📝 Publications

Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
Qinglin Zhu, Runcong Zhao, Hanqi Yan, Yulan He, Yudong Chen, Lin Gui.

• We propose an embedding-based search framework that optimises the embedding of the first token to guide generation. It combines
• (1) Embedding perturbation for controlled exploration and
• (2) Bayesian optimisation to refine embeddings via a verifier-guided objective, balancing exploration and exploitation.

Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering
Zhanghao Hu, Hanqi Yan, Qinglin Zhu†, Zhenyi Shen, Yulan He, Lin Gui.

• Proposes EmbQA, an embedding-level framework for open-domain QA that optimizes retrieval with unsupervised contrastive learning and improves answer diversity via exploratory embeddings.
  

Sparse Activation Editing for Reliable Instruction Following in Narratives
Runcong Zhao, Chengyu Cao, Qinglin Zhu, Xiucheng Lv, Shun Shao, Lin Gui, Ruifeng Xu, Yulan He.

• We introduce Concise-SAE, a training-free method that improves instruction following by editing relevant neurons using natural language instructions.
• Tested on our new FreeInstruct benchmark of 1,212 narrative-rich examples, it achieves state-of-the-art results without training or labelled data.

Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning
Hanqi Yan*, Qinglin Zhu* , Xinyu Wang, Lin Gui, Yulan He.

• Proposes Mirror, enabling LLMs to reflect from multiple perspectives via Navigator–Reasoner cooperation.
  
• Encourages both diverse and consistent reasoning to overcome self-reflection traps.
  

Spectrum Projection Score: Aligning Retrieved Summaries with Reader Models in Retrieval-Augmented Generation
Zhanghao Hu, Qinglin Zhu, Siya Qi, Yulan He, Hanqi Yan, Lin Gui.

• Proposes SPS, a supervision-free metric to assess semantic alignment between retrieved summaries and LLM representations.
  
• Introduces xCompress, an inference-time controller that ranks and compresses retrievals to improve generation and clarify retrieval–generation interaction.
  </div>

Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives
Runcong Zhao*, Qinglin Zhu* , Hainiu Xu, Jiazheng Li, Yuxiang Zhou, Yulan He, Lin Gui.

• Existing datasets for narrative understanding often fail to represent the complexity and uncertainty of relationships in real-life social scenarios.
• To address this gap, we introduce a new benchmark, Conan, designed for extracting and analysing intricate character relation graphs from detective narratives.

PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games
Qinglin Zhu, Runcong Zhao, Jinhua Du, Lin Gui, Yulan He.

• We propose PLAYER*, a novel framework for Murder Mystery Games (剧本杀) using an anytime sampling-based planner and a questioning-driven search framework.

SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding
Runcong Zhao, Qinglin Zhu*, Hainiu Xu, Bin Liang, Yulan He, Lin Gui.

• Proposes SymbolicThought, a human-in-the-loop system combining LLM extraction and symbolic reasoning for character relationship understanding.
• Supports editable relationship graphs, logical constraints, and interactive conflict resolution.