NLPCC 2026
Oral Sessions
The 15th CCF International Conference on Natural Language Processing and Chinese Computing
Wednesday 4 November
Oral Session I
Wednesday, 4 November 2026 · 2:00–4:00 p.m. · MR 4+5
| No. | Paper ID | Paper Title | Authors |
|---|---|---|---|
| 1 | 126 | N:M-Aware Sparsification of Large Language Models via Shared-Axis Rotation | Chenhui Zhu; Hongxu Jiang; Yaochen Han; Runhua Zhang |
| 2 | 272 | Refining Large Language Model Quantization via Asymmetrically Scaled Affine Transformation | xuan xie; Bin Ji; Xiaodong Liu; Jinzhu Kong; Fan Xiaofeng; Linbo Li; Shasha Li; Ma Jun; Jie Yu |
| 3 | 386 | Outlier-Aware Mixed Sparsity Pruning for Encoder-Decoder Speech Models | Zhaolai Zhou; Zhe Wang; Chuanbo Liu; Lin Li |
| 4 | 635 | NASPEFT: Neural Architecture Search for Parameter-Efficient Fine-Tuning of Pre-trained Large Language Models | Martin Homweyetsuro; LALIT; Miao Zhang |
| 5 | 194 | Single-Pass Ensemble: Efficient Text Embeddings via KV-Shared Postfix Prompt Tuning | Weixin Wang; Yeqin Zhang; Yuzi Yang; Cam-Tu Nguyen |
| 6 | 307 | BaScan: Boundary-Aware Sequence Automaton for Retrieval-Based Speculative Decoding | Ang Li; Jiao Wu; Yuliang Lei; Kuangyu Zheng; Bingzhen Xie; Pan Lu; An Huang; Weihang Xu |
| 7 | 557 | LiveThinking: Enabling Real-Time Efficient Reasoning for AI-Powered Livestreaming via Reinforcement Learning | Junfeng Ma; Yuhan Sun; Wanqing Cui; Zhiwei Huang; Shaopan Xiong; Meiguang Jin; Xiaohu Yang |
| 8 | 135 | TFDT-LLM: Time-Frequency Dual-Tower Autoregressive Forecaster | Zhuoran Duan; Yongbin Liu; Chunping Ouyang; Ying Yu |
Oral Session II
Wednesday, 4 November 2026 · 2:00–4:00 p.m. · MR 8
| No. | Paper ID | Paper Title | Authors |
|---|---|---|---|
| 1 | 748 | Retrieval-Feedback Aligned Distillation for Deployable LLM Query Expansion | Minghan Li; Guodong Zhou |
| 2 | 330 | Do List-wise Rerankers Ignore Document Order? Position Bias Persists | NanHang Luo; Dongdong Xie; Jingcheng Yuan; Donghong Ji |
| 3 | 654 | EHHR-RAG: Evidence-Aware Hierarchical Hypergraph Retrieval Framework for Multi-Hop Adaptive Retrieval-Augmented Generation | Yunfei Chen; Yu Liu; Yongbiao Han; Siwei Wan; Teng Huang; Chen Qiu; Jinguang Gu |
| 4 | 830 | HyBridge-RAG: Robust Graph Retrieval via Hybrid Initialization and Entity Bridging Inference | Jinjie Hao; Guixuan Zhang; Ying Huang; Jie Liu; Shuwu Zhang |
| 5 | 354 | SAGE: Scalable Knowledge Integration for Large Language Models via Distributed Semantic Graphs | Yi-Chun Chang; Zixi Wang; Xinyu Wang |
| 6 | 377 | DisentRAG: Explicitly Disentangling Parametric and Contextual Knowledge in Retrieval-Augmented Generation | Yuning Wan; Jiaang Li; Quan Wang |
| 7 | 406 | S-CAD: Source-Calibrated Adaptive Decoding for Trustworthy Retrieval-Augmented Generation | Yalong Guo; Yangsen Zhang; Jing Kang; 王思维 |
| 8 | 770 | TASC: A Temporal Alignment and Snapshot-Consistency Framework for Time-Sensitive Question Answering | Jingyu Zhang; Meiqi Huang; luqing; Xiling Yang |
Oral Session III
Wednesday, 4 November 2026 · 2:00–4:00 p.m. · MR 9
| No. | Paper ID | Paper Title | Authors |
|---|---|---|---|
| 1 | 214 | From Diversity to Retrieval Robustness: Adapting Large Language Models to Complex Table Access | Jia Wang; Mingyu Zheng; Chenwang Zheng; Zheng Lin |
| 2 | 289 | STAR: A Multi-Agent Framework for Table Reasoning via Sub-Table Anchoring and Routing | Shuai Luo; Yanhua Yu; Ruopei Guo; WANG XiDian; Nan Cheng; Xin Gao; Zhiyong Huang; Haoyang Xu |
| 3 | 711 | SchemaRank: Structure-Aware Schema Linking via Graph Propagation for Text-to-SQL | Jingyu Zhang; Xu Zhang; Qing Lu; Shumin Li; Xiling Yang |
| 4 | 775 | Structural and Semantic-Aware Calibration for Semantic Parsing | Robert Ridley; Zhen Wu; Jianbing Zhang; Xinyu Dai |
| 5 | 516 | Multi-View Expansion for Field-Name-Robust Structured Extraction in Small Language Models | Chenzhang Guo; Wenbo Zhao; Xijun Wang; Limei Huang; Honghong Liao; Xiang Chen-SYSU |
| 6 | 622 | Calibrated and Conflict-Aware Rule Injection for Explainable Inductive Knowledge Graph Reasoning | 闫志聪; Hui Zhao |
| 7 | 349 | RepoCG: Python Call Graph Construction with Static Analysis and LLM-Assisted Call Resolution | Zhen Zhu; Jiaxin Li; Lin Peng; Lihua Yang; Linjin Wei; Xuwen Wang; Min Xie |
| 8 | 680 | Consistently Wrong: An Operand-Grounding Anatomy of Reliability in LLM Numerical Table Question Answering | Yifan Lu |
Oral Session IV
Wednesday, 4 November 2026 · 4:15–6:15 p.m. · MR 4+5
| No. | Paper ID | Paper Title | Authors |
|---|---|---|---|
| 1 | 266 | Optimizing Diversity and Correctness for Reliable LLM-Based Assertion Generation | ChengFeng Ge; Chunyan Hou; Chen Chen |
| 2 | 544 | LASER: Learning Active Perception via Self-Evolving Reasoning for GUI Grounding | Wanfu Wang; Qipeng Huang; Guangquan Xue; Xiaobo Liang; Qi Lv; XiaoLong Zhang; Zhe Zhao; Zhenxiang Yan; Juntao Li |
| 3 | 639 | Detected Is Not Enough: Risk-State Binding for Reliable Long-Horizon Data Agents | Xueyan Yao; Yuji Dong; Matilda Issac |
| 4 | 640 | FIG-MAC: A Fine-grained Inspiration Graph Empowered Multi-Agent Collaboration for Automated Scientific Hypothesis Generation | SiyuanChen; Yuping Gao; Tai Huang; Yuling Zhou; Dongyu Su; Tongguan Wang; Ying Sha |
| 5 | 801 | MACL-IOMA: A Unified Framework for Multi-LLM Co-Evolution via Cognitive Gap Quantification | Shihua Gou; Xinyu Hou; YIPING SONG |
| 6 | 827 | AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory | Zijie Cao; xijun qu; Zhicheng Gu; Xiaoshu Chen; Duanyang Yuan; Yanning Hou; Sihang Zhou; Jianxing Gong; Jian Huang; YANG Mei |
| 7 | 515 | Evaluating LLM Reliability in External SOP Execution: A Process-Level Study of Context Selection in Task-Oriented Dialogue | Shengyan Cai; Yang He; Renhong Liu; Lujun Yin |
| 8 | 789 | Learning Task Progress in Robot Manipulation from Suboptimal and Failed Policy Rollouts | Huaxi Ai; Li Zeng; Yuhang Guo |
Oral Session V
Wednesday, 4 November 2026 · 4:15–6:15 p.m. · MR 8
| No. | Paper ID | Paper Title | Authors |
|---|---|---|---|
| 1 | 218 | SimpleREA: A Lightweight Context Selection for Robust Multi-Turn Conversations | Zhaoning Zhang; hongwanyang |
| 2 | 603 | LEAP: LLM-Guided Experience Augmentation with MCTS Planning for Task-Oriented Dialogue Policy Learning | Renchao Xie; Yangyang Zhao |
| 3 | 591 | TRACE: Transition-aware Contrastive LLM-CRF for Emotional Support Strategy Prediction | Yu Zhang; Yulong Li; Jiaoyun Yang; honglin chen; Yan-Yan Chen; Ning An |
| 4 | 645 | WereToM: Benchmarking Theory of Mind for Social Deduction in LLMs | YimingQin; Bobo Li; Chong Teng; Fei Li; Donghong Ji |
| 5 | 815 | Reasoning in Buddhist Hetuvidya Debate: A Benchmark for Adjudication, Source Attribution, and Dynamic Commitment Tracking in LLMs | Ruiyin Qian; JiaxinYou; Xueer Wang; Daifeng Li |
| 6 | 677 | TTC: Term-Tree Coupled Agents for Pedagogical Vocabulary Construction | Ziyi Zhang; Guanlin Li; Guangfei Geng; ZHANG ZHE; Wang Zhimin |
| 7 | 484 | SimLearnerEval: Auditing Whether Simulated Learners Are Valid Measurement Instruments for Tutor-Policy Evaluation | Zijun Mao; Peng Zhang; Liu Lun; Haozhe Yang |
| 8 | 701 | SNEU-Guide: Traceable Evidence-State Evaluation for Chinese Tour-Guide Training | Guanheng Qu; Jingxiang Qiu; Na Li; Jiangming Liu |
Oral Session VI
Wednesday, 4 November 2026 · 4:15–6:15 p.m. · MR 9
| No. | Paper ID | Paper Title | Authors |
|---|---|---|---|
| 1 | 85 | MCEMA: Multi-Granularity Contrastive EM Attention Network for Fake News Video Detection | Yihao Wang; Zhong Qian; Peifeng Li; Qiaoming Zhu |
| 2 | 351 | Explaining to Detect: Improving Multimodal Metaphor Detection with Structured Explanation Supervision | Huiting Gao; Yongtao Wei; Yanquan Zhou |
| 3 | 407 | Multi-Granularity Sentiment Integration for LLM-Based Multimodal Sentiment Analysis | Shanshan Lin; Yuesheng Wu; Chao Chen; Yizhe Yang; Zhihao Chen; Zexian Yang; Xiangwen Liao |
| 4 | 502 | Listen Before You Look: Joint Visual-Audio Mixture of Retrieval Experts for Video Comprehension | Zhiqiao Wang; Xiaomei Chen; Haiwei Xue |
| 5 | 628 | TriCon-MEL: Candidate-Aware Triple Verification for Multimodal Entity Linking | Wenhao Xu; Yafei Jia; Xiaoying Pan; Hongcai Shen; Ruiqiang Lyu; Tingting Du; You Song |
| 6 | 806 | SIEVE: Sifting Hallucinated Visual Arguments in Multimodal Event Extraction via Training-Free Scene-Level Verification | Yuanye He; Shuhao Hu; Ji Xiang; Tianshu Fu; Zeyi Liu; Xin Wang |
| 7 | 614 | Enough to See, Not Enough to Answer: BIND-Probe for Multimodal Scientific Documents | Xuan Wang; Bo Wang; Ye Xiang; Ge Shi; Chong Feng |
| 8 | 231 | CORE-RL: Consistency-Oriented Reasoning Enhancement for Multimodal Mathematical Problem Solving | Xingyun Hong; Yan Shao; Shanshan Yan; Hui Liu |
Thursday 5 November
Oral Session VII
Thursday, 5 November 2026 · 1:00–3:00 p.m. · MR 8
| No. | Paper ID | Paper Title | Authors |
|---|---|---|---|
| 1 | 42 | LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering | Runze Ma; Shunbo Jia; Haonan Lyu; Guo Liu; Caizhi Liao |
| 2 | 374 | Didactic knowledge or Clinical Cases? How Data Types Shape Medical Large Language Models | Yuzheng Fan; Haochun Wang; Sendong Zhao; Han Xiao; Ming Ma; Bing Qin |
| 3 | 316 | MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chains for Clinical Diagnosis | Yuqi Zhan; Xinyue Wu; Tianyu Lin; Yutong Bao; Xiaoyu Wang; Weihao Cheng; Huangwei Chen; Feiwei Qin; Zhu Zhu |
| 4 | 721 | DiagState: Process-Level Evaluation and Stage-Aware State Tracking for Interactive Medical Diagnosis | Zhuoran Lu; Qihuang Zhong; Juhua Liu; Bo Du; Dehua Peng; Daojun Gong |
| 5 | 733 | ClinCog-Router: Target-Label-Free Answer-Utility Routing over Frozen Medical Adapter Banks | yining huang; Keke Tang; Meilian Chen |
| 6 | 768 | UICD: Uncertainty-Aware Iterative Contrastive Decoding for Radiology Report Generation | Xing Jia; Ailing Shen; Yun Xiong; Haofen Wang; Yichen Liu; Siqi Lin; 李柯曼; Chunlei Tang |
| 7 | 378 | EDSurv-Lite: A Strict Early-Window Benchmark for Multimodal ED Deterioration Prediction | Peilin Shen; Yulong Zheng |
| 8 | 427 | SAGE: Soft-gated Aggregation of Graded Experts for Cognitive Level Prediction in Video Interviews | Yan Luo; Huiyao Chen; Ramen Liu; Yumeng Fu; Kamal Elgallouch; Sanjida Ferdous; Meishan Zhang; Baotian Hu; Min Zhang |
Oral Session VIII
Thursday, 5 November 2026 · 1:00–3:00 p.m. · MR 9
| No. | Paper ID | Paper Title | Authors |
|---|---|---|---|
| 1 | 463 | CoReE-Net: Aligning Convolutional and Axial Reasoning for Document-Level Relation Extraction | Rongen Yan; Lixuan Zhou; Jinyi Zhan; Yakun Li; Fu Xu |
| 2 | 726 | CMNIE: An Information Extraction Benchmark for Chinese Military News | Yan Yu; Mengna Zhu; Zhenyu Song; Hao Yang; Haiwen Chen; Mao Wang |
| 3 | 851 | A Feature-Guided Framework for Zero-Shot Event Temporal Relation Extraction with Large Language Models | Qingkai Min; Yue Zhang |
| 4 | 428 | M2DO: A Prior-Guided Multi-View Decision-Optimized Framework for Short Text Classification | Mingle Zhou; Yiyue Liu; Yuan Gao; Min Li; Delong Han |
| 5 | 731 | SAFE: A Semantic Augmentation and Fusion Enhancement Method for Chinese Offensive Language Detection | Jingkai Lin; Ziqi Yin; Xinyi Li; Bo Chen; Jingbo Sun; Yubo Chen; Ge Gao; Xiaobing Zhao |
| 6 | 821 | Threshold-Stable Selective Classification for Freedom of Information Act Privilege Review | Shibo Niu; Ke He; Bolin Hu; Yuejia Li; Yi Zhu |
| 7 | 771 | Beyond Dialect Labels: Validation-Gated Sparse Features in Dialectalized Chinese Writing | Wanqin Zhou; Keyan Jin |
| 8 | 576 | CFEC-Bench: A Chinese Fact Error Correction Benchmark for Large Language Models | Qingcheng Xiao; Tan Yue; Wei Wang; Huishuai Zhang; Dongyan Zhao |
Oral Session IX
Thursday, 5 November 2026 · 3:15–5:15 p.m. · MR 8
| No. | Paper ID | Paper Title | Authors |
|---|---|---|---|
| 1 | 657 | Toward Fine-Grained Value Alignment for Chinese LLMs: A Value-Aware Modular Architecture with Reflection | Shenmeng Chen |
| 2 | 331 | PrefHCL: Human–AI Collaborative Text Detection via Multi-Style Preference Optimization with Hierarchical Contrastive Learning | Wangwang Zhan; HongChen Yu; Wenbo Li; Yangfan Zhang; Qianyu Xu; Wenliang Deng; Wu Guohua |
| 3 | 360 | TOSR: Task-Oriented Subspace Repair for Textual Backdoor Defense | Jiayi Li; Yuanchao Liu |
| 4 | 437 | BlackDecipher: Collaborative Weak Supervision for Robust Black-Box Membership Inference in LLMs | Wei Luo; Ruihan Hu; Yu-Ming Shang; Yong Ma; Sanchuan Guo; Xi Zhang |
| 5 | 574 | TRACE: Real-Time Token-Level Rectification for Safe and Capable LLM Generation | Pingyu Wu; Jiayu Wang; Wenbo Zhou; Weiming Zhang; Nenghai Yu |
| 6 | 836 | Code-ORBench: A Code-Oriented Over-Refusal Benchmark for Large Language Models | Yunxiang Wu; Qian Chen |
| 7 | 450 | Same Exam, Different Scores: A Tokenizer-Grounded Audit of Evaluation-Protocol Sensitivity on Chinese Benchmarks | Kun Zhang; Chunwei Xia |
| 8 | 303 | SCORE: Towards Robust Situational Cognitive Reasoning in LLMs | Yirui Wang; Kaicheng Yang; Yumeng Wang |
Oral Session X
Thursday, 5 November 2026 · 3:15–5:15 p.m. · MR 9
| No. | Paper ID | Paper Title | Authors |
|---|---|---|---|
| 1 | 719 | Curriculum-Based Incremental Evolution for Chinese ASR Post-Processing | Rui Wang; Ying Li; Yuan Li; Yuxin Huang; Shengxiang Gao; Cunli Mao; Zhengtao Yu |
| 2 | 526 | Text Judges Can't Hear: Prosodic Contrast Sets Expose Systematic Bias in Voice AI Evaluation | Adarsh Agrawal |
| 3 | 395 | BCP: A Lightweight Boundary-Controlled Framework for Online Sign Language Recognition and Translation | Xiao Ma; Lin Li; Shiqing Wu; Wang Gao; Chuanbo Liu; Jianquan Liu |
| 4 | 49 | Adaptive Denoising for Monolingual Domain Adaptation in kNN-MT | Hongyu Liu; yingfeng luo; Abudurexiti Reheman; Tong Xiao; JingBo Zhu |
| 5 | 107 | Lost in Interaction: Systematic Failures of MT and Automated Evaluation in Preserving Interpersonal Discourse Markers | Sirui Chen |
| 6 | 697 | Less Thinking, More Poetry: A Controlled Comparison of Reasoning and Non-Reasoning LLMs for Modern Chinese Poetry Translation | Bailiang Li; Wentao Zhang; Mu You; Jietian Tan; Junbin Zhang; Zehan Tan; Henghua Shen; Derek F. Wong; Tao Fang |