Do LLMs Internally "Know" When They Follow Instructions?
AuthorsJuyeon Heo, Christina Heinze-Deml, Oussama Elachqar, Shirley Ren, Udhay Nallasamy, Andy Miller, Kwan Ho Ryan Chan, Jaya Narain
AuthorsJuyeon Heo, Christina Heinze-Deml, Oussama Elachqar, Shirley Ren, Udhay Nallasamy, Andy Miller, Kwan Ho Ryan Chan, Jaya Narain
This paper was accepted at the Foundation Model Interventions (MINT) Workshop at NeurIPS 2024.
Instruction-following is crucial for building AI agents with large language models (LLMs), as these models must adhere strictly to user-provided guidelines. However, LLMs often fail to follow even simple instructions. To improve instruction-following behavior and prevent undesirable outputs, we need a deeper understanding of how LLMs’ internal states relate to these outcomes. Our analysis of LLM internal states reveal a dimension in the input embedding space linked to successful instruction-following. We demonstrate that modifying representations along this dimension improves instruction-following success rates compared to random changes, without compromising response quality. This work provides insight into the internal workings of LLMs’ instruction-following, paving the way for reliable LLM agents.
April 10, 2025research area Speech and Natural Language Processingconference ICLR
Instruction-following is crucial for building AI agents with large language models (LLMs), as these models must adhere strictly to user-provided constraints and guidelines. However, LLMs often fail to follow even simple and clear instructions. To improve instruction-following behavior and prevent undesirable outputs, a deeper understanding of how LLMs’ internal states relate to these outcomes is required. In this work, we investigate whether LLMs...
April 8, 2025research area Speech and Natural Language Processingconference ICLR
Large language models (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown significant limitations in LLMs’ instruction-following capabilities, raising concerns about their reliability in high-stakes applications. Accurately estimating LLMs’ uncertainty in adhering to instructions is critical to mitigating deployment risks. We present, to our...