Papers by Xi Li

Better Process Supervision with Bi-directional Rewarding Signals (2025.findings-acl)

Challenge:	Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored.
Approach:	They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios.
Outcome:	The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC.

Copied to clipboard

Wenxiang Chen, Wei He, Zhiheng Xi, Honglin Guo, Boyang Hong, Jiazheng Zhang, Nijun Li, Tao Gui, Yun Li, Qi Zhang, Xuanjing Huang

Reasoning

Challenge:	Existing processes that reward for each step are one-directional and lack a mechanism to model the distance to the final target.
Approach:	They propose a process supervision model that evaluates the correctness of previous steps and the probability of future success.
Outcome:	The proposed model outperforms existing supervision models like ORM and PRM on reasoning tasks and improves solution re-design.

Exploring the Impact of Personality Traits on LLM Toxicity and Bias (2025.emnlp-main)

Copied to clipboard

Shuo Wang, Renhao Li, Xi Chen, Yulin Yuan, Min Yang, Derek F. Wong

Sentiment Analysis

Challenge:	anthropomorphic LLMs are being developed to serve diversified roles, but content safety concerns remain regarding their toxicity and toxicity.
Approach:	They propose to assign personality traits to large language models (LLMs) to reduce toxic language and social biases in their outputs by using the widely accepted HEXACO personality framework developed in social psychology.
Outcome:	The proposed model is able to perform on three toxic and bias benchmarks and shows that assigning personality traits reduces bias and toxicity similar to humans’ correlations between personality traits and toxic behaviors.

Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models (2026.findings-acl)

Copied to clipboard

Canhui Wu, Qiong Cao, Chang Li, Zhenfang Wang, Chao Xue, Yuwei Fan, Wei Xi, Xiaodong He

DSG-MCTS: A Dynamic Strategy-Guided Monte Carlo Tree Search for Diversified Reasoning in Large Language Models (2025.emnlp-main)

Challenge:	Existing reinforcement learning methods for large reasoning models suffer from excessive verbosity, known as "overthinking." Existing models penalize generated tokens to promote conciseness, but these methods encounter two challenges: they may develop hacking behavior in later stages of training by discarding reasoning steps.
Approach:	They propose a framework that steers large reasoning models toward more efficient reasoning . they prioritize correctness while imposing penalties for redundant steps .
Outcome:	The proposed framework reduces token usage by 69.7% on AIME24.

Copied to clipboard

Rui Ha, Chaozhuo Li, Rui Pu, Litian Zhang, Xi Zhang, Sen Su

CLHA: A Simple Yet Effective Contrastive Learning Framework for Human Alignment (2024.lrec-main)

Challenge:	Large language models (LLMs) have shown strong potential in complex reasoning tasks, but their performance often degrades, resulting in hallucinations, errors, and logical inconsistencies.
Approach:	They propose a framework that integrates multiple reasoning strategies to expand the reasoning space and a dynamic strategy selection mechanism that adapts to the task context.
Outcome:	The proposed framework outperforms existing state-of-the-art methods on a set of reasoning benchmarks.

Copied to clipboard

Feiteng Fang, Liang Zhu, Xi Feng, Jinchang Hou, Qixuan Zhao, Chengming Li, Xiping Hu, Ruifeng Xu, Min Yang

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Challenge:	Large language models (LLMs) have attracted considerable attention from academic and industrial communities due to their outstanding performance in various natural language processing tasks.
Approach:	They propose a Contrastive Learning Framework for Human Alignment to evaluate the noise within the data and dynamically adjust the training process.
Outcome:	The proposed framework surpasses other algorithms in terms of reward model scores, automatic evaluations, and human assessments on the widely used dataset "Helpful and Harmless"

Copied to clipboard

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang

Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models (2025.findings-acl)

Challenge:	Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach:	They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome:	Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .

Copied to clipboard

Xi Li, Ruofan Mao, Yusen Zhang, Renze Lou, Chen Wu, Jiaqi Wang

Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories (2026.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, but are vulnerable to backdoor attacks.
Approach:	They propose a chain-of-scrutiny approach which leverages LLMs’ unique reasoning abilities to mitigate backdoor attacks.
Outcome:	The proposed model is well-suited for the popular API-only LLM deployments, enabling detection at minimal cost and with little data.

Copied to clipboard

Peiyang Liu, Zhirui Chen, Xi Wang, Di Liang, Youru Li, Zhi Cai, Wei Ye

Reasoning

Challenge:	MCTS methods retain only the single highest-reward trajectory, discarding comparative signals present in the many explored paths.
Approach:	They propose a framework that transforms supervision extraction into a synthesis procedure.
Outcome:	The proposed framework matches or exceeds baselines on 60K CRPS-synthesized examples on out-of-domain benchmarks.

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

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.

Multiple Knowledge-Enhanced Interactive Graph Network for Multimodal Conversational Emotion Recognition (2024.findings-emnlp)

Copied to clipboard

Geng Tu, Jun Wang, Zhenyu Li, Shiwei Chen, Bin Liang, Xi Zeng, Min Yang, Ruifeng Xu

Youling: an AI-assisted Lyrics Creation System (2020.emnlp-demos)

Challenge:	Multimodal Emotion Recognition in Conversations models struggle due to lack of Common Sense Knowledge (CSK).
Approach:	They propose a multimodal approach to integrate multiple knowledge into the edge representations by integrating textual and visual CSK.
Outcome:	The proposed model outperforms state-of-the-art methods on two popular datasets.

Copied to clipboard

Rongsheng Zhang, Xiaoxi Mao, Le Li, Lin Jiang, Lin Chen, Zhiwei Hu, Yadong Xi, Changjie Fan, Minlie Huang

Challenge:	Recent studies have focused on a single pass of lyrics generation with little human intervention.
Approach:	They propose an AI-assisted lyrics creation system that supports one pass full-text generation and interactive generation modes.
Outcome:	The proposed system supports full-text generation and interactive generation modes . it also provides a revision module which enables users to revise undesired lyrics repeatedly.

Conditioned Masked Language and Image Modeling for Image-Text Dense Retrieval (2022.findings-emnlp)

Copied to clipboard

Ziyang Luo, Yadong Xi, Rongsheng Zhang, GongZheng Li, Zeng Zhao, Jing Ma

Analyzing Chain-of-thought Prompting in Black-Box Large Language Models via Estimated V-information (2024.lrec-main)

Challenge:	Large-scale two-stream pre-trained models like CLIP have achieved tremendous success in image-text retrieval.
Approach:	They propose a cross-modal framework for image-text retrieval using two-stream pre-trained models . they embed images and texts into instance representations with two separate encoders . experimental results on MSCOCO and Flickr30k reveal the effectiveness of their framework .
Outcome:	The proposed framework improves image-text retrieval performance on two popular cross-modal retrieval benchmarks.

Copied to clipboard

Zecheng Wang, Chunshan Li, Zhao Yang, Qingbin Liu, Yanchao Hao, Xi Chen, Dianhui Chu, Dianbo Sui

E-ConvRec: A Large-Scale Conversational Recommendation Dataset for E-Commerce Customer Service (2022.lrec-1)

Challenge:	Chain-of-Thought (CoT) prompting and large language models (LLMs) have shown great potential in improving performance on challenging reasoning tasks.
Approach:	They propose a new metric which extends the concept of pointwise V-information to black-box models and quantifies label-relevant new information introduced by CoT prompting.
Outcome:	The proposed metric extends the concept of pointwise V-information to black-box models, quantifying label-relevant new information introduced by CoT prompting beyond pre-existing label information.

Copied to clipboard

Meihuizi Jia, Ruixue Liu, Peiying Wang, Yang Song, Zexi Xi, Haobin Li, Xin Shen, Meng Chen, Jinhui Pang, Xiaodong He

Natural Language Interfaces

Challenge:	Recent research has focused on developing conversational recommendation system (CRS), which provides valuable recommendations to users through conversations.
Approach:	They construct an authentic Chinese dialogue dataset consisting of over 25k dialogues and 770k utterances, which contains user profile, product knowledge base, and multiple sequential real conversations between users and recommenders.
Outcome:	The proposed dataset contains user profile, product knowledge base, and multiple sequential real conversations between users and recommenders.

SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis (2025.findings-naacl)

Copied to clipboard

Hengxing Cai, Xiaochen Cai, Junhan Chang, Sihang Li, Lin Yao, Wang Changxin, Zhifeng Gao, Hongshuai Wang, Li Yongge, Mujie Lin, Shuwen Yang, Jiankun Wang, Mingjun Xu, Jin Huang, Xi Fang, Jiaxi Zhuang, Yuqi Yin, Yaqi Li, Changhong Chen, Zheng Cheng, Zifeng Zhao, Linfeng Zhang, Guolin Ke

Challenge:	Existing benchmarks fail to adequately evaluate the proficiency of Large Language Models (LLMs) Existing standards do not cover the skills needed to evaluate LLMs in scientific literature analysis.
Approach:	They propose a benchmark to evaluate the proficiency of large language models in scientific literature analysis.
Outcome:	SciAssess evaluates 11 LLMs on multiple tasks across scientific fields.

ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis (2026.acl-long)

Copied to clipboard

Runkai Li, Jia Xiong, Xiuyuan He, Jieru Zhao, Jiaqi Lv, Haowen Fang, Lei Qi, Xi Wang

Reasoning

Challenge:	High-Level Synthesis (HLS) is a hardware design tool that can be used to design hardware from C-like languages, but its widespread adoption is limited by strict coding constraints and design-specific optimizations.
Approach:	They propose a multi-agent HLS design framework that leverages specialized LLMs for automated debugging and directive tuning.
Outcome:	The proposed framework outperforms Gemini-3-pro in debugging and speedups across various HLS kernels and neural network accelerators.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning (2026.acl-long)

Copied to clipboard

Rui Pu, Chaozhuo Li, Rui Ha, Litian Zhang, Lirong Qiu, Xi Zhang

BaitAttack: Alleviating Intention Shift in Jailbreak Attacks via Adaptive Bait Crafting (2024.emnlp-main)

Challenge:	Existing defenses rely on shallow pattern matching, which struggles to generalize to novel and unseen attack strategies.
Approach:	They propose a framework which emulates human cognitive reasoning through a structured reasoning chain.
Outcome:	The proposed framework achieves state-of-the-art performance and exhibits strong generalization to unseen attacks.

Copied to clipboard

Rui Pu, Chaozhuo Li, Rui Ha, Litian Zhang, Lirong Qiu, Xi Zhang

Contextualized End-to-End Neural Entity Linking (2020.aacl-main)

Challenge:	Existing attacks focus on meticulously constructing prompts to disguise harmful intentions . however, incorporation of disguising prompts may incur the challenge of "intention shift"
Approach:	They propose a jailbreak attack component, BaitAttack, to alleviate the effects of intention shift . Bait provides a response to the query, prompting LLMs to rectify or supplement the knowledge within the bait .
Outcome:	The proposed component, BaitAttack, reduces the effects of intention shift within jailbreak attacks.

Copied to clipboard

Haotian Chen, Xi Li, Andrej Zukov Gregoric, Sahil Wadhwa

Editing the Moving World: Model Editing for Video LLMs (2026.acl-long)

Challenge:	a proposed entity linking model that disjointly applies MD and ED from the same contextualized BERT embeddings is able to generalize better.
Approach:	They propose an entity linking (EL) model that jointly learns mention detection (MD) and entity disambiguation (ED) they propose to use task-specific heads on top of shared BERT contextualized embeddings to learn MD and ED.
Outcome:	The proposed model achieves state-of-the-art results across a standard EL dataset and under a setting where hand-crafted candidate sets are not available.

Copied to clipboard

Qian Zhang, Xinye Li, Xiaokai Wu, Junhao Xu, Zhanyue Qin, Qingbin Liu, Junxian Cai, Xi Chen, Bolin Zhang, Zhiying Tu, Dianhui Chu, Xiaoyan Yu, Dianbo Sui

SudokuFill: A Multi-Agent Progressive Filling Framework for Document-Level Scientific Information Extraction (2026.findings-acl)

Challenge:	Existing models for knowledge editing focus on knowledge-level or static visual domains, overlooking dynamic semantics.
Approach:	They propose a benchmark for modeling large language models using six representative models . they analyze the strengths and limitations of existing models and identify new directions .
Outcome:	The proposed benchmark extends existing models from static modalities to dynamic video scenarios.

Copied to clipboard

Yang Li, Yajiao Wang, Yu Zhang, Yuanzhe Zhang, Maodi Hu, Mengting Zhang, Xi Sun, Hua Yue, Zhixiong Zhang

STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding (2026.findings-acl)

Challenge:	Scientific information extraction (SciIE) is a key bottleneck for turning unstructured papers into computable knowledge bases.
Approach:	They propose a scientific information extraction framework that solves a Sudoku problem as a progressive filling problem.
Outcome:	The proposed framework outperforms the GPT-4o model on a document-level adjuvant dataset.

Copied to clipboard

Hongwang Xiao, Wenjun Lin, Xi Chen, Hui Wang, Kai Chen, Jiashan Li, Yuancheng Sun, Sicheng Dai, Boya Wu, Qiwei Ye

Enhancing Text-to-SQL Capabilities of Large Language Models through Tailored Promptings (2024.lrec-main)

Challenge:	a multimodal protein language model (LLM) integrates sequence, structure, and function into functional annotation.
Approach:	They propose a multimodal protein language model that synergistically aligns bimodal representations with the textual modality to advance protein functional annotation.
Outcome:	The proposed model synergizes bimodal representations with the textual modality to advance protein functional annotation.

Copied to clipboard

Zhao Tan, Xiping Liu, Qing Shu, Xi Li, Changxuan Wan, Dexi Liu, Qizhi Wan, Guoqiong Liao

Programming Languages in NLP

Challenge:	Large language models with prompting have achieved encouraging results on many natural language processing tasks due to the absence of task-tailored promptings.
Approach:	They propose three promptings specifically designed for Text-to-SQL: SL-prompt, CC-promped, and SL+CC prompt.
Outcome:	The proposed promptings achieve execution accuracy of 86.2% and test-suite accuracy of 76% . the granularity of schema linking and the order of clause generation have great impact on performance, which are considered little in previous research.

Lifting the Curse of Multilinguality by Pre-training Modular Transformers (2022.naacl-main)

Copied to clipboard

Jonas Pfeiffer, Naman Goyal, Xi Lin, Xian Li, James Cross, Sebastian Riedel, Mikel Artetxe

Sensitivity-LoRA : Low-Load Sensitivity-Based Fine-Tuning for Large Language Models (2025.findings-emnlp)

Challenge:	Recent work on multilingual pre-trained models has focused on pre-training transformers on concatenated corpora of a large number of languages.
Approach:	They propose a language-specific module approach that allows for more languages to be trained post-hoc.
Outcome:	The proposed model can be pre-trained on multiple languages with no drop in performance .

Copied to clipboard

Hao Zhang, Bo Huang, Zhenjia Li, Xi Xiao, Hui Yi Leong, Zumeng Zhang, Xinwei Long, Tianyang Wang, Hao Xu

Summarizing Chinese Medical Answer with Graph Convolution Networks and Question-focused Dual Attention (2020.findings-emnlp)

Challenge:	Low-Rank Adaptation (LoRA) is a promising approach to adapting LLMs to specialized tasks . existing rank allocation techniques remain computationally inefficient and unstable .
Approach:	They propose a low-rank adapted model that approximates model weight updates using low-ranked decomposition.
Outcome:	The proposed method is limited by its uniform rank allocation to each incremental matrix . it leverages the second-order derivatives of the loss function to capture weight sensitivity .

Copied to clipboard

Ningyu Zhang, Shumin Deng, Juan Li, Xi Chen, Wei Zhang, Huajun Chen

CA*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation (2025.findings-naacl)

Challenge:	Existing approaches to generate answer summarization for medical questions are not straightforward to apply to the medical domain.
Approach:	They propose an approach that utilizes graph convolution networks and question-focused dual attention for Chinese medical answer summarization.
Outcome:	The proposed model generates more coherent and informative summaries compared with baseline models.

Copied to clipboard

Xi Xu, Wenda Xu, Siqi Ouyang, Lei Li

Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging (2024.emnlp-main)

Challenge:	Existing metrics for Simultaneous speech translation (SimulST) are inaccurately measuring latency in unsegmented streaming settings.
Approach:	They propose to modify existing metrics to correctly measure computation-aware latency for SimulST systems, addressing limitations present in existing metrics.
Outcome:	The proposed model is based on a real-time, lowlatency scenario where the model starts generating the textual translation before the entire audio input is processed.

Copied to clipboard

Deyuan Liu, Zhanyue Qin, Hairu Wang, Zhao Yang, Zecheng Wang, Fangying Rong, Qingbin Liu, Yanchao Hao, Bo Li, Xi Chen, Cunhang Fan, Zhao Lv, Dianhui Chu, Zhiying Tu, Dianbo Sui

BOLT: Benchmarking Open-World Learning for Text Classification (2026.findings-acl)

Challenge:	Existing methods for parameter pruning fail to utilize the knowledge from pruned parameters.
Approach:	They propose a method that uses manifold learning and the Information Bottleneck measure to merge similar layers to preserve model performance.
Outcome:	The proposed method outperforms pruning methods on multiple datasets and LLMs with quantization and achieves substantial compression ratios.

Copied to clipboard

Chuan Qin, Xi Chen, Jinpeng Li, Hengshu Zhu

RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning (2026.findings-acl)

Challenge:	Existing benchmarks focus on out-of-distribution (OOD) detection while overlooking broader challenges such as the discovery of novel categories.
Approach:	They propose a unified Benchmark and evaluation toolkit supporting Open-world learning for text classification.
Outcome:	The proposed methods overfit training distributions and struggle to generalize to unseen classes.

Copied to clipboard

Meng Xi, Sihan Lv, Yechen Jin, Guanjie Cheng, Naibo Wang, Ying Li, Jianwei Yin

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance (2026.findings-acl)

Challenge:	Existing methods to generate RAG documents require knowledge of the target RAG system’s internal composition and implementation details, whereas black-box methods are unable to utilize interactive information.
Approach:	They propose a RIPRAG attack framework that treats the target RAG system as a black box and leverages a Reinforcement Learning from Black-box Feedback (RLBF) method to optimize the generation model for poisoned documents.
Outcome:	The proposed method achieves an attack success rate (ASR) improvement of up to 0.72 compared to baseline methods.

Copied to clipboard

Hao Zhang, Zhenjia Li, Yifan Gao, Xi Xiao, Heng Zhang, Shuyang Zhang, null Xiaoxincc, Bo Huang, Yuhang Wu, Tianyang Wang, Hao Xu

How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey (2023.findings-emnlp)

Challenge:	Low-Rank Adaptation (LoRA) assumes a uniform rank r for each incremental matrix, not accounting for the varying significance of weight matrices across modules and layers.
Approach:	They propose a framework that allows for faster convergence of low-rank adaptive models . they use a hypernetwork to prune the outputs of the hypernetworks to generate parameters .
Outcome:	The proposed framework accelerates convergence of AdaLoRA by leveraging a hypernetwork.

Copied to clipboard

Jun Bai, Xiaofeng Zhang, Chen Li, Hanhua Hong, Xi Xu, Chenghua Lin, Wenge Rong

PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection (2026.tacl-1)

Challenge:	Transferability estimation has been a topic of great interest in computer vision fields . a lack of a comprehensive comparison between these estimation methods is a problem .
Approach:	They conduct a thorough survey of existing methods to find the most suitable model . they also outline difficulties of consideration of training details and applicability to text generation .
Outcome:	The proposed methods perform well with superiorities in effectiveness and efficiency.

Copied to clipboard

Bingbing Wang, Jingjie Lin, Zhixin Bai, Xintong Song, Qianlong Wang, Min Yang, Xi Zeng, Jing Li, Ruifeng Xu

Sentiment Analysis

Challenge:	Experimental results demonstrate that a Pruned interpretable knowledge Graph Learning framework for explainable stance detection is state-of-the-art for social media stance prediction.
Approach:	They propose a Pruned interpretable knowledge Graph Learning framework for explainable stance detection that incorporates commonsense knowledge and prunes redundant information to ensure precision and minimize noise.
Outcome:	The proposed framework achieves state-of-the-art on three public datasets.

Graph Enhanced Dual Attention Network for Document-Level Relation Extraction (2020.coling-main)

Copied to clipboard

Bo Li, Wei Ye, Zhonghao Sheng, Rui Xie, Xiangyu Xi, Shikun Zhang

FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation (2025.acl-demo)

Challenge:	Document-level relation extraction requires inter-sentence reasoning capabilities to capture local and global contextual information for multiple relation facts.
Approach:	They propose to characterize the interaction between sentences and potential relation instances via a Graph Enhanced Dual Attention network (GEDA) . they also propose a simple yet effective regularizer based on the natural duality of the S2R and R2S attentions, whose weights are also supervised by the supporting evidence of relation instances during training.
Outcome:	The proposed model achieves competitive performance on an existing large-scale dataset while the predictions can be interpretable and easily observed.

Copied to clipboard

Zheqi He, Yesheng Liu, Jing-Shu Zheng, Xuejing Li, Jin-Ge Yao, Bowen Qin, Richeng Xuan, Xi Yang

Summarizing Dialogues with Negative Cues (2022.coling-1)

Challenge:	FlagEvalMM is an evaluation framework designed to assess multimodal models . it is designed to be used for vision-language understanding and generation tasks .
Approach:	They propose an evaluation framework that decouples model inference from evaluation through an independent evaluation service.
Outcome:	The evaluation framework offers accurate and efficient insights into model strengths and limitations.

Copied to clipboard

Junpeng Liu, Yanyan Zou, Yuxuan Xi, Shengjie Li, Mian Ma, Zhuoye Ding

Dialogue Systems & Conversational Agents

Challenge:	Abstractive dialogue summarization aims to convert long dialogue content into its short form where the salient information is preserved while the redundant pieces are ignored.
Approach:	They propose to have the model perceive the redundant parts of an input dialogue history during the training phase.
Outcome:	The proposed method significantly outperforms baselines on the semantic matching and factual consistent based metrics.

MetaASSIST: Robust Dialogue State Tracking with Meta Learning (2022.emnlp-main)

Copied to clipboard

Fanghua Ye, Xi Wang, Jie Huang, Shenghui Li, Samuel Stern, Emine Yilmaz

ScEdit: Script-based Assessment of Knowledge Editing (2025.findings-acl)

Challenge:	Existing dialogue datasets contain lots of noise in their state annotations.
Approach:	They propose a framework to train robust dialogue state tracking models by combining pseudo and vanilla labels by a common weighting parameter.
Outcome:	The proposed framework achieves state-of-the-art accuracy of 80.10% on multiWOZ 2.4.

Copied to clipboard

Xinye Li, Zunwen Zheng, Qian Zhang, Dekai Zhuang, Jiabao Kang, Liyan Xu, Qingbin Liu, Xi Chen, Zhiying Tu, Dianhui Chu, Dianbo Sui

Challenge:	Knowledge Editing (KE) has gained increasing attention, yet current evaluation frameworks do not integrate KE into real-world application scenarios.
Approach:	They propose a script-based benchmark which encompasses both counterfactual and temporal edits and integrates token-level and text-level evaluation methods.
Outcome:	The proposed method combines token-level and text-level evaluation methods with a new fact-based evaluation framework.

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

Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation (2026.acl-long)

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

Xi Xiao, Chenrui Ma, Yunbei Zhang, Chen Liu, Zhuxuanzi Wang, Yanshu Li, Lin Zhao, Guosheng Hu, Tianyang Wang, Hao Xu

Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model (2023.emnlp-main)

Challenge:	Low-Rank Adaptation (LoRA) is a key parameter-efficient fine-tuning method . however, its effectiveness is hampered by semantic drift and structural incoherence .
Approach:	They propose a low-rank Adaptation framework that tackles semantic drift and structural incoherence by pruning task-irrelevant directions.
Outcome:	Experiments on large language models, vision models, and vision models show that the proposed framework outperforms LoRA and advanced dynamic rank allocation and sparsity-based methods.

Copied to clipboard

Zeyu Liu, Tim Dettmers, Xi Lin, Veselin Stoyanov, Xian Li

Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Challenge:	Large and sparse feed-forward layers (S-FFN) have proven effective in scaling up the model size for pretraining large language models.
Approach:	They compare S-FFN architectures for language modeling and compare their performance and efficiency . they found a simpler selection method that selects blocks through their mean aggregated hidden states .
Outcome:	The proposed model size and selection method achieve lower perplexity in language model pretraining compared to existing MoE architectures.

Copied to clipboard

Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach:	They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome:	The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

GenDis: Generative-Discriminative Dual-View Co-Training for Generalized Category Discovery (2026.acl-long)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Xi Chen, Chuan Qin, Jinpeng Li, Shasha Hu, Chao Wang, Hengshu Zhu, Hui Xiong

Challenge:	Existing methods rely on one-hot discriminative supervision, leading to overfitting on seen classes and poor generalization to unseen ones.
Approach:	They propose a Generative–Discriminative Dual-View Co-Training framework that unifies discriminative classification and semantic label generation within an LLM.
Outcome:	The proposed framework outperforms existing methods on five benchmarks on the generalized category discovery (GCD) task.

CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models (2025.acl-long)

Copied to clipboard

Xiaqiang Tang, Jian Li, Keyu Hu, Nan Du, Xiaolong Li, Xi Zhang, Weigao Sun, Sihong Xie

Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)

Challenge:	Existing benchmarks focus on “factual statements” that rephrase source materials, but ignore “cognitive statements” . evaluating and detecting "faithfulness hallucinations" remains challenging .
Approach:	They propose a framework to assess faithfulness of cognitive statements and introduce a dataset to scale easily across models.
Outcome:	The proposed framework assesses faithfulness of cognitive statements and scales easily across models.

Copied to clipboard

Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang

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

Challenge:	Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking.
Approach:	They propose an iterative adversarial training method that incorporates three key innovations to address these challenges.
Outcome:	Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%.

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

Translation Canvas: An Explainable Interface to Pinpoint and Analyze Translation Systems (2024.emnlp-demo)

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

Chinmay Dandekar, Wenda Xu, Xi Xu, Siqi Ouyang, Lei Li

Multilinguality

Challenge:	Existing tools for evaluation of translation models focus on high-level metrics like BLEU or COMET scores, which are time-consuming and prone to error.
Approach:	They propose a toolkit that provides a detailed analysis of translation models and a user-friendly interface.
Outcome:	The toolkit shows superior performance over COMET and SacreBLEU packages under enjoybility and understandbility criteria.

Class Lifelong Learning for Intent Detection via Structure Consolidation Networks (2023.findings-acl)

Copied to clipboard

Qingbin Liu, Yanchao Hao, Xiaolong Liu, Bo Li, Dianbo Sui, Shizhu He, Kang Liu, Jun Zhao, Xi Chen, Ningyu Zhang, Jiaoyan Chen

Sentiment Analysis

Challenge:	Existing intent detection models can only handle predefined intent classes in the offline environment.
Approach:	They propose a method that continually learns new intent classes from new data . structure-based retrospection and contrastive knowledge distillation are used to solve these problems .
Outcome:	The proposed method outperforms existing models on three benchmarks.

Exploring Deductive and Inductive Reasoning Capabilities of Large Language Models in Procedural Planning (2025.findings-emnlp)

Copied to clipboard

Jiabao Kang, Xinye Li, Liyan Xu, Qingbin Liu, Xi Chen, Zhiying Tu, Dianhui Chu, Dianbo Sui

Conan-Embedding-v2: Training an LLM from Scratch for Text Embeddings (2025.emnlp-main)

Challenge:	Deductive and inductive reasoning are fundamental components of human cognition . authors present a benchmark to assess their performance in procedural planning .
Approach:	They propose a benchmark to assess the deductive and inductive reasoning abilities of LLMs . they propose IMSE to enable LLM to generate multiple similar procedural plans .
Outcome:	The proposed method improves inductive reasoning abilities of LLMs, the authors show . they show that LLM models show excellent deductive reasoning capabilities but suboptimal inductive performance.

Copied to clipboard

Shiyu Li, Yang Tang, Ruijie Liu, Shi-Zhe Chen, Xi Chen

Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts (2025.emnlp-main)

Challenge:	Existing studies use LoRA to fine-tune existing LLMs, but this is limited by the data and training gap between them and embedding models.
Approach:	They propose a new 1.4B-parameter LLM trained from scratch and fine-tuned as a text embedder that integrates embeddings across different languages.
Outcome:	The proposed model improves performance on the Massive Text Embedding Benchmark (MTEB) and Chinese MTEB (May 19, 2025).

Copied to clipboard

Yifei Yu, Qian-Wen Zhang, Lingfeng Qiao, Di Yin, Fang Li, Jie Wang, Chen Zeng Xi, Suncong Zheng, Xiaolong Liang, Xing Sun

Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction (2025.naacl-short)

Challenge:	Recent models have extended Corresponding Author. context lengths to millions of tokens while maintaining reasoning and comprehension capabilities.
Approach:	They propose a benchmark to evaluate the ability of large language models to extract sequential information items from long contexts.
Outcome:	The proposed model achieves maximum accuracy of 63.50% on six well-known LLMs.

Copied to clipboard

Xi Chen, Mao Mao, Shuo Li, Haotian Shangguan

Green & Sustainable NLP

Challenge:	Comparative experiments show that our model outperforms several general-purpose and domain-specific legal models.
Approach:	They propose a legal judgment prediction model that integrates LLMs with argumentative reasoning techniques to simulate the debate phase of real courtroom trials.
Outcome:	The proposed model outperforms several general-purpose and domain-specific legal models and offers a dynamic reasoning process.

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

ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation (2026.findings-acl)

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 .

Copied to clipboard

Yihua Zhang, Mingfu Liang, Jiyan Yang, Rong Jin, Wen-Yen Chen, Yiping Han, Huayu Li, Buyun Zhang, Liang Luo, Luke Simon, Sijia Liu, Tianlong Chen, Xi Liu

The CRECIL Corpus: a New Dataset for Extraction of Relations between Characters in Chinese Multi-party Dialogues (2022.lrec-1)

Challenge:	Recent advances in multimodal recommenders lack explicit reasoning and self-awareness of uncertainty.
Approach:	They propose a reasoning-augmented multimodal agent structured around a three-stage explicit reasoning pipeline.
Outcome:	The proposed agent improves ranking metrics and performance on four standard recommendation tasks across five real-world datasets.

Copied to clipboard

Yuru Jiang, Yang Xu, Yuhang Zhan, Weikai He, Yilin Wang, Zixuan Xi, Meiyun Wang, Xinyu Li, Yu Li, Yanchao Yu

LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation (2025.findings-emnlp)

Challenge:	Existing datasets focus on relation extraction between two entities in one sentence, and some focus on cross-sentence relationships.
Approach:	They propose to use a Chinese multi-party dialogue dataset for automatic extraction of dialogue-based character relationships.
Outcome:	The proposed dataset extracts relationships between 140 entities on the CRECIL corpus and another existing relation extraction corpus.

Copied to clipboard

Ming Zhang, Yujiong Shen, Zelin Li, Huayu Sha, Binze Hu, Yuhui Wang, Chenhao Huang, Shichun Liu, Jingqi Tong, Changhao Jiang, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)

Challenge:	Current medical benchmarks have limitations in question design, data sources and evaluation methods.
Approach:	They propose a new benchmark covering five core medical areas . it includes 2,996 questions created from real-world electronic health records .
Outcome:	The proposed model covers five core medical areas and includes 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios.

Copied to clipboard

Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du

FlagEval-Arena: A Side-by-Side Comparative Evaluation Platform for Large Language Models and Text-Driven AIGC (2025.acl-demo)

Challenge:	a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks.
Approach:	They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories .
Outcome:	The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points.

Copied to clipboard

Jing-Shu Zheng, Richeng Xuan, Bowen Qin, Zheqi He, Tongshuai.ren Tongshuai.ren, Xuejing Li, Jin-Ge Yao, Xi Yang

Incorporating Review-missing Interactions for Generative Explainable Recommendation (2025.coling-main)

Challenge:	a new evaluation platform for large language models and text-driven AIGCs is available for free.
Approach:	They propose an evaluation platform for side-by-side comparisons of large language models and text-driven AIGC systems.
Outcome:	a new evaluation platform for large language models and text-driven AIGC systems is available for free . the platform is more focused on the Chinese language and more models developed by Chinese institutes .

Copied to clipboard

Xi Li, Xiaohe Bo, Chen Ma, Xu Chen

Explainability & Interpretability in NLP

Challenge:	Existing models of explainable recommendation use user reviews as ground truths, but in practice, a large amount of users may not leave reviews after purchasing items.
Approach:	They propose to incorporate user preferences into explainable recommender models by leveraging generative models to predict the missing reviews and then training the model based on all the predicted and original reviews.
Outcome:	The proposed model improves the explanation quality on three publicly available datasets.

Evidence Retrieval is almost All You Need for Fact Verification (2024.findings-acl)

Copied to clipboard

Liwen Zheng, Chaozhuo Li, Xi Zhang, Yu-Ming Shang, Feiran Huang, Haoran Jia

Beyond Read-Only: Crafting a Comprehensive Chinese Text-to-SQL Dataset for Database Manipulation and Query (2024.findings-naacl)

Challenge:	Existing evidence retrieval methods adopt a trivial retrieval strategy, resulting in task-irrelevant evidence and undesirable performance.
Approach:	They propose a framework for evidence retrieval and joint fact verification that integrates two modules.
Outcome:	The proposed framework improves evidence retrieval and claims verification on a FEVER dataset.

Copied to clipboard

Xi Chen, Jinguo You, Likun Likun, Xiang Li

Diversity in Unity, Theory in Practice: Hierarchical Multitask Benchmarks for Chinese Minority Languages (2026.acl-long)

Challenge:	Current research focuses mainly on read operations and ignores other aspects of database operations such as create, update, and delete operations.
Approach:	They propose a large-scale cross-domain single-table CRUD operations Chinese Text-to-SQL dataset . the dataset contains 10,000 question/SQl pairs involving 625 tables from different domains .
Outcome:	The proposed method achieves 67.08% and 83.8% exact set matching accuracy under read and delete operations, but only 49.6% and 61.8% under create and update operations.

Copied to clipboard

Yijie Li, Xi Cao, Yuan Sun, Quulgan Minggad, Abdulla Ablikim, Jia Qing Cai Wang

Machine Translation

Challenge:	CMiLBench is a framework to evaluate linguistically and culturally diverse minority languages . rapid evolution of LLMs has revolutionized NLP, but progress is unevenly distributed .
Approach:	They propose a framework to translate a theoretical notion of "diversity in unity" into practical evaluation for three minority languages . CMiLBench comprises 24,663 instances across 5 difficulty levels and 17 tasks .
Outcome:	The proposed framework evaluates 14 state-of-the-art LLMs with a hybrid framework . it integrates automatic metrics and LLM-as-a-Judge scoring .

AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)

Copied to clipboard

Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E

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

Challenge:	AEGIS examines whether current models can effectively audit AI-generated images in academic papers.
Approach:	They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics.
Outcome:	AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis.

Copied to clipboard

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

BioGraphia: A LLM-Assisted Biological Pathway Graph Annotation Platform (2025.emnlp-demos)

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

Xi Xu, Sumin Jo, Adam Officer, Angela Chen, Yufei Huang, Lei Li

A Probabilistic Toolkit for Multi-grained Word Segmentation in Chinese (2025.coling-demos)

Challenge:	Existing methods for obtaining pathway information from biomedical literature rely on simplifying assumptions that limit their ability to capture true complexity of biological reactions.
Approach:	They propose a web-based platform to facilitate collaborative pathway graph annotation.
Outcome:	The platform supports multi-user collaboration with real-time monitoring, curation, and interactive pathway graph visualization.

Copied to clipboard

Xi Ma, Yang Hou, Xuebin Wang, Zhenghua Li

Syntactic Text Processing

Challenge:	Existing tools for word segmentation are based on different linguistic theories or target different scenarios.
Approach:	They propose a probabilistic toolkit for multi-grained word segmentation in Chinese . they adopt semi-Markov CRF for single-grain word segmenting (SWS) .
Outcome:	The proposed approach can produce marginal probabilities of words during inference and significantly improve performance in the cross-domain scenario.

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

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

Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning (2026.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

Junpeng Ding, Zichen Tang, Haihong E, Mengyuan Ji, Yang Liu, Haolin Tian, Haiyang Sun, Pengqi Sun, Yang Xu, Yichen Liu, Haocheng Gao, Zijie Xi, Ruomeng Jiang, Peizhi Zhao, Rongjin Li, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Jintong Chen, Siying Lin

Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience (2025.emnlp-main)

Challenge:	Xu and Peng, 2025) . . SPUR is a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images.
Approach:	They propose to use 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images to evaluate the visual perception of multimodal large language models (MLLMs) . they also propose to utilize cross-panel relation understanding to evaluate MLLM’s ability to decipher intricate cross-panel relations.
Outcome:	The proposed model is based on 4,264 question-answering pairs derived from 1,084 expert-curated images.

Copied to clipboard

Xi Wang, Songlei Jian, Shasha Li, Xiaopeng Li, Bin Ji, Ma Jun, Xiaodong Liu, Jing Wang, Jianfeng Zhang, Jie Yu, Feilong Bao, null Wangbaosheng

SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design (2025.emnlp-main)

Challenge:	Existing methods to generate human-aligned content with a “jailbreak prompt” are inefficient and repetitive, causing inefficiency and a lack of experience.
Approach:	They propose a framework that integrates past attack experiences to aid current jailbreak attempts.
Outcome:	The proposed framework improves both attack effectiveness and efficiency compared to the current black-box jailbreak method.

Copied to clipboard

Wenxin Tang, Jingyu Xiao, Wenxuan Jiang, Xi Xiao, Yuhang Wang, Xuxin Tang, Qing Li, Yuehe Ma, Junliang Liu, Shisong Tang, Michael R. Lyu

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

Challenge:	Existing natural language-based LLM generation methods struggle to capture visual and structural nuances of slide designs.
Approach:	They propose a layout-aware framework for generating editable slides from reference images . they propose python code that translates NL instructions into Python code to construct each slide .
Outcome:	The proposed framework outperforms state-of-the-art models by up to 40.5 points . it also outperformed open-source models with improved reverse-engineered data.

Copied to clipboard

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

From Scores to Preferences: Redefining Evaluation Paradigm for Speech Quality Reward Modeling (2026.findings-acl)

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

Yifei Cao, Changhao Jiang, Jiabao Zhuang, Jiajun Sun, Ming Zhang, Zhiheng Xi, Hui Li, Shihan Dou, Yuran Wang, Yunke Zhang, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features (N19-2)

Challenge:	Experimental results show that the MOS-aware GRM significantly improves fine-grained speech quality discrimination.
Approach:	They propose a MOS-aware reward model that incorporates MOS gap into reward function during reinforcement learning.
Outcome:	The proposed model significantly improves fine-grained speech quality discrimination.

Copied to clipboard

Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin

Challenge:	e-commerce companies often have the option of escalating complaints by filing grievances with a government authority . this is detrimental to an ecommerce company, but this problem is challenging to solve by integrating recurrent neural networks with manually-engineered features.
Approach:	They propose a model that integrates recurrent neural networks with manually-engineered features to identify cases where the customer expresses such an intent.
Outcome:	The proposed model outperforms baseline models and provides better recall and triage for specialized agents.

Easy and Efficient Transformer: Scalable Inference Solution For Large NLP Model (2022.naacl-industry)

Copied to clipboard

Gongzheng Li, Yadong Xi, Jingzhen Ding, Duan Wang, Ziyang Luo, Rongsheng Zhang, Bai Liu, Changjie Fan, Xiaoxi Mao, Zeng Zhao

HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation (2025.findings-acl)

Challenge:	Recent studies show that transformer-based models are effective over many tasks, but they are expensive to deploy in the industrial application.
Approach:	They propose a transformer-based inference solution that optimizes kernels for long inputs and large hidden sizes and a flexible CUDA memory manager to reduce the memory footprint when deploying a large model.
Outcome:	The proposed solution achieves an average speedup of 1.40-4.20x on the transformer decoder layer with an A100 GPU.

Copied to clipboard

Hao Liu, Zhengren Wang, Xi Chen, Zhiyu Li, Feiyu Xiong, Qinhan Yu, Wentao Zhang

Information Retrieval

Challenge:	Traditional retrieval systems focus on lexical or semantic similarity rather than logical relevance.
Approach:	They propose a new RAG framework that augments retrieval with logical reasoning . hopRAG uses a retrieve-reason-prune mechanism to explore multi-hop neighbors .
Outcome:	The proposed framework outperforms conventional retrieval systems and state-of-the-art benchmarks on multi-hop QA tasks.

InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model (2025.findings-acl)

Copied to clipboard

Siqi Ouyang, Xi Xu, Lei Li

Multilinguality

Challenge:	Existing models for simultaneous speech translation assume pre-segmented speech, limiting their real-world applicability.
Approach:	They propose a multi-turn dialogue task that can translate unbounded streaming speech . they construct translation trajectories and robust segments from MuST-C with multi-latency augmentation during training and develop a cache management strategy to facilitate efficient inference.
Outcome:	The proposed approach reduces computation-aware latency by 0.5 to 1 second while maintaining the same translation quality compared to baselines.

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)

Copied to clipboard

Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries (2026.acl-long)

Challenge:	Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations.
Approach:	They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference.
Outcome:	The proposed method significantly mitigates object hallucinations across various model architectures.

Copied to clipboard

Ki Sen Hung, Xi Yang, Chang Liu, Haoran Li, Kejiang Chen, Changxuan Fan, Tsun On Kwok, Weiming Zhang, Xiaomeng Li, Yangqiu Song

Characteristic AI Agents via Large Language Models (2024.lrec-main)

Challenge:	a goal of LLM alignment is to balance usefulness with harmlessness, but this conflictes when knowledge serves both legitimate and malicious purposes.
Approach:	They propose a framework that combines safety-research contexts with adversarial interactions to exploit a vulnerability in Jargon queries.
Outcome:	a framework outperforms existing methods in analyzing Jargon queries, a study shows . it achieves 93% of attacks across seven models, while remaining useful, the authors say .

Copied to clipboard

Xi Wang, Hongliang Dai, Shen Gao, Piji Li

Think Earlier, Not Longer: Prompt Optimization via Reducing Unhealthy Exploration (2026.findings-acl)

Challenge:	Commercial products have been devoted to creating character-driven chatbots using large language models, but academic research in this area remains relatively scarce.
Approach:	They investigate the performance of LLMs in constructing characteristic AI agents by simulating real-life individuals across different settings.
Outcome:	The proposed benchmark compared LLMs with real-life individuals in different settings and includes evaluation metrics.

Copied to clipboard

Ling-I Wu, Minyu Chen, Jingyang Li, Xi Chang, Guoqiang Li

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification (2026.acl-long)

Challenge:	Existing approaches to improve reasoning performance ignore the presence of unhealthy exploration that increases token usage without contributing to effective problem-solving.
Approach:	They propose an entropy-dynamics-aware prompt optimization framework that trains a lightweight optimizer to generate concise clarifications.
Outcome:	The proposed framework reduces ambiguity-induced early-stage uncertainty while preserving the model's reasoning capabilities.

Copied to clipboard

Xi Wang, Songlei Jian, Shasha Li, Xiaopeng Li, Zhaoye Li, Bin Ji, Baosheng Wang, Jie Yu

Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision (2026.acl-long)

Challenge:	Large Language Models (LLMs) are vulnerable to diverse jailbreak attacks despite extensive safety alignment .
Approach:	They propose a method to rectify dynamic jailbreak paths towards safety anchors by dynamically mining on-policy adversarial samples to expose vulnerabilities and identify jailbreak path.
Outcome:	The proposed model significantly improves jailbreak resistance against dynamic attacks while maintaining its utility.

Copied to clipboard

Bingsen Chen, Boyan Li, Ping Nie, Yuyu Zhang, Xi Ye, Chen Zhao

Challenge:	Existing benchmarks for Deep Research Agents (DRAs) treat report generation as a single-shot writing task.
Approach:	They propose an evaluation suite that establishes multi-turn report revision as a new axis.
Outcome:	The evaluation suite establishes multi-turn report revision as a new axis.

LoRACoE: Improving Large Language Model via Composition-based LoRA Expert (2025.emnlp-main)

Copied to clipboard

Guanyu Li, Zhiheng Xi, Zhihao Zhang, Boyang Hong, Tao Gui, Qi Zhang, Xuanjing Huang

Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs’ Hallucinations (2026.acl-long)

Challenge:	Recent studies show that the Mixture of Experts architecture improves performance of large language models.
Approach:	They propose a method to build static experts using LoRA parameters . they propose to use rank-level parameters to build experts based on rank-based parameters based in LoRA module.
Outcome:	The proposed method improves task performance across a broader range of tasks.

Copied to clipboard

Xinyue Fang, Zhiliang Tian, Zhen Huang, Ziyi Pan, Zhihua Wen, Xi Wang, Quntian Fang, Dongsheng Li

KuiLeiXi: a Chinese Open-Ended Text Adventure Game (2021.acl-demo)

Challenge:	Existing methods to mitigate hallucinations include prompt engineering and model optimization, but lack domain generalization and potential errors in fine-tuning data may exacerbate the hallucism.
Approach:	They propose an expert-aware adaptive contrast decoding that uses expert differences in MoE’s higher layers to mitigate hallucinations on QA tasks.
Outcome:	The proposed method outperforms baseline models on four datasets Large language models (LLMs) show strong performance but suffer from hallucinations, limiting their application.

Copied to clipboard

Yadong Xi, Xiaoxi Mao, Le Li, Lei Lin, Yanjiang Chen, Shuhan Yang, Xuhan Chen, Kailun Tao, Zhi Li, Gongzheng Li, Lin Jiang, Siyan Liu, Zeng Zhao, Minlie Huang, Changjie Fan, Zhipeng Hu

Adaptive Retrieval-Augmented Generation for Conversational Systems (2025.findings-naacl)

Challenge:	Recent advances in pre-trained language models have made it possible to generate human-like text.
Approach:	They propose to integrate an open-ended text adventure game in Chinese, named KuiLeiXi, where players interact with the AI until the plot goals are reached.
Outcome:	The proposed game lacks incentives and relies on players to explore on their own.

Copied to clipboard

Xi Wang, Procheta Sen, Ruizhe Li, Emine Yilmaz

Natural Language Interfaces

Challenge:	Existing studies have shown the effectiveness of retrieving and augmenting external knowledge for informative responses.
Approach:	They propose to use a gating model to predict if a conversational system requires retrieval-augmented generation to generate high-quality responses with high confidence.
Outcome:	The proposed model can predict if a conversational system requires RAG to generate high-quality responses with high confidence.

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

Copied to clipboard

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

Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration (2025.naacl-long)

Challenge:	Existing methods for deciphering ancient Chinese Oracle Bone Script (OBS) treat deciphering as a closed-set image recognition problem, which fails to bridge the "interpretation gap" .
Approach:	They propose a vision-language model framework that integrates a VLM and an LLM to automate a reasoning chain of component identification and knowledge retrieval.
Outcome:	The proposed framework yields more detailed and precise decipherments compared to baseline methods.

Copied to clipboard

Ang Li, Jingqian Zhao, Bin Liang, Lin Gui, Hui Wang, Xi Zeng, Xingwei Liang, Kam-Fai Wong, Ruifeng Xu