Papers by Zhou Xi

The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit (2025.acl-long)

Challenge:	Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach:	They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome:	The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.

Copied to clipboard

Huixue Zhou, Hengrui Gu, Zaifu Zhan, Xi Liu, Kaixiong Zhou, Yongkang Xiao, Mingfu Liang, Srinivas Prasad Govindan, Piyush Chawla, Jiyan Yang, Xiangfei Meng, Huayu Li, Buyun Zhang, Liang Luo, Wen-Yen Chen, Yiping Han, Bo Long, Rui Zhang, Tianlong Chen

Green & Sustainable NLP

Challenge:	Existing frameworks for Large Language Models (LLMs) for Click-Through Rate prediction require a careful balance between computational efficiency and predictive accuracy.
Approach:	They propose a framework that integrates Retrieval-Augmented Generation with a novel multi-head early exit architecture to address both challenges.
Outcome:	The proposed framework reduces retrieval time while maintaining high model performance.

C-World: A Computer Use Agent Environment Creator (2026.acl-long)

Copied to clipboard

Ziqiao Xi, Shuang Liang, Qi Liu, Jiaqing Zhang, Letian Peng, Fang Nan, Meshal Nayim, Tianhui Zhang, Rishika Mundada, Lianhui Qin, Biwei Huang, Kun Zhou

Challenge:	C-World enables users to build agent environments on demand.
Approach:	They propose a system that enables users to build agent environments on demand.
Outcome:	The proposed system outperforms baselines on 119k samples and achieves Spearman = 0.883 ranking correlation with real execution.

Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning (2024.emnlp-main)

Copied to clipboard

Lu Chen, Rui Zheng, Binghai Wang, Senjie Jin, Caishuang Huang, Junjie Ye, Zhihao Zhang, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

TLSA: LLM-Guided Text-Label Space Alignment with Contrastive Learning for Generalized Category Discovery (2026.acl-long)

Challenge:	Current methods rely on ranking losses to teach reward model to assess preferences, but they are susceptible to noise and ambiguous data, often failing to deeply understand human intentions.
Approach:	They propose a method that incorporates contrastive learning into the reward modeling process to enhance generalization and stabilize the reinforcement learning training process.
Outcome:	The proposed method enhances generalization of the reward model, stabilizes the reinforcement learning training process, and improves the final alignment with human preferences.

Copied to clipboard

Wenxi Xu, Chuan Qin, Xi Chen, Chuyu Fang, Yuanchun Zhou, Hengshu Zhu

Toward Better Loanword Identification in Uyghur Using Cross-lingual Word Embeddings (C18-1)

Challenge:	Existing methods for generalized category discovery suffer from weak text–label alignment, inconsistent objectives across known and novel categories, and poor discrimination of semantically similar clusters.
Approach:	They propose a unified framework that enforces contrastive alignment between text and label representations within a shared semantic space.
Outcome:	The proposed framework outperforms state-of-the-art methods on four benchmark datasets.

Copied to clipboard

Chenggang Mi, Yating Yang, Lei Wang, Xi Zhou, Tonghai Jiang

Multilinguality

Challenge:	Almost every natural language processing task suffers from data sparseness.
Approach:	They propose a method which identify loanwords in monolingual corpora by using cross-lingual word embeddings as core feature and a log-linear model which combines several shallow features to predict the final results.
Outcome:	The proposed method outperforms baseline models significantly on loanword identification and translation in four languages and eight translation directions.

ChildMandarin: A Comprehensive Mandarin Speech Dataset for Young Children Aged 3-5 (2025.acl-long)

Copied to clipboard

Jiaming Zhou, Shiyao Wang, Shiwan Zhao, Jiabei He, Haoqin Sun, Hui Wang, Cheng Liu, Aobo Kong, Yujie Guo, Xi Yang, Yequan Wang, Yonghua Lin, Yong Qin

A Table-to-Text Framework with Heterogeneous Multidominance Attention and Self-Evaluated Multi-Pass Deliberation (2023.findings-emnlp)

Challenge:	Automatic speech recognition systems have advanced significantly with models like Whisper, Conformer, and self-supervised frameworks such as Wav2vec 2.0.
Approach:	They propose to use Mandarin speech datasets to analyze pronunciation and tone of children aged 3 to 5 and evaluate their models on speaker verification (SV) They find that the datasets are more robust than those used by adult speech recognition systems and are open-source and available for all academic purposes.
Outcome:	The proposed dataset includes 41.25 hours of speech with carefully crafted manual transcriptions, collected from 397 speakers across various provinces in China, with balanced gender representation.

Copied to clipboard

Xi Chen, Xinjiang Lu, Haoran Xin, Wenjun Peng, Haoyang Duan, Feihu Jiang, Jingbo Zhou, Hui Xiong

Structured Data in NLP

Challenge:	Table-to-text works have been widely applied in different domains, such as weather forecast and financial report generation.
Approach:	They propose a table-to-text approach on top of Self-evaluated multi-pass Generation and Heterogenous Multidominance Attention to explore the hierarchical structure.
Outcome:	The proposed method outperforms several SOTA methods quantitatively and qualitatively on three public datasets.

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement (2023.findings-emnlp)

Copied to clipboard

Zhiheng Xi, Senjie Jin, Yuhao Zhou, Rui Zheng, Songyang Gao, Jia Liu, Tao Gui, Qi Zhang, Xuanjing Huang

Multi-Programming Language Sandbox for LLMs (2025.acl-demo)

Challenge:	Existing prompting methods have been used to enhance multistep reasoning capabilities of large language models, but they have overlooked the potential of formulating higher-quality problems.
Approach:	They propose a method that starts from the problem side and refines problems to be more comprehensible and solvable for models.
Outcome:	The proposed method achieves notable and consistent effectiveness on five reasoning benchmarks across different models.

Copied to clipboard

Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang

Relation-aware Video Reading Comprehension for Temporal Language Grounding (2021.emnlp-main)

Challenge:	MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
Approach:	They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models.
Outcome:	The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs).

Copied to clipboard

Jialin Gao, Xin Sun, Mengmeng Xu, Xi Zhou, Bernard Ghanem

RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering (2022.acl-long)

Challenge:	Existing methods for temporal language grounding in videos are boundary regression and span extraction tasks.
Approach:	They propose a Relation-aware Network to localize a temporal span relevant to a given query sentence.
Outcome:	The proposed framework selects a video moment choice from the predefined answer set with the aid of coarse-and-fine choice-query interaction and choice-choice relation construction.

Copied to clipboard

Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Caiming Xiong

Natural Language Interfaces

Challenge:	Existing KBQA approaches struggle with generalization of unseen KB schema items . Rank-and-generate approach solves coverage issue with strong generalization .
Approach:	They propose a Rank-and-Generate approach for KBQA that uses a generation model to generalize to unseen KB schema items.
Outcome:	The proposed approach outperforms the prior state-of-the-art on GrailQA and WebQSP datasets.

Low-Resource Language Expansion and Translation Capacity Enhancement for LLM: A Study on the Uyghur (2025.coling-main)

Copied to clipboard

Kaiwen Lu, Yating Yang, Fengyi Yang, Rui Dong, Bo Ma, Aihetamujiang Aihemaiti, Abibilla Atawulla, Lei Wang, Xi Zhou

Text Generation

Challenge:	Extensive experiments have shown that our strategy effectively expands the low-resource languages supported by large language models and significantly enhances the model’s translation ability in Uyghur with less parallel data.
Approach:	They propose a direct preference optimization based on translation self-evolution to expand low-resource languages into large language models by using Uyghur as an example.
Outcome:	The proposed strategy expands low-resource languages supported by large language models and significantly enhances the model’s translation ability in Uyghur with less parallel data.

Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals (2024.lrec-main)

Copied to clipboard

Rui Zheng, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

Robustness in NLP

Challenge:	Existing models that extract discrete inputs into fixed-length representations are vulnerable to adversarial attacks that place perturbations on clean inputs to fool DNNs.
Approach:	They propose to inspect the subspaces of sample features through spectral analysis to better understand adversarial attacks.
Outcome:	The proposed strategy enables the model to inherently suppress adversaries, which boosts model robustness and motivates new directions of effective adversarial defense.

GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond (2024.findings-naacl)

Copied to clipboard

Shen Zheng, Yuyu Zhang, Yijie Zhu, Chenguang Xi, Pengyang Gao, Zhou Xun, Kevin Chang

Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)

Challenge:	Existing LLM leaderboards often reference scores reported in other papers without consistent settings and prompts, which may encourage cherry-picking favored settings and for better results.
Approach:	They propose an open-source and reproducible LLM evaluation suite built on top of OpenAI Evals that systematically evaluates 10+ leading LLMs and OpenAI’s legacy models on 20+ curated benchmarks across 7 capability categories.
Outcome:	The evaluation suite is built on top of OpenAI Evals and evaluates 10+ leading LLMs and OpenAI’s legacy models on 20+ curated benchmarks across 7 capability categories.

Copied to clipboard

Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values.
Approach:	They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values .
Outcome:	The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets.

AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Copied to clipboard

Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song

TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation (2026.findings-acl)

Challenge:	Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach:	They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome:	The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.

Copied to clipboard

Bangde Du, Minghao Guo, Songming He, Ziyi Ye, Xi Zhu, Weihang Su, Shuqi Zhu, Yujia Zhou, Yongfeng Zhang, Qingyao Ai, Yiqun Liu

Natural Language Interfaces

Challenge:	Existing studies show that advanced LLMs produce text indistinguishable from human writing.
Approach:	They propose a benchmark to assess persona simulation across diverse contexts by decomposing the evaluation into six fundamental capabilities including opinion consistency, memory recall, logical reasoning, persona tone, and syntactic style.
Outcome:	The proposed model achieves moderate accuracy but falls short of the basic capabilities needed to simulate personas in real-world contexts.

WebWalker: Benchmarking LLMs in Web Traversal (2025.acl-long)

Copied to clipboard

Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Linhai Zhang, Yulan He, Deyu Zhou, Pengjun Xie, Fei Huang

Information Retrieval

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of natural language processing tasks.
Approach:	They propose a benchmark to assess the ability of LLMs to perform web traversal by using an explore-critic paradigm.
Outcome:	The proposed framework mimics human-like web navigation through an explore-critic paradigm and demonstrates the effectiveness of RAG combined with WebWalker in real-world scenarios.

Label-Free Distant Supervision for Relation Extraction via Knowledge Graph Embedding (D18-1)

Copied to clipboard

Guanying Wang, Wen Zhang, Ruoxu Wang, Yalin Zhou, Xi Chen, Wei Zhang, Hai Zhu, Huajun Chen

Information Extraction & Text Mining

Challenge:	Existing methods to generate large scale labeled data for relation extraction produce noisy relation labels when there are multiple relationships between entities.
Approach:	They propose a method which assumes that a pair of entities appears in a Knowledge Graph and trains a relation classifier.
Outcome:	The proposed method performs well in the current distant supervision dataset.

ORTicket: Let One Robust BERT Ticket Transfer across Different Tasks (2024.lrec-main)

Copied to clipboard

Yuhao Zhou, Wenxiang Chen, Rui Zheng, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

Responsible & Trustworthy NLP

Challenge:	Pretrained language models are susceptible to subtle perturbations and require multiple adversarial training during fine-tuning to improve their robustness.
Approach:	They propose a novel adversarial defense method ORTicket that fine-tunes a model for downstream tasks.
Outcome:	The proposed method achieves comparable robustness to other defense methods while maintaining the efficiency of fine-tuning.

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment (2026.acl-long)

Copied to clipboard

Yuming Yang, Mingyoung Lai, Wanxu Zhao, Xiaoran Fan, Zhiheng Xi, Mingqi Wu, Chiyue Huang, Jun Zhao, Haijun Lv, Jian Tong, Yunhua Zhou, Yicheng Zou, Qipeng Guo, Tao Gui, Qi Zhang, Xuanjing Huang

Reasoning

Challenge:	Existing methods assess suitability primarily through student likelihood, favoring trajectories that align closely with the student model’s current behavior but overlooking more informative ones.
Approach:	They propose a Rank–Surprisal Ratio metric that captures both alignment and informativeness to assess the suitability of a reasoning trajectory.
Outcome:	The proposed metric captures both alignment and informativeness to assess the suitability of a reasoning trajectory.

Instruction-tuned Language Models are Better Knowledge Learners (2024.acl-long)

Copied to clipboard

Zhengbao Jiang, Zhiqing Sun, Weijia Shi, Pedro Rodriguez, Chunting Zhou, Graham Neubig, Xi Lin, Wen-tau Yih, Srini Iyer

Beyond Inherent Cognition Biases in LLM-Based Event Forecasting: A Multi-Cognition Agentic Framework (2025.findings-emnlp)

Challenge:	Large language models store factual knowledge in parameters, but it can become outdated as the work evolves . pre-instruction-tuning improves ability of LLMs to absorb knowledge from new documents .
Approach:	They propose a method that instruction-tunes on questions prior to training on documents . they propose to use QA pairs to update factual knowledge of large language models .
Outcome:	The proposed method outperforms instruction-tuning on documents by 17.8%.

Copied to clipboard

Zhen Wang, Xi Zhou, Yating Yang, Bo Ma, Lei Wang, Rui Dong, Azmat Anwar

Challenge:	Large Language Models exhibit human-like cognitive biases in event forecasting . a human-curated dataset reveals significant cognitive bias in LLMs .
Approach:	They propose a human-curated dataset to explore LLMs' cognitive biases . they leverage LLM participants to act as multi-cognition event participants .
Outcome:	The proposed framework alleviates cognitive biases in LLMs and offers diverse perspectives.

GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety (2026.findings-acl)

Copied to clipboard

Changxuan Fan, Xi Yang, Yueyuan Zheng, Bin Zhou, Yuanping Wang, Wenbin Hu, Huihao Jing, Ki Sen Hung, Dazhao Du, Haoran Li, Janet Hui-wen Hsiao, Yangqiu Song

Responsible & Trustworthy NLP

Challenge:	a survey of older adults shows that many LLMs mishandle elderly-specific contextual risks.
Approach:	They propose a framework to assess elderly-specific contextual risks in LLM interactions . they use a taxonomy to identify 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains .
Outcome:	a new framework assesses elderly-specific contextual risks in LLM interactions . it achieves 96.2% and 90.9% unsafe-prompt detection accuracy, respectively .

MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang

Visual Data in NLP

Challenge:	Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query.
Approach:	They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis.
Outcome:	The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO.

EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations (2026.findings-acl)

Copied to clipboard

Haoqin Sun, Jinghua Zhao, Xuechen Wang, Shiwan Zhao, Jiaming Zhou, Hui Wang, Xi Yang, Yequan Wang, Yonghua Lin

Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning (2025.emnlp-main)

Challenge:	Existing datasets face issues such as low quality, limited scale, and incomplete modalities, hindering model performance.
Approach:	They propose to use Chinese multimodal datasets to capture authentic emotional interplay from 19 professional actors.
Outcome:	The EmotionTalk dataset spans 23.6 hours of dyadic conversations across diverse scenarios.

Copied to clipboard

Senjie Jin, Lu Chen, Zhiheng Xi, Yuhui Wang, Sirui Song, Yuhao Zhou, Xinbo Zhang, Peng Sun, Hong Lu, Tao Gui, Qi Zhang, Xuanjing Huang

Reasoning

Challenge:	Existing work focuses on enabling models to generate natural language chain-of-thought rationales or leverage executable and verifiable code, such as Python.
Approach:	They propose a novel training pipeline that integrates sequential P-CoT and N-Co T generation and a subtask hybrid training strategy to facilitate natural language transferability.
Outcome:	The proposed training pipeline improves both N-CoT and P-Co T performance over the RL baseline.

Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization (2025.emnlp-main)

Copied to clipboard

Jian Li, Shenglin Yin, Yujia Zhang, Alan Zhao, Xi Chen, Xiaohui Zhou, Pengfei Xu

Benchmarking the Fine-Grained Discriminability in Image-Text Retrieval via Controlled Contrastive Differences (2026.findings-acl)

Challenge:	Direct Preference Optimization (DPO) is a widely used reinforcement learning from human feedback (RLHF) method across various domains.
Approach:	They propose an approach that automatically re-weights ambiguous content to reduce ambiguities by calculating semantic similarity from preference pairs.
Outcome:	The proposed approach outperforms state-of-the-art approaches in performance across multiple model scales and widely adopted benchmark datasets.

Copied to clipboard

Zhen Wang, Xi Zhou, Yating Yang, Bo Ma, Lei Wang, Rui Dong, Azmat Anwar, Siru Miao

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development (2026.findings-acl)

Challenge:	Existing cross-modal image-text retrieval models often retrieve samples with inconsistent details.
Approach:	They propose two fine-grained image-text retrieval benchmarks that incorporate extensive contrastive samples with one controlled contrastive difference from its anchor.
Outcome:	Extensive experiments show that contrastive samples can significantly degrade retrieval performance.

Copied to clipboard

Jie Yang, Honglin Guo, Li Ji, Jiazheng Zhou, Rui Zheng, Zhikai Lei, Shuo Zhang, Zhiheng Xi, Shichun Liu, Yuxin Wang, Bo Wang, Yining Zheng, Tao Gui, Xipeng Qiu

StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)

Challenge:	Large Language Models (LLMs) have redefined the role of AI in software engineering . current benchmarks focus on localized code generation, but neglect dynamic, full-process requirements of real-world engineering.
Approach:	They propose a benchmark to evaluate agentic backend coding within a realistic, executable workflow.
Outcome:	The ABC-Bench benchmark evaluates agentic backend coding within a realistic, executable workflow.

Copied to clipboard

Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

Programming Languages in NLP

Challenge:	Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective.
Approach:	They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality.
Outcome:	The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality.

RealBehavior: A Framework for Faithfully Characterizing Foundation Models’ Human-like Behavior Mechanisms (2023.findings-emnlp)

Copied to clipboard

Enyu Zhou, Rui Zheng, Zhiheng Xi, Songyang Gao, Xiaoran Fan, Zichu Fei, Jingting Ye, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Existing studies on human-like behaviors in foundation models do not verify their faithfulness . a simple application of psychological tools cannot faithfully characterize all human-type behaviors .
Approach:	They propose a framework to characterize humanoid behaviors in foundation models . they argue that a simple application of psychological tools cannot faithfully characterize all human-like behaviors .
Outcome:	The proposed framework assesses the faithfulness of results based on reproducibility, internal consistency, and generalizability.

VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training (2026.acl-long)

Copied to clipboard

Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Enyu Zhou, Ming Zhang, Yuhui Wang, Caishuang Huang, Chenhao Huang, Yunke Zhang, Yuran Wang, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang

Robustness in NLP

Challenge:	Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete supervision.
Approach:	They propose a framework that enhances value modeling for robust RL in LLM post-training by integrating auxiliary losses guided by entropy and perplexity from a frozen language model and variational information bottleneck.
Outcome:	The proposed framework outperforms baselines on multi-turn dialogue, math reasoning, and science QA with rule-based and model-based rewards.

A Survey of Large Language Model-Based Search Agents (2026.acl-long)

Copied to clipboard

Yunjia Xi, Jianghao Lin, Yongzhao Xiao, Zheli Zhou, Rong Shan, Te Gao, Jiachen Zhu, Weiwen Liu, Yong Yu, Weinan Zhang

M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Model (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have revolutionized web search, but their integration is static and cannot handle complex contexts.
Approach:	They analyze existing research and analyze existing work from the perspectives of architecture, optimization, application, and evaluation.
Outcome:	The proposed models can comprehend user intentions and context and execute multi-turn retrieval with dynamic planning, extending search capabilities far beyond the web.

Copied to clipboard

Yang Zhou, Pengfei Cao, Yubo Chen, Qingbin Liu, Dianbo Sui, Xi Chen, Kang Liu, Jun Zhao

Are LLMs Rational Investors? A Study on the Financial Bias in LLMs (2025.findings-acl)

Challenge:	Existing knowledge editing methods for MLLMs lack multi-granularity knowledge . existing knowledge editing approaches lack multimodality knowledge and generalize to multimodal data.
Approach:	They propose a multimodal knowledge editing method which integrates key knowledge layers within MLLMs and collaboratively edits them.
Outcome:	The proposed method improves visual generality performance on knowledge data of different granularities.

Copied to clipboard

Yuhang Zhou, Yuchen Ni, Zhiheng Xi, Zhangyue Yin, Yu He, Gan Yunhui, Xiang Liu, Zhang Jian, Sen Liu, Xipeng Qiu, Yixin Cao, Guangnan Ye, Hongfeng Chai

Responsible & Trustworthy NLP

Challenge:	Existing studies on biases within specific domains, such as finance, remain limited.
Approach:	They propose a framework to detect, detect, analyze and mitigate financial biases in large language models.
Outcome:	The proposed framework reduces bias by 68% for the most biased model, according to key metrics.

ASCM: An Answer Space Clustered Prompting Method without Answer Engineering (2022.findings-acl)

Copied to clipboard

Zhen Wang, Yating Yang, Zhou Xi, Bo Ma, Lei Wang, Rui Dong, Azmat Anwar

Low-Resource NLP

Challenge:	Pre-trained language models have shown a great impact on NLP tasks.
Approach:	They propose an answer space clustered prompting model and a synonym initialization method that automatically categorizes all answer tokens in a semantic-clustered embedding space.
Outcome:	Experiments show that the proposed method outperforms existing state-of-the-art methods in few-shot settings.

A Neural Network Based Model for Loanword Identification in Uyghur (L18-1)

Copied to clipboard

Chenggang Mi, Yating Yang, Lei Wang, Xi Zhou, Tonghai Jiang

Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation (2026.acl-long)

Challenge:	Lexical borrowing happens in almost all languages, and we propose a new method to identify loanwords in Uyghur.
Approach:	They propose a neural network based loanword identification model for Uyghur that captures past and future information and learns both word level and character level features automatically.
Outcome:	The proposed model outperforms baseline models on Chinese, Arabic and Russian loanword detection in Uyghur.

Copied to clipboard

Jianing Zhang, Runan Li, Honglin Pang, Ding Xia, Zhou Zhu, Qian Zhang, Chuntao Li, Xi Yang