Key points are not available for this paper at this time.
Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks. However, current LLMs exhibit limited robustness to unseen instructions, generating inconsistent outputs when the same instruction is phrased with slightly varied forms or language styles. This behavior indicates LLMs' lack of robustness to textual variations and generalizability to unseen instructions, potentially leading to trustworthiness issues. Accordingly, we propose Contrastive Instruction Tuning, which maximizes the similarity between the hidden representations of semantically equivalent instruction-instance pairs while minimizing the similarity between semantically different ones. To facilitate this approach, we augment the existing FLAN collection by paraphrasing task instructions. Experiments on the PromptBench benchmark show that CoIN consistently improves LLMs' robustness to unseen instructions with variations across character, word, sentence, and semantic levels by an average of +2.5% in accuracy.
Building similarity graph...
Analyzing shared references across papers
Loading...
Yan et al. (Fri,) studied this question.
www.synapsesocial.com/papers/68e78e3ab6db6435876fff45 — DOI: https://doi.org/10.48550/arxiv.2402.11138
Tianyi Yan
Wang Fei
James Y. Huang
Building similarity graph...
Analyzing shared references across papers
Loading...
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: