Papers by Yao Guo

RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation (2026.acl-long)

Challenge:	Experimental evaluations on NQ, TriviaQA, and HotpotQA datasets demonstrate that our approach achieves a 90% reduction in retrieval time compared to conventional methods while maintaining considerate recall performance.
Approach:	They propose a framework that integrates deep hashing techniques with systematic optimizations to address these limitations.
Outcome:	The proposed framework outperforms retrieval/non-retrieval baselines by 1.4-4.3% in EM scores on NQ, TriviaQA, and HotpotQA datasets.

Copied to clipboard

Bingxian Wu, Yu Zhang, Zonghao Guo, Tang Liu, Chen Qian, Yuxiang Lu, Xingbo Du, Yanghao Li, Yidan Zhang, Chi Chen, Ling Yao, Chenghu Zhou, Maosong Sun

The Elephant in the Room: Exploring the Role of Neutral Words in Language Model Group-Agnostic Debiasing (2025.findings-acl)

Challenge:	Existing RS agents built on general-purpose LLMs are domain-agnostic, resulting in brittle and error-prone workflows.
Approach:	They propose a knowledge-enhanced memory evolution mechanism that bootstraps RS agents with pre-distilled domain knowledge and iteratively integrates online experience for robust multi-step tool execution.
Outcome:	Experiments show that the new model improves tool-use performance and accuracy . iteratively, iteration of the model integrates online experience for robust multi-step tool execution .

Copied to clipboard

Xinwei Guo, Jiashi Gao, Junlei Zhou, Jiaxin Zhang, Guanhua Chen, Xiangyu Zhao, Quanying Liu, Haiyan Wu, Xin Yao, Xuetao Wei

RotateCT: Knowledge Graph Embedding by Rotation and Coordinate Transformation in Complex Space (2022.coling-1)

Challenge:	Large Language Models (LLMs) are increasingly integrated into our daily lives, raising ethical concerns, especially about perpetuating stereotypes.
Approach:	They propose a method that incorporates a neutral word semantics-based loss function to alleviate the deterioration of the LMS during debiasing.
Outcome:	The proposed method alleviates the deterioration of the Language Modeling Score (LMS) by incorporating a neutral word semantics-based loss function.

Copied to clipboard

Yao Dong, Lei Wang, Ji Xiang, Xiaobo Guo, Yuqiang Xie

LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder (2025.emnlp-main)

Challenge:	Existing knowledge graph embedding methods fail to model non-commutative composition patterns . Existing methods are limited to complex space, resulting in a large number of parameters.
Approach:	They propose a knowledge graph embedding method that transforms the coordinates of each entity and then represents each relation as a rotation from head entity to tail entity in complex space.
Outcome:	The proposed method outperforms state-of-the-art methods on link prediction and path query answering.

Copied to clipboard

Yi Jing, Zijun Yao, Hongzhu Guo, Lingxu Ran, Xiaozhi Wang, Lei Hou, Juanzi Li

ProvBench: A Benchmark of Legal Provision Recommendation for Contract Auto-Reviewing (2025.acl-long)

Challenge:	Prior research on linguistic mechanisms of large language models is limited by coarse granularity, limited analysis scale, and narrow focus.
Approach:	They propose a framework for analyzing the linguistic mechanisms of large language models based on Sparse Auto-Encoders.
Outcome:	The proposed framework extracts Chinese and English linguistic features across four dimensions . it uncovers intrinsic representations of linguistic knowledge in LLMs and can control outputs .

Copied to clipboard

Xiuxuan Shen, Zhongyuan Jiang, Junsan Zhang, Junxiao Han, Yao Wan, Chengjie Guo, Bingcheng Liu, Jie Wu, Renxiang Li, Philip S. Yu

What Is Overlap Knowledge in Event Argument Extraction? APE: A Cross-datasets Transfer Learning Model for EAE (2023.acl-long)

Challenge:	Contract review is labor-intensive, time-consuming, and costly . a benchmark is proposed to detect potential legal conflicts .
Approach:	They propose a benchmark for legal provision recommendation and conflict detection for contract auto-reviewing which aims to recommend the legal provisions related to contract clauses and detect possible legal conflicts.
Outcome:	The proposed task recommends legal provisions related to contract clauses and detects legal conflicts.

Copied to clipboard

Kaihang Zhang, Kai Shuang, Xinyue Yang, Xuyang Yao, Jinyu Guo

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

Challenge:	Existing approaches ignore the overlap knowledge across datasets, preventing models from achieving better performance.
Approach:	They propose to divide the EAE knowledge into overlap knowledge across datasets and specific knowledge of the target dataset.
Outcome:	The proposed model outperforms the baseline model with a large margin when only ten records are available in the target dataset.

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

Gated Differentiable Working Memory for Long-Context Language Modeling (2026.acl-long)

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.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Yuyao Ge, Baolong Bi, Jiayu Yao, Jun Wan, Ziling Yin, Jiafeng Guo, Xueqi Cheng

FAME: Towards Factual Multi-Task Model Editing (2024.emnlp-main)

Challenge:	Long contexts break transformers, attention scores dilute, model cannot adapt to novel patterns at inference time.
Approach:	They propose a framework that gates the memory consolidation process by estimating Contextual Utility . they propose GDWM to maintain a form of working memory with constant contexts .
Outcome:	The proposed framework achieves comparable or superior performance on sparse-information tasks with 4 fewer gradient steps compared to uniform baselines.

Copied to clipboard

Li Zeng, Yingyu Shan, Zeming Liu, Jiashu Yao, Yuhang Guo

Superpose Task-specific Features for Model Merging (2025.emnlp-main)

Challenge:	Large language models embed extensive knowledge and perform exceptionally well across tasks. outdated knowledge or factual errors within LLMs can lead to misleading or incorrect responses.
Approach:	They propose to use a dataset to enhance the practicality of model editing to correct inaccurate information within LLMs.
Outcome:	The proposed method performs excellently across tasks and scenarios, confirming its practicality.

Copied to clipboard

Haiquan Qiu, You Wu, Dong Li, Jianmin Guo, Quanming Yao

Challenge:	Existing methods for model merging are limited by resource demands . recent studies validate the linear representation hypothesis .
Approach:	They propose a method that superposes task-specific features from individual models into a merged model.
Outcome:	The proposed method outperforms existing methods on multiple benchmarks and models.

LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Yuxuan Li, Xinwei Guo, Jiashi Gao, Guanhua Chen, Xiangyu Zhao, Jiaxin Zhang, Quanying Liu, Haiyan Wu, Xin Yao, Xuetao Wei

Information Retrieval

Challenge:	Large language models (LLMs) generate outputs that stray from user input or contravene established knowledge.
Approach:	They propose a new phenomenon, Authority Bias, where LLMs favor one knowledge source over the other . they propose atomic information that generates conflicts and a Conflict Detection Enhanced Query framework .
Outcome:	The proposed framework reduces Authority bias in large language models . it detects conflicts, performs credibility assessment on conflicting paragraphs, and detects perturbed text .

Joint Goal Segmentation and Goal Success Prediction on Multi-Domain Conversations (2022.coling-1)

Copied to clipboard

Meiguo Wang, Benjamin Yao, Bin Guo, Xiaohu Liu, Yu Zhang, Tuan-Hung Pham, Chenlei Guo

MOBA-E2C: Generating MOBA Game Commentaries via Capturing Highlight Events from the Meta-Data (2022.findings-emnlp)

Challenge:	Existing metrics to measure the performance of conversational AI assistants are difficult to establish due to their slow nature.
Approach:	They propose an automatic dialogue evaluation framework that performs goal segmentation and success prediction by adding multi-task learning heads.
Outcome:	The proposed model achieves on-par with human annotation compared to a gold annotation benchmark.

Copied to clipboard

Dawei Zhang, Sixing Wu, Yao Guo, Xiangqun Chen

Challenge:	e-sports game competitions lack commentators because of the shortage of professional human commentators.
Approach:	They propose a data-driven MOBA commentary generation framework for MOBA games . they use a rule-based generator and a generative GPT generator to generate commentaries .
Outcome:	The proposed model generates commentaries based on the game meta-data and a rule-based generator and generative GPT generator.

HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices (2025.acl-long)

Copied to clipboard

Silin Li, Yuhang Guo, Jiashu Yao, Zeming Liu, Haifeng Wang

Challenge:	Existing state-of-the-art LLMs cannot perform well in situations where instructions are invalid or multiple devices are involved.
Approach:	They propose to integrate large language models into smart home assistants by enhancing their ability to accurately understand user needs and respond appropriately.
Outcome:	The proposed dataset is the first with valid and invalid instructions across devices . it achieves only 0.0% success rate in the scenario of invalid multi-device instructions .

Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering (2022.findings-naacl)

Copied to clipboard

Jpliu@wtu.edu.cn Jpliu@wtu.edu.cn, Shijie Mei, Xinrong Hu, Xun Yao, Jack Yang, Yi Guo

Nested-Refinement Metamorphosis: Reflective Evolution for Efficient Optimization of Networking Problems (2025.findings-acl)

Challenge:	Existing methods for Knowledge Base Question Answering rely on semantic parsing and information retrieval.
Approach:	They propose a contrastive regularization based method to extract correct answer entities from a context knowledge base and a corresponding question.
Outcome:	The proposed method achieves state-of-the-art performance on the WebQuestionsSP dataset and the effectiveness of proposed modules is also evaluated.

Copied to clipboard

Shuhan Guo, Nan Yin, James Kwok, Quanming Yao

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) excel in network algorithm design but suffer from inefficient iterative coding and high computational costs.
Approach:	They propose a method to iteratively refine task descriptions and metamorphosis on algorithms to generate more effective solutions.
Outcome:	Experimental results show that Nested-Refinement Metamorphosis outperforms state-of-the-art approaches in performance and efficiency.

LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation? (2024.naacl-long)

Copied to clipboard

Yuchi Wang, Shuhuai Ren, Rundong Gao, Linli Yao, Qingyan Guo, Kaikai An, Jianhong Bai, Xu Sun

ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents (2026.findings-acl)

Challenge:	Existing models for text-to-image generation have been underperforming in image-totext generation tasks.
Approach:	They propose a framework that uses a split BERT to create a dedicated latent space for captions and integrates a regularization module to manage varying text lengths.
Outcome:	The proposed framework achieves state-of-the-art performance on the MS COCO dataset with 38.2 BLEU@4 and 126.2 CIDEr .

Copied to clipboard

Dawei Li, Yuguang Yao, Zhen Tan, Huan Liu, Ruocheng Guo

Challenge:	Reward-guided search methods have shown potential in enhancing tool-using agents . however, there is a lack of reliable evaluation benchmarks for PRMs in tool-use settings .
Approach:	They propose a large-scale benchmark specifically designed to evaluate PRMs for tool-using agents.
Outcome:	The proposed benchmark shows that tool reward models perform better in tool-using environments.

Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis (2025.findings-acl)

Copied to clipboard

Yicheng Lang, Kehan Guo, Yue Huang, Yujun Zhou, Haomin Zhuang, Tianyu Yang, Yao Su, Xiangliang Zhang

Can LLMs Hear the Dogwhistle? (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have been used to remove harmful knowledge and undesirable capabilities.
Approach:	They propose a framework that leverages Cognitive Diagnosis Modeling to evaluate LLM unlearning.
Outcome:	The proposed framework enhances evaluation and facilitates removal of harmful abilities.

Copied to clipboard

Yifan Liu, Yi Lin, Xinwei Guo, Ziwei Wang, Jiaxin Zhang, Guanhua Chen, Haiyan Wu, Xiangyu Zhao, Xin Yao, Xuetao Wei

PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes (2026.findings-acl)

Challenge:	Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles.
Approach:	They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices .
Outcome:	The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts.

Copied to clipboard

Yingyu Shan, Zeming Liu, Silin Li, Boao Qian, Jiashu Yao, Yuhang Guo, Haifeng Wang

Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study (2021.tacl-1)

Challenge:	Existing home assistants struggle to interpret elliptical commands based on ellipine expressions . current assistants overlook the progressive omission that occurs in human dialogue as context accumulates - limiting their effectiveness in real-world applications .
Approach:	They propose a simulated home dataset specifically designed for interpreting progressively elliptical commands in smart homes.
Outcome:	The proposed dataset shows that existing home assistants struggle to execute user-intended operations based solely on elliptical commands.

Copied to clipboard

Xiangyang Mou, Chenghao Yang, Mo Yu, Bingsheng Yao, Xiaoxiao Guo, Saloni Potdar, Hui Su

Natural Language Interfaces

Challenge:	Recent advances in open-domain question answering (ODQA) have led to human-level performance on many datasets.
Approach:	They provide a comprehensive and quantitative analysis about the difficulty of book QA . they compare the results of their research with extensive ODQA experiments .
Outcome:	The proposed model outperforms existing models on event-oriented questions on the NarrativeQA dataset.

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)

Copied to clipboard

Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang

Reasoning

Challenge:	Current outcome-centric verification paradigms neglect potential errors in the derivation process.
Approach:	They propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME.
Outcome:	The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models.

Adaptive Structure Induction for Aspect-based Sentiment Analysis with Spectral Perspective (2023.findings-emnlp)

Copied to clipboard

Hao Niu, Yun Xiong, Xiaosu Wang, Wenjing Yu, Yao Zhang, Zhonglei Guo

Sentiment Analysis

Challenge:	incorporating structure information can enhance the performance of aspect-based sentiment analysis.
Approach:	They propose to use pre-trained language models to induct latent structures from a spectrum perspective.
Outcome:	The proposed model shortens Aspects-sentiment Distance and improves structure induction ability.

SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation (2026.findings-acl)

Copied to clipboard

Shuang Cheng, Yihan Bian, Dawei Liu, Yuhua Jiang, Yihao Liu, Linfeng Zhang, Qian Yao, Zhongbo Tian, Wenhai Wang, Qipeng Guo, Kai Chen, Biqing Qi, Bowen Zhou

Assist Non-native Viewers: Multimodal Cross-Lingual Summarization for How2 Videos (2022.emnlp-main)

Challenge:	Autoregressive (AR) language models are a dominant paradigm in the field of parallelism and non-causal modeling.
Approach:	They propose a blockwise discrete diffusion model that preserves AR-compatible serving while enabling parallel intra-block generation.
Outcome:	The proposed model achieves theoretical speedups over 5 and wall-clock speedup of 2.3 on H200 GPUs in latency-critical regimes.

Copied to clipboard

Nayu Liu, Kaiwen Wei, Xian Sun, Hongfeng Yu, Fanglong Yao, Li Jin, Guo Zhi, Guangluan Xu

ChildTalk: A Multi-Dialect Chinese Child Speech Corpus with Full-Length Child–Caregiver Conversations for Speech Recognition (2026.findings-acl)

Challenge:	Existing multimodal summarization methods are limited to monolingual videos . a proposed task aims to generate cross-lingual summaries from multimodal inputs .
Approach:	They propose a task to generate cross-lingual summaries from multimodal inputs of videos . they propose fusion network that integrates multimodal and cross-linguistic information .
Outcome:	The proposed task outperforms existing methods on a reorganized How2 dataset on the reorganized How2 data set.

Copied to clipboard

Jiaming Zhou, Yujie Guo, Shiwan Zhao, Yao Lu, Jianye Wang, Haoqin Sun, Hui Wang, Yong Qin

CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization (2026.acl-long)

Challenge:	Automatic speech recognition (ASR) for children remains challenging due to developmental variability and the scarcity of high-quality corpora.
Approach:	They propose a large-scale Chinese child speech corpus that contains 112.5 hours of speech from 498 children and 500 caregivers.
Outcome:	The proposed model improves in-domain and cross-domain performance on children's speech.

Copied to clipboard

Zhongyuan Peng, Yifan Yao, Kaijing Ma, Shuyue Guo, Yizhe Li, Yichi Zhang, Chenchen Zhang, Yifan Zhang, Zhouliang Yu, Luming Li, Minghao Liu, Yihang Xia, Jiawei Shen, Yuchen Wu, Yixin Cao, Zhaoxiang Zhang, Wenhao Huang, Jiaheng Liu, Ge Zhang

Reasoning

Challenge:	Existing approaches to formalizing mathematical statements face limitations in accuracy, especially in the context of complex, highlevel problems that involve sophisticated mathematical reasoning.
Approach:	They propose a CriticLean framework that elevates the role of the critic from a passive validator to an active learning component and introduce a benchmark to measure models’ ability to distinguish semantically correct from incorrect formalizations.
Outcome:	The proposed framework outperforms open- and closed-source benchmarks and shows that it significantly outperformed existing models.

Toward Optimal LLM Alignments Using Two-Player Games (2025.findings-emnlp)

Copied to clipboard

Rui Zheng, Hongyi Guo, Zhihan Liu, Xiaoying Zhang, Yuanshun Yao, Xiaojun Xu, Zhaoran Wang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Yang Liu, Hang Li

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks (2026.findings-acl)

Challenge:	Alignment of large language models (LLM) is a process that ensures the model’s responses to user prompts align with human intentions and social values.
Approach:	They propose an alignment method based on a two-agent game consisting of an adversarial agent and a defensive agent.
Outcome:	The proposed method improves on a two-agent game with an adversarial agent and a defensive agent.

Copied to clipboard

Zhuo Li, Guodong DU, Zesheng Shi, Weiyang Guo, Weijun Yao, Yuan Zhou, Jiabo Zhang, Jing Li

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) can specialize under fixed memory and inference budgets, but they struggle to achieve high performance across heterogeneous domains.
Approach:	They propose a modular improvement framework that partitions full capabilities of a general-purpose model into domain-specific delta modules that reorganize and refine the model's internal knowledge.
Outcome:	The proposed framework outperforms monolithic models on multi-task and agentic benchmarks and achieves up to 4 speedup.

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

Copied to clipboard

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

N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator (2026.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

Zheyu Lin, Jirui Yang, Yukui Qiu, Yubing Bao, Hengqi Guo, Yao Guan

TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis (2025.findings-acl)

Challenge:	Evaluating the safety robustness of LLMs is critical for their deployment.
Approach:	They propose to use latent representations to characterize hidden layer dynamics by analyzing the APT of latent models and introducing the JSS metric.
Outcome:	The proposed method exploits the APT (Angular-Probabilistic Trajectory) of latent representations and introduces the JSS (Jensen-Shannon Separability) metric.

Copied to clipboard

Yu Zhang, Wenxiang Guo, Changhao Pan, Dongyu Yao, Zhiyuan Zhu, Ziyue Jiang, Yuhan Wang, Tao Jin, Zhou Zhao

Half-S: Halving the Scale for Near-Lossless 4-Bit LLM Training (2026.findings-acl)

Challenge:	Existing zero-shot singing voice synthesis models depend on phoneme and note boundary annotations, limiting their robustness and producing poor transitions between phonemes and notes.
Approach:	They propose a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts.
Outcome:	Experimental results show that TCSinger 2 outperforms baseline models in subjective and objective metrics across multiple related tasks.

Copied to clipboard

Jinyang Du, Ruihao Gong, Linghan Ai, Zining Wang, Yunke Peng, Yao Wang, Lei Yan, null Wxuefei, Yaoyuan Wang, Jinyang Guo, Dahua Lin, Xianglong Liu

Green & Sustainable NLP

Challenge:	Existing 4-bit training pipelines rely on max-scaling, which causes representation collapse . despite this, there are limitations in the accuracy of 4-bit LLM training .
Approach:	They propose a scaling strategy that uses half-scaling as a hardware-friendly default . they propose fp4 support that allows for a faster scaling of large language models .
Outcome:	The proposed scaling strategy narrows the gap between theoretical optimum and BF16 while maintaining the efficiency benefits of 4-bit training.

Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation (2025.findings-emnlp)

Copied to clipboard

Zhenglin Hua, Jinghan He, Zijun Yao, Tianxu Han, Haiyun Guo, Yuheng Jia, Junfeng Fang

VEG: Verbal 𝜖-greedy for Semantic Exploration in Multi-Turn RL Agents (2026.acl-industry)

Challenge:	Existing approaches to address hallucinations in large vision-language models require substantial computational cost and time.
Approach:	They propose to leverage sparse autoencoders to identify semantic directions closely associated with faithfulness or hallucination, extracting more precise and disentangled hallucinian-related representations.
Outcome:	The proposed method outperforms existing decoding approaches while maintaining transferability across different model architectures with negligible additional time overhead.

Copied to clipboard

Yongchang Hao, Jie Hao, Yongsheng Mei, Ze Ye, Junyi Chai, Bin Guo, Benjamin Z. Yao, Chenlei Guo, Lili Mou

Challenge:	Standard RL approaches suffer from reward sparsity and mode-seeking behavior . lack of diversity hinders exploration necessary for optimal learning .
Approach:	They propose a framework that leverages external feedback as a dynamic control variable to explicitly balance exploration and exploitation within the semantic space.
Outcome:	Experiments on Tau Bench and SearchQA show that the proposed framework outperforms standard RL baselines.

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction (2026.findings-acl)

Copied to clipboard

Haonan Bian, Zhiyuan Yao, Sen Hu, Zishan Xu, Shaolei Zhang, Yifu Guo, Ziliang Yang, Xueran Han, Huacan Wang, Ronghao Chen

JudgeAgent: Beyond Static Benchmarks for Knowledge-Driven and Dynamic LLM Evaluation (2026.findings-acl)

Challenge:	Existing benchmarks focus on casual conversation or task-oriented dialogue, failing to capture “long-term project-oriented” interactions where agents must track evolving goals.
Approach:	They propose a benchmark that simulates the dynamic evolution of memory in real-world projects.
Outcome:	The proposed benchmarks simulate the dynamic evolution of memory in real-world projects.

Copied to clipboard

Zhichao Shi, Xuhui Jiang, Chengjin Xu, Cangli Yao, Shengjie Ma, Yinghan Shen, Zixuan Li, Jian Guo, Yuanzhuo Wang

Challenge:	Current evaluation methods for large language models rely on static benchmarks . limited knowledge coverage and fixed difficulties hinder the targeted optimizations resulting in superficial evaluations of LLMs - a problem that has been addressed by JudgeAgent .
Approach:	They propose a knowledge-driven and dynamic evaluation framework for large language models . judgeAgent leverages LLM agents equipped with context graphs to traverse knowledge structures .
Outcome:	The proposed framework can achieve comprehensive evaluations and facilitate effective model iterations.

Deterministic Reversible Data Augmentation for Neural Machine Translation (2024.findings-acl)

Copied to clipboard

Jiashu Yao, Heyan Huang, Zeming Liu, Yuhang Guo

Machine Translation

Challenge:	Recent neural machine translation models have improved translation quality but they also introduce small perturbations like misspelling and paraphrasing.
Approach:	They propose a method that generates multi-granularity subword representations with reversible operations and deterministic segmentations.
Outcome:	The proposed method outperforms strong baselines on several translation tasks with a clear margin and exhibits good robustness in noisy, low-resource, and cross-domain datasets.

RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning (2026.acl-long)

Copied to clipboard

Xiang Gao, Yuguang Yao, Qi Zhang, Kaiwen Dong, Avinash Baidya, Ruocheng Guo, Hilaf Hasson, Kamalika Das

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

Challenge:	Large language models (LLMs) struggle to use tools reliably in domain-specific settings.
Approach:	They propose a neuro-symbolic approach to adapt large language models to task-specific tools . they propose reusable rules that are distilled from failure traces and injected into the prompt .
Outcome:	Experiments show that the proposed approach outperforms prompting-based adaptation methods and complements finetuning.

Copied to clipboard

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

Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps (2025.findings-acl)

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

Jie Ou, Jinyu Guo, Shuaihong Jiang, Zhaokun Wang, Libo Qin, Shunyu Yao, Wenhong Tian

Thinking Alignment of Scenario-Oriented User Simulation (2026.acl-long)

Challenge:	Existing approaches to augmented generation ignore the overlap in retrieval results . overlapping content is redundantly represented, affecting the overall efficiency.
Approach:	They propose a model-agnostic approach to re-augmented generation that speeds up prefilling and decoding . they propose an instruction-driven module to guide the model to more suitable ways for LLMs .
Outcome:	The proposed approach achieves 2.79 and 2.33 times significant acceleration on average for prefilling and decoding respectively while maintaining equal generation quality.

Copied to clipboard

Xiaoting Wu, Yi Huang, Chunyang Gao, Mengfei Guo, Jingyu Yao, Junlan Feng

CGBridge: Bridging Code Graphs and Large Language Models for Better Structure-Aware Code Understanding (2026.findings-acl)

Challenge:	Existing user simulators based on prompting to role-play or SFT focus on imitating textual utterances without considering multi-faceted cognitive processes that underlie human decision-making during interactions.
Approach:	They construct a user-simulator dataset that augments 51k human–LLM conversations by reconstructing the user’s inner reasoning during and at the end of each dialogue.
Outcome:	The proposed user simulators augment 51k human–LLM conversations by reconstructing the user’s inner reasoning both during and at the end of each dialogue.

Copied to clipboard

Zeqi Chen, Zhaoyang Chu, Yi Gui, Feng Guo, Yao Wan, Chuan Shi