Papers by Song Guo

ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching (2026.findings-acl)

Challenge:	Iterative non-autoregressive (NAR) models have recently demonstrated impressive performance in varied generation tasks, surpassing the autoregressive Transformer.
Approach:	They propose a strategy to conduct efficient refinements without performance declines by using two simple metrics to identify potential problems existing in current refinement processes.
Outcome:	The proposed model outperforms the autoregressive Transformer by around one BLEU on average.

Copied to clipboard

Han Zhu, Wei Kang, Liyong Guo, Zengwei Yao, Fangjun Kuang, Weiji Zhuang, Zhaoqing Li, Zhifeng Han, Dong Zhang, Xin Zhang, Xingchen Song, Lingxuan Ye, Long Lin, Daniel Povey

Dialogue Systems & Conversational Agents

Challenge:	Existing autoregressive models for dialogue generation suffer from high latency and stability issues.
Approach:	They propose a non-autoregressive (NAR) zero-shot spoken dialogue generation model based on flow-matching.
Outcome:	The proposed model outperforms existing models in speech generation due to poor speech intelligibility and turn-taking precision.

LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Copied to clipboard

Jian Yang, Wei Zhang, Shuyue Guo, Yizhi LI, Linzheng Chai, Zhengmao Ye, Shukai Liu, Yuyang Song, Jiajun Wu, Che Liu, Tianyu Zheng, Siwei Wu, Leo L, Xudong Ma, Chuan Hao, Ran Tao, Yan Xing, Jianzhou Wang, Mingjie Tang, Aishan Liu, Zhoujun Li, Xianglong Liu, Weifeng Lv, Bryan Dai

StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding (2023.emnlp-main)

Challenge:	Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach:	They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome:	The proposed model achieves comparable performance to standard dense models with more parameters.

Copied to clipboard

Cheng Jiayang, Lin Qiu, Tsz Chan, Tianqing Fang, Weiqi Wang, Chunkit Chan, Dongyu Ru, Qipeng Guo, Hongming Zhang, Yangqiu Song, Yue Zhang, Zheng Zhang

TED-EL: A Corpus for Speech Entity Linking (2024.lrec-main)

Challenge:	Analogy-making between narratives is crucial for human reasoning . despite its importance, there has been limited research on story analogies .
Approach:	They construct a large-scale story-level analogy corpus with 24K story pairs . they find that the tasks are incredibly difficult for large language models such as ChatGPT .
Outcome:	The proposed corpus contains 24K story pairs from diverse domains with human annotations on two similarities from the extended Structure-Mapping Theory.

Copied to clipboard

Silin Li, Ruoyu Song, Tianwei Lan, Zeming Liu, Yuhang Guo

Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing (2026.acl-long)

Challenge:	Current entity linking tasks rely on textual information, but entities usually exist in textual, audio, and visual contexts in real-world data such as social media and video websites.
Approach:	They propose a speech entity linking task to recognize mentions from speech and link them to entities in knowledge bases.
Outcome:	The proposed model outperforms the existing models on the TED-EL dataset, scoring an F1 score of 60.68%.

Copied to clipboard

Tingyu Song, Yanzhao Zhang, Mingxin Li, Zhuoning Guo, Dingkun Long, Pengjun Xie, Siyue Zhang, Yilun Zhao, Shu Wu

Context-aware Watermark with Semantic Balanced Green-red Lists for Large Language Models (2024.emnlp-main)

Challenge:	Composed Image Retrieval (CIR) is a complex task in multimodal understanding . current CIR benchmarks lack a robust evaluation pipeline and limited query categories .
Approach:	They construct a fine-grained CIR benchmark that allows for precise control over modification types and content.
Outcome:	The proposed benchmark covers 5,000 high-quality queries structured across five main categories and fifteen subcategories.

Copied to clipboard

Yuxuan Guo, Zhiliang Tian, Yiping Song, Tianlun Liu, Liang Ding, Dongsheng Li

HomoGraphAdapter: A Homogeneous Graph Neural Network as an Effective Adapter for Vision-Language Models (2025.findings-emnlp)

Challenge:	Recent research suggests that watermarking methods cause degradation of text quality due to semantic disparities between the watermarked text and the unwatermarked text.
Approach:	They propose a semantic-aware watermark method that generates a watermark key considering contexts to split a green/red list for watermark injection.
Outcome:	The proposed method reduces performance drop due to adding bias on green lists . it also allows green lists to cover almost all semantics .

Copied to clipboard

Chuan He, Zhuozhao Li, Song Guo, Xiaocheng Lu, Jinxiang Lai

Code Needs Comments: Enhancing Code LLMs with Comment Augmentation (2024.findings-acl)

Challenge:	Existing adaptation methods overlook structural knowledge between text and image modalities or create overly complex graphs containing redundant information for alignment.
Approach:	They propose a method to adapt visual models to downstream tasks using text and image modalities.
Outcome:	The proposed method improves classification accuracy by 1.51% for 1-shot and 0.74% for 16-shot on 11 datasets.

Copied to clipboard

Demin Song, Honglin Guo, Yunhua Zhou, Shuhao Xing, Yudong Wang, Zifan Song, Wenwei Zhang, Qipeng Guo, Hang Yan, Xipeng Qiu, Dahua Lin

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) require a deep understanding of programming languages and their correlation with natural languages (NLs).
Approach:	They propose a data augmentation method that generates comments for existing code and a filtering strategy that filters out code data poorly correlated with natural language.
Outcome:	The proposed method outperforms the model trained on the augmented data and the model further trained on data without augmentation on two widely-used programming skill benchmarks.

InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents (2026.findings-acl)

Copied to clipboard

Zhenghao Zhu, Yuanfeng Song, Xing Chen, Chengzhong Liu, Cui Yakun, Caleb Chen Cao, Sirui Han, Yike Guo

Challenge:	Existing frameworks for data analysis and insight exploration are lacking in terms of benchmarks . existing frameworks suffer from format inconsistencies, poorly conceived objectives, and redundant insights.
Approach:	They propose a data-curation pipeline to construct a new dataset named InsightEval.
Outcome:	The proposed benchmarks highlight prevailing challenges in automated insight discovery and raise key findings to guide future research.

UnitCoder: Scalable Code Synthesis from Pre-training Corpora (2025.emnlp-main)

Copied to clipboard

Yichuan Ma, Yunfan Shao, Peiji Li, Demin Song, Qipeng Guo, Linyang Li, Xipeng Qiu, Kai Chen

The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems (2025.findings-acl)

Challenge:	Large Language Models (LLMs) excel at code understanding and generation, yet code generation remains a challenge.
Approach:	They propose a model that supervises pre-training data quality through automatically generated unit tests while ensuring correctness via an iterative fix and refine flow.
Outcome:	The proposed model improves performance on a large dataset with high quality pre-training data.

Copied to clipboard

Hongru Song, Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Jianming Lv, Maarten de Rijke, Xueqi Cheng

MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation (2026.acl-long)

Challenge:	Existing studies have focused on corpus poisoning, but there are no studies on adversarial attacks on RAG systems.
Approach:	They propose a novel imperceptible retrieve-to-generate attack against RAG systems . they propose regenerative reinforcement learning framework that tracks interactions between attacker and target RAG .
Outcome:	The proposed framework outperforms existing attacks on factual and non-factual RAG systems with small imperceptible text perturbations.

Copied to clipboard

Jin Cui, Jiaqi Guo, Jiepeng Zhou, Ruixuan Yang, Jiayi Lu, Jiajun Xu, Jiangcheng Song, Boran Zhao, Pengju Ren

TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis (2026.findings-acl)

Challenge:	Existing approaches restrict students to following a single golden rationale and treat different reasoning paths independently, causing suboptimal performance.
Approach:	They propose a capability-adaptive framework that transitions distillation from passive mimicry to active cognitive construction and employ a feedback-driven inertia calibration mechanism to align supervision with the student’s current adaptability.
Outcome:	Experiments show that the proposed framework achieves state-of-the-art performance on both in-distribution and out-of distribution benchmarks.

Copied to clipboard

Sikai Bai, Haoxi Li, Jie Zhang, Yongjiang Liu, Song Guo

Low-Resource NLP

Challenge:	Existing test-time methods are limited in specialized or novel domains where supervision is prohibitively expensive or unavailable.
Approach:	They propose a framework that augments training stream from unlabeled test queries.
Outcome:	Extensive experiments show TTVS outperforms state-of-the-art RL-based techniques on unlabeled test-time data.

Covariance Matrix-Driven Image Channel Allocation for Multimodal Fake News Detection (2026.findings-acl)

Copied to clipboard

Zongliang Han, Wenyu Guo, Guoqing Jin, Yang Liu, Yan Song, Dong Yu, Wang Min

Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance (2023.findings-emnlp)

Challenge:	Existing methods focus on designing efficient multimodal fusion frameworks to bridge the semantic gap between images and texts.
Approach:	They propose a covariance matrix-driven image channel allocation method that expands the number of original channel maps and assigns importance scores to the expanded channel maps.
Outcome:	The proposed method achieves state-of-the-art on three public multimodal fake news detection benchmark datasets.

Copied to clipboard

Song Wang, Zhen Tan, Ruocheng Guo, Jundong Li

IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval (2025.naacl-long)

Challenge:	Pretrained Language Models (PLMs) are advanced but data labels are noisy due to the complex annotation process.
Approach:	They propose a framework for fine-tuning PLMs using noisy labels that incorporates guidance from Large Language Models like ChatGPT.
Outcome:	Experiments on synthetic and real-world noisy datasets show that the proposed framework outperforms the state-of-the-art framework.

Copied to clipboard

Tingyu Song, Guo Gan, Mingsheng Shang, Yilun Zhao

Information Retrieval

Challenge:	Current information retrieval systems struggle to handle complex instructions, despite its critical importance . current models struggle to follow complex instructions in real-world applications, resulting in user-specific tasks.
Approach:	They propose a benchmark to evaluate instruction-following information retrieval in expert domains.
Outcome:	The proposed method improves on existing models and provides valuable insights to guide future advancements in retrieval.

Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models (2026.acl-long)

Copied to clipboard

Yongjiang Liu, Haoxi Li, Xiaosong Ma, Jie Zhang, Song Guo

Reasoning

Challenge:	Recent Large Reasoning Models (LRMs) excel at complex reasoning tasks but often suffer from overthinking.
Approach:	They propose a two-stage fine-tuning strategy that progressively inspires LRMs’ difficulty cognition and redundancy cognition of LRM.
Outcome:	The proposed model significantly reduces inference costs by over 70% on easy tasks and 40% on complex ones without compromising performance.

AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents (2025.findings-emnlp)

Copied to clipboard

Zhun Wang, Vincent Siu, Zhe Ye, Tianneng Shi, Yuzhou Nie, Xuandong Zhao, Chenguang Wang, Wenbo Guo, Dawn Song

VizoMem: A Visual-Textual Memory Framework for Efficient Long-Horizon Reasoning (2026.findings-acl)

Challenge:	AGENTVIGIL is a black-box optimization framework to exploit indirect prompt injection vulnerabilities . indirect prompts compromise the core of LLM agents by manipulating contextual information rather than direct user prompts.
Approach:	They propose a black-box optimization framework to exploit indirect prompt injection vulnerabilities . they use a Monte Carlo tree-based algorithm to iteratively refine inputs .
Outcome:	The proposed framework achieves 71% and 70% success rates against two public benchmarks .

Copied to clipboard

Weijie Liang, Yuanfeng Song, Xing Chen, Caleb Chen Cao, Sirui Han, Yike Guo

Visual Data in NLP

Challenge:	Existing systems that use long-context modeling incur computational and memory overhead.
Approach:	They propose a visual memory framework that pre-rendered text into structured images and stored as visual notes for agentic systems.
Outcome:	The proposed system reduces token consumption while preserving effective long-term memory recall.

Improving Deep Embedded Clustering via Learning Cluster-level Representations (2022.coling-1)

Copied to clipboard

Qing Yin, Zhihua Wang, Yunya Song, Yida Xu, Shuai Niu, Liang Bai, Yike Guo, Xian Yang

Information Extraction & Text Mining

Challenge:	Existing efforts to learn meaningful representations at the instance level are limited.
Approach:	They propose a deep embedded clustering model with cluster-level representation learning to jointly learn cluster and instance level representations.
Outcome:	The proposed model produces meaningful clusters on real-world short text datasets.

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

MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning (2022.findings-acl)

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

Fangkai Jiao, Yangyang Guo, Xuemeng Song, Liqiang Nie

Semantic Text Processing

Challenge:	Existing methods to infer logical relations with annotated training data suffer from over-fitting and poor generalization problems due to the dataset sparsity.
Approach:	They propose a MEta-path guided contrastive learning method for logical ReasonIng of text that performs self-supervised pre-training on abundant unlabeled text data.
Outcome:	The proposed method outperforms the baselines on two logical reasoning benchmarks with significant improvements.

Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models (2026.acl-long)

Copied to clipboard

Jiahuan Zhang, Shunwen Bai, Tianheng Wang, KaiWen Guo, Zijia Song, Hanqing WU, Guozheng Rao, Kai Han, Kaicheng Yu

Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation (2026.acl-long)

Challenge:	Existing benchmarks explore aspects of threedimensional spatial reasoning and visual-language reasoning in dynamic environments, but they are unable to perform well on 3D spatial deformation reasoning.
Approach:	They propose to use a ladder competition format to assess the model's spatial deformation reasoning abilities to determine its performance.
Outcome:	The proposed framework assesses the performance of Vision-Language Models in spatial deformation reasoning tasks.

Copied to clipboard

Yanzhi Tian, Cunxiang Wang, Zeming Liu, Heyan Huang, Wenbo Yu, Dawei Song, Jie Tang, Yuhang Guo

Machine Translation

Challenge:	Large Language Models (LLMs) have advanced machine translation (MT) a meta-evaluation dataset focused on non-literal translations is lacking . experimental results show the inaccuracies of traditional MT metrics and the limitations of LLM-as-a-Judge.
Approach:	They propose a meta-evaluation framework that leverages sub-agents to evaluate machine translation metrics.
Outcome:	The proposed framework improves on the knowledge cutoff and score inconsistency problem.

Multi-Scale Spectral Selection and Entropy-Guided Uncertainty Fusion for Multimodal Rumor Detection (2026.findings-acl)

Copied to clipboard

Zongliang Han, Wenyu Guo, Guoqing Jin, Yang Liu, Fan Li, Dong Yu, Yan Song, null Zhangfengzhen

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

Challenge:	Existing methods for multimodal content detection fail to capture cross-modal semantic inconsistencies and ignore inherent noise in multimodal features.
Approach:	They propose a multimodal rumor detection method based on a frequency domain spectral selection method and entropy-guided uncertainty fusion method to capture cross-modal semantic inconsistencies.
Outcome:	The proposed method outperforms state-of-the-art methods in multimodal rumor detection . it shows stronger detection capability and robustness on multiple datasets .

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.

Stop Hardening Everything: A Training-Free Neuron-Level Defense for Neural Ranking Models (2026.acl-long)

Copied to clipboard

Yu-An Liu, Ruqing Zhang, Hongru Song, Jiafeng Guo, Yixing Fan, Xueqi Cheng

ChatKBQA: A Generate-then-Retrieve Framework for Knowledge Base Question Answering with Fine-tuned Large Language Models (2024.findings-acl)

Challenge:	Existing defenses for neural ranking models are data-centric and require retraining and adversarial data generation.
Approach:	They propose a model-centric defense that addresses vulnerability at its architectural source without costly retraining or adversarial data generation.
Outcome:	The proposed approach outperforms state-of-the-art models on MS MARCO and TREC 19 while maintaining strong performance on clean data.

Copied to clipboard

Haoran Luo, Haihong E, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin, Yifan Zhu, Anh Tuan Luu

Semantic Text Processing

Challenge:	Existing KBQA methods address inefficient knowledge retrieval and semantic parsing errors.
Approach:	They propose a generatethen-retrieve KBQA framework that generates logical form and replaces entities and relations with an unsupervised retrieval method to improve both generation and retrieval more directly.
Outcome:	Experimental results show that ChatKBQA achieves new state-of-the-art performance on standard KBQA datasets, WebQSP, and CWQ.

RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning (2022.emnlp-main)

Copied to clipboard

Mingkai Deng, Jianyu Wang, Cheng-Ping Hsieh, Yihan Wang, Han Guo, Tianmin Shu, Meng Song, Eric Xing, Zhiting Hu

HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level (2023.acl-long)

Challenge:	Existing methods for finding the optimal prompt for a task are difficult to optimize.
Approach:	They propose an efficient discrete prompt optimization approach with reinforcement learning that generates the optimal discrete stimulus after training with reward.
Outcome:	The proposed approach is based on a parameter-efficient policy network that generates the optimal discrete prompt after training with reward.

Copied to clipboard

Haoran Luo, Haihong E, Yuhao Yang, Yikai Guo, Mingzhi Sun, Tianyu Yao, Zichen Tang, Kaiyang Wan, Meina Song, Wei Lin

ProxyQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models (2024.acl-long)

Challenge:	Existing research on HKGs rarely models the graphical and sequential structure of HKG, limiting their representation.
Approach:	They propose a Hierarchical Attention model for HKG Embedding that includes global-level and local-level attention to model the graphical structure of HKGs.
Outcome:	The proposed model achieves state-of-the-art performance on HKG standard datasets and addresses the issue of HKG multi-position prediction for the first time.

Copied to clipboard

Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Yunlong Feng, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, Linqi Song

Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation (2024.acl-long)

Challenge:	Existing evaluation methods for large language models are labor-intensive and lack efficiency.
Approach:	They propose a framework dedicated to assessing long-text generation that includes in-depth human-curated meta-questions spanning various domains . they use a set of proxy-quests with pre-annotated answers to assess the content's quality by incorporating the generated texts as contextual background.
Outcome:	The proposed framework assesses the quality of long-text content by matching it with references through human evaluation or automated metrics.

Copied to clipboard

Jiaxin Bai, Yicheng Wang, Tianshi Zheng, Yue Guo, Xin Liu, Yangqiu Song

CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture (2025.findings-emnlp)

Challenge:	Abductive reasoning is the process of making educated guesses to provide explanations for observations.
Approach:	They propose a task of complex logical hypothesis generation to generate a complex logique hypothesis that can explain a set of observations.
Outcome:	The proposed model generates logical hypotheses closer to the reference hypothesis, but not better on unseen observations.

Copied to clipboard

Zaiyi Zheng, Song Wang, Zihan Chen, Yaochen Zhu, Yinhan He, Liangjie Hong, Qi Guo, Jundong Li

Semantic Text Processing

Challenge:	Existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base, which often miss relevant information located further away from a global view.
Approach:	Hybrid-RAG combines textual documents and graph-structured relational information for RAG . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base .
Outcome:	Hybrid-RAG combines textual documents and graph-structured relational information . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base .

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning (2025.coling-main)

Copied to clipboard

Yifan Du, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, Ji-Rong Wen

CritiQ: Mining Data Quality Criteria from Human Preferences (2025.acl-long)

Challenge:	Experimental results show that visual instruction tuning improves performance of Multi-modal Large Language Models (MLLMs) to extend the application scope of Large Language Modells, a surge of work augments LLMs with vision encoders to endow the ability of multi-modal cognition and reasoning.
Approach:	They propose a systematic approach to create high-quality visual reasoning instructions using a synthesize-complicate-reformulate paradigm.
Outcome:	The proposed method improves performance of MLLMs by 27.86% and 27.60% on MME-Perception and MME Cognition.

Copied to clipboard

Honglin Guo, Kai Lv, Qipeng Guo, Tianyi Liang, Zhiheng Xi, Demin Song, Qiuyinzhe Zhang, Yu Sun, Kai Chen, Xipeng Qiu, Tao Gui

Information Retrieval

Challenge:	Existing methods to train language models rely on manual design, perplexity, or careful prompt engineering.
Approach:	They propose a method that automatically mines criteria from human preferences for data quality with only 30 human-annotated pairs and performs efficient data selection.
Outcome:	The proposed method improves on human-annotated test sets and shows high accuracy on code, math, and logic domains.

Lock on Target! Precision Unlearning via Directional Control (2025.findings-emnlp)

Copied to clipboard

Yuntao Wen, Ruixiang Feng, Feng Guo, Yifan Wang, Ran Le, Yang Song, Shen Gao, Shuo Shang

Challenge:	Existing methods for unlearning harmful, sensitive, or outdated knowledge suffer from two critical limitations: (1) collateral forgetting, where erasing target data inadvertently removes related but desirable knowledge, and (2) generality forgetting degrades the model’s general capabilities.
Approach:	They propose a method that identifies and leverages a targeted "unlearning direction" in the model's parameter space and selectively updates along this direction.
Outcome:	Experiments show that the proposed method achieves state-of-the-art unlearning precision while preserving both related knowledge and general capabilities.

Multi-step Jailbreaking Privacy Attacks on ChatGPT (2023.findings-emnlp)

Copied to clipboard

Haoran Li, Dadi Guo, Wei Fan, Mingshi Xu, Jie Huang, Fanpu Meng, Yangqiu Song

LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning (2026.acl-long)

Challenge:	With the rapid evolution of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts.
Approach:	They propose to integrate ChatGPT and Bing GPT3 into their applications to create a set of LLMs that can be used to generate NLP tasks with appropriate prompts.
Outcome:	The proposed models can be zero-shot or few-shot learners to solve specified tasks and can even be zero or few shot learners.

Copied to clipboard

Haoyue Zhang, Hualei Zhang, Xiaosong Ma, Jie Zhang, Song Guo

VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos (2025.acl-long)

Challenge:	Existing KV cache compression methods mitigate memory bottlenecks but struggle in long reasoning tasks.
Approach:	They propose a lagged eviction framework that prioritizes evicts based on tokens’ recurrence patterns to reduce KV cache by 50% and maintain comparable accuracy.
Outcome:	The proposed framework reduces KV cache by 50% 70% while maintaining comparable accuracy, outperforming existing KV baselines.

Copied to clipboard

Tingyu Song, Tongyan Hu, Guo Gan, Yilun Zhao

PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models (2024.acl-long)

Challenge:	Multimodal large language models (MLLMs) are used for video quality assessment, image captioning and video analysis.
Approach:	They propose a benchmark to evaluate MLLMs on AIGC videos using coherence validation, error awareness, error type detection and reasoning evaluation tasks.
Outcome:	The proposed benchmark evaluates 13 frontier MLLMs on AIGC videos.

Copied to clipboard

Haoran Li, Dadi Guo, Donghao Li, Wei Fan, Qi Hu, Xin Liu, Chunkit Chan, Duanyi Yao, Yuan Yao, Yangqiu Song

A Span-based Multimodal Variational Autoencoder for Semi-supervised Multimodal Named Entity Recognition (2022.emnlp-main)

Challenge:	generative large language models (LLMs) exhibit surprising capability and integrate previous tasks into a unified text generation formulation.
Approach:	They propose a privacy evaluation benchmark to quantify the privacy leakage of language models.
Outcome:	The proposed benchmark compares PPLMs with different privacy implementations to find out how privacy leakage is handled.

Copied to clipboard

Baohang Zhou, Ying Zhang, Kehui Song, Wenya Guo, Guoqing Zhao, Hongbin Wang, Xiaojie Yuan