Papers by Xi He
Better Process Supervision with Bi-directional Rewarding Signals (2025.findings-acl)
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
| 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. |
Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models (2026.findings-acl)
Copied to clipboard
| 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. |
MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing evaluation metrics for memory-augmented dialogue systems lack practical value . current evaluation methods only consider passive memory retrieval while ignoring diverse memory recall with rich triggering factors. |
| Approach: | They propose to use long-term memory to create human-like dialogues using chatbots. |
| Outcome: | The proposed benchmark covers memory retrieval and memory recognition tasks with both passive and proactive memory recall data. |
Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to improve retrieval performance of large language models are limited by static knowledge. |
| Approach: | They propose a multimodal re-ranking framework that combines curriculum learning with fine-grained reranking and multimodal section reassessment to improve CLIP-based visual coarse-grain retrieval. |
| Outcome: | The proposed framework achieves state-of-the-art answer accuracy and competitive retrieval performance on InfoSeek and Enc-VQA. |
E-ConvRec: A Large-Scale Conversational Recommendation Dataset for E-Commerce Customer Service (2022.lrec-1)
Copied to clipboard
Meihuizi Jia, Ruixue Liu, Peiying Wang, Yang Song, Zexi Xi, Haobin Li, Xin Shen, Meng Chen, Jinhui Pang, Xiaodong He
| 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. |
AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)
Copied to clipboard
Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks. |
| Approach: | They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process. |
| Outcome: | The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS. |
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
| 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. |
Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling (2025.naacl-long)
Copied to clipboard
Yiwen Ding, Zhiheng Xi, Wei He, Lizhuoyuan Lizhuoyuan, Yitao Zhai, Shi Xiaowei, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Large language models (LLMs) generate solutions themselves and iteratively train on filtered, high-quality rationales, but performance reaches a ceiling after a few iterations. |
| Approach: | They propose a strategy to improve the efficiency of sampling heavy-tailed data by using Socratic-style guidance signals to help LLMs reasoning with complex queries. |
| Outcome: | The proposed approach is effective on difficult queries and on held-out tasks, while requiring human supervision. |
AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)
Copied to clipboard
Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Xin Guo, Dingwen Yang, Chenyang Liao, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang
| Challenge: | Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents. |
| Approach: | They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction. |
| Outcome: | The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction. |
ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis (2026.acl-long)
Copied to clipboard
| 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. |
CAPID: Context-Aware PII Detection for Question-Answering Systems (2026.eacl-srw)
Copied to clipboard
Mariia Ponomarenko, Sepideh Abedini, Masoumeh Shafieinejad, D. B. Emerson, Shubhankar Mohapatra, Xi He
| Challenge: | Existing approaches mainly redact all PII, disregarding the fact that some may be contextually relevant to the user’s question, resulting in a degradation of response quality. |
| Approach: | They propose a method that fine-tunes a locally owned small language model that filters sensitive information before it is passed to LLMs for QA. |
| Outcome: | The proposed approach outperforms baselines in span, relevance and type accuracy while preserving significantly higher utility under anonymization. |
FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation (2025.acl-demo)
Copied to clipboard
| 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. |
All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection (2026.acl-long)
Copied to clipboard
Yuechen Jiang, Zhiwei Liu, Yupeng Cao, Yueru He, Ziyang Xu, Chen Xu, Zhiyang Deng, Prayag Tiwari, Xi Chen, Alejandro Lopez-Lira, Jimin Huang, Junichi Tsujii, Sophia Ananiadou
| Challenge: | RFC-Bench evaluates large language models on financial misinformation under realistic news . current models struggle to maintain coherent belief states without external grounding, study finds . |
| Approach: | They propose a benchmark for evaluating large language models on financial misinformation under realistic news. |
| Outcome: | The proposed model performs better when context is available, while reference-free settings expose significant weaknesses. |
TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation (2026.findings-acl)
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
| 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
| 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. |
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)
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
| 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 . |
AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation (2026.findings-acl)
Copied to clipboard
Wentao Shi, Yu Wang, Yuyang Zhao, Yuxin Chen, Fuli Feng, Xueyuan Hao, Xi Su, Qi GU, Hui Su, Xunliang Cai, Xiangnan He
| Challenge: | Existing approaches to verify agent behaviors in complex environments rely on rule-based verifiers or LLM-as-a-Judge models. |
| Approach: | They propose a benchmark to evaluate Agent-as-a-Judge across three domains . the benchmark covers search, data systems, and graphical user interfaces - with 155 tasks and 516 trajectories . |
| Outcome: | The proposed benchmark outperforms existing benchmarks in search, data systems, and GUI domains while revealing open challenges in agent-based verification. |
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
| 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. |
The CRECIL Corpus: a New Dataset for Extraction of Relations between Characters in Chinese Multi-party Dialogues (2022.lrec-1)
Copied to clipboard
Yuru Jiang, Yang Xu, Yuhang Zhan, Weikai He, Yilin Wang, Zixuan Xi, Meiyun Wang, Xinyu Li, Yu Li, Yanchao Yu
| 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. |
FlagEval-Arena: A Side-by-Side Comparative Evaluation Platform for Large Language Models and Text-Driven AIGC (2025.acl-demo)
Copied to clipboard
Jing-Shu Zheng, Richeng Xuan, Bowen Qin, Zheqi He, Tongshuai.ren Tongshuai.ren, Xuejing Li, Jin-Ge Yao, Xi Yang
| 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 . |
SAME: Signer-Aware Mixture-of-Experts for Test-Time Adaptation in Sign Language Translation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for supervised fine-tuning are limited due to labeled data . existing methods require long adaptation times and batch statistics are unavailable in streaming settings . |
| Approach: | They propose a plug-and-play, signer-aware Mixture-of-Experts (MoE) TTA architecture for SLT . they use a combination of lightweight MoE modules and unsupervised regularizers to decouple domain shift . |
| Outcome: | The proposed test-time adaptation outperforms existing TTA methods in sign language translation . the proposed architecture can be used in real-world deployments without labeling . |
Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods that rely on limited demos and out-of-demonstration (OOD) queries fail when faced with out- of-demotion queries. |
| Approach: | They propose a query-aware prompting method that elicits the inherent generalizability of large language models by query-based demo generation. |
| Outcome: | The proposed method outperforms state-of-the-art methods in the OOD setting and two public math benchmarks. |
Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for embodied agents to learn and perform tasks use low-level instructions, which may not reflect natural human communication. |
| Approach: | They propose to use different types of language inputs to facilitate reinforcement learning (RL) embodied agents. |
| Outcome: | The proposed methods show that agents trained with diverse and informative language can achieve enhanced generalization and fast adaptation to new tasks in an open world. |
LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models (2026.acl-long)
Copied to clipboard
Jian Gao, Richeng Xuan, Zhaolu Kang, Dingshi Liao, Wenxin Huang, Zongmou Huang, Yangdi Xu, Bowen Qin, Zheqi He, Xi Yang, null Changjinli, Yonghua Lin
| Challenge: | Existing SEA-focused benchmarks miss Lao-specific cultural grounding and linguistic properties. |
| Approach: | They propose a multi-dimensional benchmark for assessing large language models in Lao . they use open-source and held-out subsets to evaluate languages with a hybrid pipeline . |
| Outcome: | LaoBench is the first large-scale, high-quality, and multidimensional benchmark for assessing LLM language understanding and reasoning in Lao. |
Distill Visual Chart Reasoning Ability from LLMs to MLLMs (2025.findings-emnlp)
Copied to clipboard
Wei He, Zhiheng Xi, Wanxu Zhao, Xiaoran Fan, Yiwen Ding, Zifei Shan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | a new method for generating chart annotations is proposed to improve visual reasoning in multimodal large language models. |
| Approach: | They propose a code-as-intermediary translation method for distilling visual reasoning abilities from LLMs to MLLMs. |
| Outcome: | The proposed method is cost-effective, efficient and scalable. |
Are LLMs Rational Investors? A Study on the Financial Bias in LLMs (2025.findings-acl)
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
| 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. |