How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: language models, lying, deception, alignment, safety, truthfulness, honesty
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: How to elicit, and detect, lying behaviour in black-box LLMs.
Abstract: Large language models (LLMs) can “lie”, which we define as outputting false statements when incentivised to, despite “knowing” the truth in a demonstrable sense. LLMs might “lie”, for example, when instructed to output misinformation. Here, we develop a simple lie detector that requires neither access to the LLM’s activations (black-box) nor ground-truth knowledge of the fact in question. The detector works by asking a predefined set of unrelated follow-up questions after a suspected lie, and feeding the LLM’s yes/no answers into a logistic regression classifier. Despite its simplicity, this lie detector is highly accurate and surprisingly general. When trained on examples from a single setting—prompting GPT-3.5 to lie about factual questions—the detector generalises out-of-distribution to (1) other LLM architectures, (2) LLMs fine-tuned to lie, (3) sycophantic lies, and (4) lies emerging in real-life scenarios such as sales. These results indicate that LLMs have distinctive lie-related behavioural patterns, consistent across architectures and contexts, which could enable general-purpose lie detection.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
Supplementary Material: pdf
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: societal considerations including fairness, safety, privacy
Submission Number: 5212
Loading