Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes
원문 초록
Large Language Models (LLMs) are often used as automated judges to evaluate text, but their effectiveness can be hindered by various unintentional biases. We propose using linear classifying probes, trained by leveraging differences between contrasting pairs of prompts, to directly access LLMs' latent knowledge and extract more accurate preferences. Through extensive experiments using models of varying size from four different families and six diverse datasets assessing text quality evaluation and common sense reasoning, we demonstrate that both supervised and unsupervised probing approaches consistently outperform traditional generation-based judgement while maintaining similar computational costs. These probes generalise under domain shifts and can even outperform finetuned evaluators with the same training data size. Our results suggest linear probing offers an accurate, robust and computationally efficient approach for LLM-as-judge tasks while providing interpretable insights into how models encode judgement-relevant knowledge. Our data and code will be openly released in the future.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization
Prime the search: Using large language models for guiding geometric task and motion planning by warm-starting tree search
AmbiK: Dataset of Ambiguous Tasks in Kitchen Environment
3D Visual Illusion Depth Estimation
VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.