collaborators

6 papers

cs.CL2026

Why Retrieval-Augmented Generation Fails: A Graph Perspective

Kai Guo, Xinnan Dai, Zhibo Zhang +5

Retrieval-Augmented Generation (RAG) has become a powerful and widely used approach for improving large language models by grounding generation in retrieved evidence. However, RAG…

cs.AI2026

When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression

Xinnan Dai, Kai Yang, Cheng Luo +3

Reasoning hallucinations in large language models (LLMs) often appear as fluent yet unsupported conclusions that violate either the given context or underlying factual knowledge. A…

cs.IR2026

Fix Before Search: Benchmarking Agentic Query Visual Pre-processing in Multimodal Retrieval-augmented Generation

Jiankun Zhang, Shenglai Zeng, Kai Guo +4

Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a key paradigm for grounding MLLMs with external knowledge. While query pre-processing (e.g., rewriting) is standard…

cs.CL2026

GraphGhost: Tracing Structures Behind Large Language Models

Xinnan Dai, Xianxuan Long, Chung-Hsiang Lo +4

Large Language Models (LLMs) exhibit strong reasoning capabilities on structured tasks, yet the internal mechanisms underlying such behaviors remain poorly understood. Existing int…

cs.CL2025

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers

Xinnan Dai, Kai Yang, Jay Revolinsky +4

Recent studies suggest that large language models (LLMs) possess the capability to solve graph reasoning tasks. Notably, even when graph structures are embedded within textual desc…

cs.LG2025

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing

Xinnan Dai, Chung-Hsiang Lo, Kai Guo +3

Transformer-based LLMs demonstrate strong performance on graph reasoning tasks, yet their internal mechanisms remain underexplored. To uncover these reasoning process mechanisms in…