Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach
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.
Code (0)
등록된 구현이 없습니다.
Tasks
RAGRetrieval-augmented GenerationSimilar Papers 제목 키워드 기반
Supervised In-Context Fine-Tuning for Generative Sequence Labeling
Sequence labeling (SL) tasks, where labels are assigned to tokens, are abundant in NLP (e.g., named entity recognition and aspect-based sentiment analysis). Owing to the intuition that they require bidirectional context,…
Response GenerationSentiment AnalysisLarge Language Models for Anomaly Detection in Computational Workflows: from Supervised Fine-Tuning to In-Context Learning
Anomaly detection in computational workflows is critical for ensuring system reliability and security. However, traditional rule-based methods struggle to detect novel anomalies. This paper leverages large language model…
Anomaly DetectionIn-Context LearningSentenceSentence ClassificationLIFT: Improving Long Context Understanding of Large Language Models through Long Input Fine-Tuning
Long context understanding remains challenging for large language models due to their limited context windows. This paper presents Long Input Fine-Tuning (LIFT), a novel framework for long-context modeling that can impro…
In-Context LearningLong-Context UnderstandingMemorizationFine-Tuning Large Language Models for Stock Return Prediction Using Newsflow
Large language models (LLMs) and their fine-tuning techniques have demonstrated superior performance in various language understanding and generation tasks. This paper explores fine-tuning LLMs for stock return forecasti…
DecoderPortfolio OptimizationFine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches
We explore efficient strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints. Two approaches are investigated: (1) attaching a classification head t…
Text Classification