CLIRFeb 19, 2025

Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach

arXiv:2502.14100v25 citationsh-index: 16ACL
Originality Incremental advance
AI Analysis

This addresses the issue of misleading and unhelpful contexts in LLMs for applications like RAG, though it appears incremental as it builds on existing fine-tuning methods.

The paper tackles the problem of LLMs over-relying on imperfect external contexts in retrieval-augmented generation, proposing a gated representation fine-tuning approach that achieves context-robust behaviors by training a lightweight intervention function with only 0.0004% of model size on fewer than 200 examples.

Large Language Models (LLMs) enhanced with external contexts, such as through retrieval-augmented generation (RAG), often face challenges in handling imperfect evidence. They tend to over-rely on external knowledge, making them vulnerable to misleading and unhelpful contexts. To address this, we propose the concept of context-robust LLMs, which can effectively balance internal knowledge with external context, similar to human cognitive processes. Specifically, context-robust LLMs should rely on external context only when lacking internal knowledge, identify contradictions between internal and external knowledge, and disregard unhelpful contexts. To achieve this goal, we introduce Grft, a lightweight and plug-and-play gated representation fine-tuning approach. Grft consists of two key components: a gating mechanism to detect and filter problematic inputs, and low-rank representation adapters to adjust hidden representations. By training a lightweight intervention function with only 0.0004\% of model size on fewer than 200 examples, Grft can effectively adapt LLMs towards context-robust behaviors.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes