6 papers
Uncertainty-Aware Clarification in LLM Agents with Information Gain
Mengyi Deng, Zhiwei Li, Xin Li +4
Large Language Model (LLM) agents often operate under underspecified user instructions, where latent uncertainty over user intent leads to erroneous tool actions. To address this c…
DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
Mengyi Deng, Zhiwei Li, Xin Li +4
Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consistency while preserving reason…
BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs
Duyi Pan, Tianao Lou, Xin Li +5
Large Language Models (LLMs) exhibit hallucinations in knowledge-intensive tasks. Graph-based retrieval augmented generation (RAG) has emerged as a promising solution, yet existing…
Structure-Aware Epistemic Uncertainty Quantification for Neural Operator PDE Surrogates
Haoze Song, Zhihao Li, Mengyi Deng +4
Neural operators (NOs) provide fast, resolution-invariant surrogates for mapping input fields to PDE solution fields, but their predictions can exhibit significant epistemic uncert…
An Attention-Enhanced Φ-OTDR Event Recognition Framework for Edge-Based Distributed Acoustic Sensing
Xiyang Lan, Xin Li, Yinglei Teng
Phase-sensitive optical time-domain reflectometry Φ-OTDR has emerged as a promising sensing technology in Internet of Things (IoT) infrastructures, enabling large-scale distribute…
When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning
Mengyi Deng, Xin Li, Tingyu Zhu +3
Existing work has shown that o1-level performance can be achieved with limited data distillation, but most existing methods focus on unidirectional supervised fine-tuning (SFT), ov…