指令微调使大语言模型与人脑对齐
Instruction-tuning Aligns LLMs to the Human Brain
AI总结：
本文评估25个原始与指令微调LLM，发现指令微调可提升大脑对齐约6%，且该对齐与模型规模和世界知识任务表现强相关。
摘要：
指令微调是一种被广泛采用的微调方法，它使大语言模型（LLM）能够生成更接近人类反应的输出。然而，尚无研究表明指令微调确实教会了LLM以与人类相似的方式处理语言。我们从两个方面研究指令微调对LLM与人类语言处理机制对齐的影响：（1）大脑对齐，即LLM内部表征与人类语言系统神经活动的相似性；（2）行为对齐，即LLM与人类在阅读任务上行为的相似性。我们在三个包含人类阅读自然故事和句子的数据集上评估了25个原始LLM和指令微调LLM，发现指令微调总体上增强了大脑对齐（约6%），但对行为对齐没有类似影响。为了确定大脑对齐改善背后的因素，我们计算了大脑对齐与各种LLM属性之间的相关性，例如模型规模、问题解决和世界知识理解。值得注意的是，我们发现大脑对齐与模型规模（r = 0.95）以及需要世界知识的任务表现（r = 0.81）之间存在强正相关。我们的结果表明，对LLM进行指令微调同时改善了世界知识表征和大脑对齐，这表明LLM中编码世界知识的机制也改善了与人脑的表征对齐。
英文摘要：
Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses. However, no studies have shown that instruction-tuning actually teaches LLMs to process language in a similar manner as humans. We investigate the effect of instruction-tuning on aligning LLM and human language processing mechanisms in two ways: (1) brain alignment, the similarity of LLM internal representations to neural activity in the human language system, and (2) behavioral alignment, the similarity of LLM and human behavior on a reading task. We assess 25 vanilla and instruction-tuned LLMs on three datasets involving humans reading naturalistic stories and sentences, and find that instruction-tuning generally enhances brain alignment (~6%), but has no similar effect on behavioral alignment. To identify factors underlying this improvement in brain alignment, we compute correlations between brain alignment and various LLM properties, such as model size, problem-solving, and world knowledge understanding. Notably, we find a strong positive correlation between brain alignment and model size (r = 0.95), as well as performance on tasks requiring world knowledge (r = 0.81). Our results demonstrate that instruction-tuning LLMs improves both world knowledge representations and brain alignment, suggesting that the mechanisms that encode world knowledge in LLMs also improve representational alignment to the human brain.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
