Papers by Xin Zeng

UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models (2026.acl-demo)

Challenge:	Mental health disorders represent a burgeoning global public health challenge . lack of ecological validity and fine-grained diagnostic supervision limits their utility .
Approach:	They propose a medical-specialized LLM trained to internalize clinical reasoning process through supervised trajectory construction and curriculum-based reinforcement learning.
Outcome:	The proposed model achieves state-of-the-art with only 14B parameters, establishing a clinically grounded framework for reliable psychiatric diagnosis.

Copied to clipboard

Qundong Shi, Jie Zhou, Biyuan Lin, Junbo Cui, Guoyang Zeng, Yixuan Zhou, Ziyang Wang, Xin Liu, Zhen Luo, Yudong Wang, Zhiyuan Liu

Bridging the Granularity Gap for Acoustic Modeling (2023.findings-acl)

Challenge:	Existing evaluation frameworks for audio foundation models are heavily reliant on English, making it difficult to objectively assess models’ performance on Chinese.
Approach:	They propose a unified framework that supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards.
Outcome:	The proposed framework supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards.

Copied to clipboard

Chen Xu, Yuhao Zhang, Chengbo Jiao, Xiaoqian Liu, Chi Hu, Xin Zeng, Tong Xiao, Anxiang Ma, Huizhen Wang, Jingbo Zhu

MixTEA: Semi-supervised Entity Alignment with Mixture Teaching (2023.findings-emnlp)

Challenge:	Despite the success of speech recognition, how to encode the speech features effectively remains an open problem.
Approach:	They propose a Progressive Down-Sampling technique which compresses acoustic features into coarser-grained units containing more complete semantic information, like text-level representation.
Outcome:	The proposed method yields comparable or better results on the speech recognition task and inference speedups ranging from 1.20x to 1.47x.

Copied to clipboard

Feng Xie, Xin Song, Xiang Zeng, Xuechen Zhao, Lei Tian, Bin Zhou, Yusong Tan

Low-Resource NLP

Challenge:	Existing methods to learn informative entity embeddings are insufficient for semi-supervised entity alignment.
Approach:	They propose a semi-supervised method which guides the model learning with an end-to-end mixture teaching of manually labeled mappings and probabilistic pseudo mappings.
Outcome:	The proposed method is superior to existing methods on benchmark datasets and further analyses.

HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks (2026.findings-acl)

Copied to clipboard

Yiming Zeng, Jinghan Cao, Zexin Li, Wanhao Yu, Zhankai Ye, Dawei Xiang, Ting Hua, Xin Liu, Shangqian Gao, Tingting Yu

Text Generation

Challenge:	Existing approaches treat instruction-based text editing as a generic text generation problem. Existing methods either over-edit or fail to apply modifications consistently.
Approach:	They propose a framework that processes each editing request to best align with it.
Outcome:	The proposed framework achieves 9% improvement over the state-of-the-art model.

No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning (2026.acl-long)

Copied to clipboard

Zhicong Li, Lingjie Jiang, Yulan Hu, Xingchen Zeng, Yixia Li, Xiangwen Zhang, Guanhua Chen, Zheng Pan, Xin Li, Yong Liu

Challenge:	Current methods for training Large Language Model agents rely on static or offline critic models, which fail to adapt as the policy evolves.
Approach:	They propose a framework that integrates a critique and a policy to optimize the policy and critic through a synchronized co-evolutionary loop.
Outcome:	The proposed framework yields more stable training and higher long-horizon task success across open-world environments.

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoning (2025.emnlp-main)

Copied to clipboard

Zezhong Wang, Xingshan Zeng, Weiwen Liu, Yufei Wang, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong

ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation (2022.acl-long)

Challenge:	Existing methods that use Chain-of-Thought suffer from path homogenization and inefficient use of intermediate results.
Approach:	They propose a framework that introduces checkpoints between reasoning steps to reduce path homogenization and create fault-tolerant mechanisms.
Outcome:	The proposed framework reduces path homogenization and creates fault-tolerant mechanism by utilizing high-quality intermediate results.

Copied to clipboard

Bei Li, Quan Du, Tao Zhou, Yi Jing, Shuhan Zhou, Xin Zeng, Tong Xiao, JingBo Zhu, Xuebo Liu, Min Zhang

Sailor: Open Language Models for South-East Asia (2024.emnlp-demo)

Challenge:	Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE).
Approach:	They propose a residual block of layers in Transformer that can be described as a higher-order solution to ODE.
Outcome:	The proposed architecture can gain large improvements over strong baselines at a slight cost in inference efficiency.

Copied to clipboard

Longxu Dou, Qian Liu, Guangtao Zeng, Jia Guo, Jiahui Zhou, Xin Mao, Ziqi Jin, Wei Lu, Min Lin

Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning (2026.findings-acl)

Challenge:	Large language models (LLMs) rely on English data for training, but are often not comparable across other languages.
Approach:	They propose to develop a family of open language models for SEA languages . they use BPE dropout, aggressive data cleaning and deduplication to improve model robustness .
Outcome:	The proposed models perform well across four benchmarks, including commonsense reasoning, question answering, reading comprehension and examination.

Copied to clipboard

Fengran Mo, Yifan Gao, Sha Li, Hansi Zeng, Xin Liu, Zhaoxuan Tan, Xian Li, Jianshu Chen, Dakuo Wang, Meng Jiang

Natural Language Interfaces

Challenge:	Existing studies focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions.
Approach:	They propose a conversational agent that interleaves search and reasoning across turns and provides tailored rewards towards evolving user goals.
Outcome:	The proposed agent interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals.

Learning to Edit: Aligning LLMs with Knowledge Editing (2024.acl-long)

Copied to clipboard

Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang

Challenge:	Existing knowledge editing techniques rely on memorizing updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions.
Approach:	They propose a Learning to Edit framework that equips LLMs with the ability to apply updated knowledge to input questions through a two-phase process .
Outcome:	The proposed framework outperforms existing methods in knowledge editing tasks and compares it with four benchmarks and two LLM architectures.

Getting the Most out of Simile Recognition (2022.findings-emnlp)

Copied to clipboard

Xiaoyue Wang, Linfeng Song, Xin Liu, Chulun Zhou, Hualin Zeng, Jinsong Su

Challenge:	Recent work ignores features other than surface strings and suffers from data hunger issue.
Approach:	They propose to use simile sentence classification and simile component extraction to find simile components.
Outcome:	The proposed model outperforms current state-of-the-art systems and baselines.

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Copied to clipboard

Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

Multilinguality

Challenge:	Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach:	They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome:	The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.

Global Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation (2026.findings-acl)

Copied to clipboard

Yubo Jiang, Xin Yang, Abudukelimu Wuerkaixi, Zheming Yuan, Xuxin Cheng, Cao Liu, Ke Zeng, Fengying Xie, Zhiguo Jiang, Haopeng Zhang

ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis (2025.naacl-long)

Challenge:	Large vision–language models suffer from object-existence hallucinations when multi-step deliberation decouples from visual evidence.
Approach:	They propose a framework that allocates visual computation by uncertainty . they propose highlighting retains global context, while selective zoom-in performs local verification.
Outcome:	The proposed framework reduces the complexity of multimodal reasoning by minimizing the operator trade-off.

Copied to clipboard

Zezhong Wang, Xingshan Zeng, Weiwen Liu, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models (LLMs) can be enhanced by using supervised fine-tuning . however, access to fine-timing data can be limited.
Approach:	They propose a Graph-based Sampling strategy and a Planned-generation strategy to enhance the coherence between dialogues by using 8,000 synthetic dialogues.
Outcome:	The proposed model achieves tool-calling performance comparable to or surpassing GPT-4 while maintaining strong general capabilities.

FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models (2024.acl-long)

Copied to clipboard

Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, Wei Wang

VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding (2025.emnlp-main)

Challenge:	Existing benchmarks focus on evaluating pure response quality, rather than assessing whether the response follows constraints stated in the instruction.
Approach:	They propose a Multi-level Fine-grained Constraints Following Benchmark for Large Language Models that adds a single constraint to the initial instruction at each increased level.
Outcome:	The proposed model can follow instructions with more constraints, and is deemed to have better instruction-following ability.

Copied to clipboard

Zhaowei Liu, Xin Guo, Haotian Xia, Lingfeng Zeng, Fangqi Lou, Jinyi Niu, Mengping Li, Qi Qi, Jiahuan Li, Wei Zhang, Yinglong Wang, Weige Cai, Weining Shen, Liwen Zhang

When 20 Agents Fail to Sort: The Distributed Sorting Benchmark for Scalable Multi-Agent Systems (2026.findings-acl)

Challenge:	Existing benchmarks focus on text comprehension, but MLLMs lack the ability to integrate visual data over financial visuals.
Approach:	They evaluate 21 state-of-the-art multimodal large language models in a zero-shot setting . they use an annotated question–answer pair from eight common financial image modalities .
Outcome:	The new benchmark outperforms existing models but trailed financial experts by 14 percentage points.

Copied to clipboard

Xin Yang, Junhao Wang, Bintao Tang, Xuxin Cheng, Cao Liu, Ke Zeng, Wenyuan Jiang

Challenge:	MAS-BENCH isolates coordination under explicit communication constraints . CAMOC significantly improves coordination success and efficiency across backends .
Approach:	They propose a distributed-sorting benchmark that isolates coordination under explicit communication constraints.
Outcome:	MAS-BENCH improves coordination success and efficiency across backends . CAMOC significantly improves efficiency under shared-state interaction .

Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning (2026.findings-acl)

Copied to clipboard

Xinyan Guan, Jiali Zeng, Chunlei Xin, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Fandong Meng

Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step (2025.findings-naacl)

Challenge:	Large language models generate costly yet semantically void reasoning on beyond-capability tasks . the dominant failure mode is specious reasoning, superficially valid outputs with subtle hallucinations .
Approach:	They propose a capability-aligned reinforcement learning approach that aligns model behavior with capability boundaries.
Outcome:	The proposed model reduces futile reasoning while maintaining performance across tasks.

Copied to clipboard

Zezhong Wang, Xingshan Zeng, Weiwen Liu, Yufei Wang, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong

DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens (2025.findings-acl)

Challenge:	Current research found the issue of Early Answering in large language models where the models already have an answer before generating the Chain-of-Thought (CoT).
Approach:	They propose a method to probe changes in confidence during the model’s reasoning and prioritize answers with correct reasoning among multiple candidates.
Outcome:	The proposed method reveals that in a significant number of question-answer cases, CoT appears to be unnecessary and this necessity correlates with the simplicity of the task, defined by the reasoning steps required.

Copied to clipboard

Shaoshen Chen, Yangning Li, Zishan Xu, Yongqin Zeng, Shunlong Wu, Xinshuo Hu, Zifei Shan, Xin Su, Jiwei Tang, Yinghui Li, Hai-Tao Zheng

Challenge:	Existing semantic vector-based compression methods do not account for the intrinsic information density variations between context chunks, instead allocating soft tokens uniformly across context chunk.
Approach:	They propose a method that leverages the LLM's intrinsic understanding of contextual relevance to guide compression.
Outcome:	The proposed method surpasses state-of-the-art methods on long context tasks.

LCQMC:A Large-scale Chinese Question Matching Corpus (C18-1)

Copied to clipboard

Xin Liu, Qingcai Chen, Chong Deng, Huajun Zeng, Jing Chen, Dongfang Li, Buzhou Tang

Paraphrasing

Challenge:	Existing methods for question answering system lack large-scale question matching corpora . lack of large-sized question matching results in problem solving .
Approach:	They propose a large-scale Chinese question matching corpus which is released to the public . they use a search engine to collect large-sized question pairs related to high-frequency words .
Outcome:	The proposed corpus is more general than paraphrase corpus as it focuses on intent matching rather than paraphrasing.

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (2024.acl-long)

Copied to clipboard

Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li

Multilinguality

Challenge:	Large language models (LLMs) can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports, and codebases.
Approach:	They propose a bilingual, multi-task benchmark for long context understanding that extends context windows and more sophisticated memory mechanisms to improve models' long context capabilities.
Outcome:	The proposed model outperforms open-source models but struggles on longer contexts.

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)

Copied to clipboard

Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Han Zhang, Yu-Kun Li, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang

Semantic Text Processing

Challenge:	Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive.
Approach:	They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory .
Outcome:	The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient.

Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios (2024.findings-acl)

Copied to clipboard

Shijue Huang, Wanjun Zhong, Jianqiao Lu, Qi Zhu, Jiahui Gao, Weiwen Liu, Yutai Hou, Xingshan Zeng, Yasheng Wang, Lifeng Shang, Xin Jiang, Ruifeng Xu, Qun Liu

TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents (2026.findings-acl)

Challenge:	Existing benchmarks focus on simple synthesized queries that do not reflect real-world complexity, thereby offering limited perspectives in evaluating tool utilization.
Approach:	They propose a benchmark to evaluate LLMs’ ability in tool utilization within real-world scenarios.
Outcome:	The proposed benchmark improves LLMs’ ability in tool utilization within real-world scenarios and eliminates the restriction of pre-defined toolset.

Copied to clipboard

Kai Li, Xuanqing Yu, Ziyi Ni, Yi Zeng, Yao Xu, Zheqing Zhang, Xin Li, Jitao Sang, Xiaogang Duan, Xuelei Wang, Chengbao Liu, Jie Tan

Dialogue Systems & Conversational Agents

Challenge:	Existing memory frameworks provide limited support for temporally structured information across hierarchical levels, leading to fragmented memories and unstable long-horizon personalization.
Approach:	They propose a temporal–hierarchical memory framework that organizes conversations through a Temporal Memory Tree.
Outcome:	The proposed framework outperforms baselines while reducing the recalled memory length by 52.20%.

A Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification (N19-1)

Copied to clipboard

Ziqian Zeng, Wenxuan Zhou, Xin Liu, Yangqiu Song

Sentiment Analysis

Challenge:	Existing weakly supervised methods for document-level multi-aspect sentiment classification are not easy to obtain.
Approach:	They propose a variational approach to weakly supervised document-level multi-aspect sentiment classification using target-opinion word pairs as "supervision" they aim to learn a sentiment polarity classifier by optimizing the lower bound .
Outcome:	The proposed method outperforms weakly supervised baselines on TripAdvisor and BeerAdvocate datasets and can be comparable to state-of-the-art supervised methods with hundreds of labels per aspect.

MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models (2024.emnlp-main)

Copied to clipboard

Wai-Chung Kwan, Xingshan Zeng, Yuxin Jiang, Yufei Wang, Liangyou Li, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong