When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trust problem: retrieved context may be useful, irrelevant, or even misleading. Existing RAG systems often apply a fixed trust policy toward retrieved evidence, which can either over-trust incorrect context or underuse context when the user explicitly asks for context-following behavior. Therefore, we propose Intent-Guided Decoding (IGD), a framework that arbitrates between retrieved context and parametric memory according to user intent. IGD uses answer-level filtering and token-level correction to steer the final decoding trajectory between retrieved context and parametric memory. We evaluate IGD on three faithful QA benchmarks and three factual-conflict benchmarks across five LLMs, IGD substantially improves factual recovery, achieving gains of up to 65.4 percentage points on factual-conflict benchmarks over Direct RAG, while preserving or improving strict context-following behavior, this findings highlight the importance of balancing factuality and faithfulness in RAG.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models
Diffusion language models decode text by iteratively denoising masked token sequences, making the choice of which positions to decode a central inference-time decision. Most training-free decoding strategies use model co…
Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language Models
Egocentric vision offers a first-person view of human perception and decision making, yet its potential for traffic-safety prediction remains underexplored. In this work, we study the decoding of pedestrian crossing inte…
parameter-efficient fine-tuningVisual Question AnsweringDecision MakingLost in Decoding? Reproducing and Stress-Testing the Look-Ahead Prior in Generative Retrieval
Generative retrieval (GR) ranks documents by autoregressively generating document identifiers. Because many GR methods rely on trie-constrained beam search, they are vulnerable to early pruning of relevant prefixes under…
Emotion and Intention Guided Multi-Modal Learning for Sticker Response Selection
Stickers are widely used in online communication to convey emotions and implicit intentions. The Sticker Response Selection (SRS) task aims to select the most contextually appropriate sticker based on the dialogue. Howev…
Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks. Malicious users often exploit adversarial context to deceive L…