to clipboard

Ye Liu, Sheng Zhang, Rui Song, Suo Feng, Yanghua Xiao

Information Extraction & Text Mining

Challenge:	Existing methods for open attribute value extraction for emerging entities are noisy or incomplete, even missing.
Approach:	They propose a knowledge-guided reinforcement learning framework for open attribute value extraction for emerging entities.
Outcome:	The proposed framework outperforms baselines by 16.5 - 27.8%.

OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval (2025.acl-long)

Copied to clipboard

Wei Yang, Jingjing Fu, Rui Wang, Jinyu Wang, Lei Song, Jiang Bian