Cover Image

What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chang, Zhiyuan, Li, Mingyang, Jia, Xiaojun, Wang, Junjie, Huang, Yuekai, Wang, Qing, Huang, Yihao, Liu, Yang
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
by: Chang, Zhiyuan, et al.
Published: (2026)

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
by: Chang, Zhiyuan, et al.
Published: (2025)

Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
by: Jiang, Ziyou, et al.
Published: (2025)

All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
by: Jiang, Ziyou, et al.
Published: (2026)

Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval
by: Wang, Wenshuo, et al.
Published: (2025)

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
by: Wang, Haowei, et al.
Published: (2024)

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
by: Wang, Haowei, et al.
Published: (2025)

DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections
by: Park, Jiwon, et al.
Published: (2025)

Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA
by: Wu, Yuchen, et al.
Published: (2025)

NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts
by: Gupta, Abhay, et al.
Published: (2025)

VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing
by: Chang, Zhiyuan, et al.
Published: (2024)

ReasVQA: Advancing VideoQA with Imperfect Reasoning Process
by: Liang, Jianxin, et al.
Published: (2025)

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning
by: Wang, Shenzhi, et al.
Published: (2026)

FinReflectKG -- MultiHop: Financial QA Benchmark for Reasoning with Knowledge Graph Evidence
by: Arun, Abhinav, et al.
Published: (2025)

ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA
by: Zhao, Xinjie, et al.
Published: (2025)

Adversarial Robustness of Open-source Text Classification Models and Fine-Tuning Chains
by: Qin, Hao, et al.
Published: (2024)

DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
by: Wang, Changhao, et al.
Published: (2025)

MoreHopQA: More Than Multi-hop Reasoning
by: Schnitzler, Julian, et al.
Published: (2024)

Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems
by: Xiong, Qian, et al.
Published: (2025)

Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration
by: Liu, Zijun, et al.
Published: (2025)

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
by: Chang, Zhiyuan, et al.
Published: (2024)

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement
by: Chang, Zhiyuan, et al.
Published: (2024)

The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA
by: Zarrinkia, Yasaman, et al.
Published: (2026)

Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning
by: Wang, Jianing, et al.
Published: (2023)

Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs
by: Wang, Xudong, et al.
Published: (2026)

Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA
by: Wang, Qizhi
Published: (2025)

Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
by: Wang, Minzheng, et al.
Published: (2024)

Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning
by: Choi, Minseok, et al.
Published: (2024)

Adversarial Testing for Visual Grounding via Image-Aware Property Reduction
by: Chang, Zhiyuan, et al.
Published: (2024)

ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty
by: Zong, Qing, et al.
Published: (2024)

Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge
by: Zhang, Haotong
Published: (2024)

AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
by: Wang, Haowei, et al.
Published: (2025)

Explore-Construct-Filter: An Automated Framework for Rich and Reliable API Knowledge Graph Construction
by: Sun, Yanbang, et al.
Published: (2025)

Characterizing LLM Abstention Behavior in Science QA with Context Perturbations
by: Wen, Bingbing, et al.
Published: (2024)

Lost in the Middle, and In-Between: Enhancing Language Models' Ability to Reason Over Long Contexts in Multi-Hop QA
by: Baker, George Arthur, et al.
Published: (2024)

Unblind Text Inputs: Predicting Hint-text of Text Input in Mobile Apps via LLM
by: Liu, Zhe, et al.
Published: (2024)

DeepRAG: Integrating Hierarchical Reasoning and Process Supervision for Biomedical Multi-Hop QA
by: Ji, Yuelyu, et al.
Published: (2025)

RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
by: Yang, Ruiyi, et al.
Published: (2025)

Calibrated Fusion for Heterogeneous Graph-Vector Retrieval in Multi-Hop QA
by: Bacellar, Andre
Published: (2026)

Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos
by: Chen, Qirui, et al.
Published: (2024)