Lin Gui

Venues

Frequent coauthors

Papers

1. Beyond Perplexity: Let the Reader Select Retrieval Summaries via Spectrum Projection Score
   AAAI 2026 ·

   Zhanghao Hu

   DBLP profile ↗ORCID search ↗
2. MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents
   AAAI 2026 ·

   Yiming Du

   DBLP profile ↗ORCID search ↗
3. OSCR-Attack: One-Shot Character Level Attacks through Self-Optimizing Continuous Relaxation
   ACL 2026 ·

   Lingyi Kong

   DBLP profile ↗ORCID search ↗
4. SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding
   ACL 2026 ·

   Runcong Zhao

   DBLP profile ↗ORCID search ↗
5. Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering
   ACL 2025 ·

   Zhanghao Hu

   DBLP profile ↗ORCID search ↗
6. COPR: Continual Human Preference Learning via Optimal Policy Regularization
   ACL 2025 ·

   Han Zhang

   DBLP profile ↗ORCID search ↗
7. Centrality-guided Pre-training for Graph
   ICLR 2025 ·

   Bin Liang

   DBLP profile ↗ORCID search ↗
8. Correcting Large Language Model Behavior via Influence Function
   AAAI 2025 ·

   Han Zhang

   DBLP profile ↗ORCID search ↗
9. Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework
   EMNLP 2025 ·

   Cai Ke

   DBLP profile ↗ORCID search ↗
10. GraphMind: Interactive Novelty Assessment System for Accelerating Scientific Discovery
    EMNLP 2025 ·

    Italo Luis da Silva

    DBLP profile ↗ORCID search ↗
11. Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration
    NAACL 2025 ·

    Ang Li

    DBLP profile ↗ORCID search ↗
12. PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA
    ACL 2025 ·

    Xinyu Wang

    DBLP profile ↗ORCID search ↗
13. RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following
    ACL 2025 ·

    Junru Lu

    DBLP profile ↗ORCID search ↗
14. Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
    ICML 2025 ·

    Qinglin Zhu

    DBLP profile ↗ORCID search ↗
15. Sparse Activation Editing for Reliable Instruction Following in Narratives
    EMNLP 2025 ·

    Runcong Zhao

    DBLP profile ↗ORCID search ↗
16. Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Time
    EMNLP 2025 ·

    Jiazheng Li

    DBLP profile ↗ORCID search ↗
17. Addressing Order Sensitivity of In-Context Demonstration Examples in Causal Language Models
    ACL 2024 ·

    Yanzheng Xiang

    DBLP profile ↗ORCID search ↗
18. Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
    ICML 2024 ·

    Shenzhi Yang

    DBLP profile ↗ORCID search ↗
19. CPPO: Continual Learning for Reinforcement Learning with Human Feedback
    ICLR 2024 ·

    Han Zhang

    DBLP profile ↗ORCID search ↗
20. Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective
    EMNLP 2024 ·

    Hanqi Yan

    DBLP profile ↗ORCID search ↗
21. Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives
    ACL 2024 ·

    Runcong Zhao

    DBLP profile ↗ORCID search ↗
22. Mirror: Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning
    ACL 2024 ·

    Hanqi Yan

    DBLP profile ↗ORCID search ↗
23. Multi-Layer Ranking with Large Language Models for News Source Recommendation
    SIGIR 2024 ·

    Wenjia Zhang

    DBLP profile ↗ORCID search ↗
24. Multi-modal Stance Detection: New Datasets and Model
    ACL 2024 ·

    Bin Liang

    DBLP profile ↗ORCID search ↗
25. NarrativePlay: An Automated System for Crafting Visual Worlds in Novels for Role-Playing
    AAAI 2024 ·

    Runcong Zhao

    DBLP profile ↗ORCID search ↗
26. The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis
    EMNLP 2024 ·

    Yuxiang Zhou

    DBLP profile ↗ORCID search ↗
27. Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond
    ACL 2024 ·

    Xinyu Wang

    DBLP profile ↗ORCID search ↗
28. Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems
    EMNLP 2024 ·

    Italo Luis da Silva

    DBLP profile ↗ORCID search ↗