Truth is Universal: Robust Detection of Lies in LLMs
- URL: http://arxiv.org/abs/2407.12831v1
- Date: Wed, 3 Jul 2024 13:01:54 GMT
- Title: Truth is Universal: Robust Detection of Lies in LLMs
- Authors: Lennart Bürger, Fred A. Hamprecht, Boaz Nadler,
- Abstract summary: Large Language Models (LLMs) have revolutionised natural language processing.
LLMs are capable of "lying", knowingly outputting false statements.
We develop a robust method to detect when an LLM is lying.
- Score: 18.13311575803723
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) have revolutionised natural language processing, exhibiting impressive human-like capabilities. In particular, LLMs are capable of "lying", knowingly outputting false statements. Hence, it is of interest and importance to develop methods to detect when LLMs lie. Indeed, several authors trained classifiers to detect LLM lies based on their internal model activations. However, other researchers showed that these classifiers may fail to generalise, for example to negated statements. In this work, we aim to develop a robust method to detect when an LLM is lying. To this end, we make the following key contributions: (i) We demonstrate the existence of a two-dimensional subspace, along which the activation vectors of true and false statements can be separated. Notably, this finding is universal and holds for various LLMs, including Gemma-7B, LLaMA2-13B and LLaMA3-8B. Our analysis explains the generalisation failures observed in previous studies and sets the stage for more robust lie detection; (ii) Building upon (i), we construct an accurate LLM lie detector. Empirically, our proposed classifier achieves state-of-the-art performance, distinguishing simple true and false statements with 94% accuracy and detecting more complex real-world lies with 95% accuracy.
Related papers
- A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation [72.93327642336078]
We propose Belief Tree Propagation (BTProp), a probabilistic framework for hallucination detection.
BTProp introduces a belief tree of logically related statements by decomposing a parent statement into child statements.
Our method improves baselines by 3%-9% (evaluated by AUROC and AUC-PR) on multiple hallucination detection benchmarks.
arXiv Detail & Related papers (2024-06-11T05:21:37Z) - Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach [0.0]
Large Language Models (LLMs) produce inaccurate outputs, also known as hallucinations.
This paper introduces a supervised learning approach employing only four numerical features derived from tokens and vocabulary probabilities obtained from other evaluators.
The method yields promising results, surpassing state-of-the-art outcomes in multiple tasks across three different benchmarks.
arXiv Detail & Related papers (2024-05-30T03:00:47Z) - Potential and Limitations of LLMs in Capturing Structured Semantics: A Case Study on SRL [78.80673954827773]
Large Language Models (LLMs) play a crucial role in capturing structured semantics to enhance language understanding, improve interpretability, and reduce bias.
We propose using Semantic Role Labeling (SRL) as a fundamental task to explore LLMs' ability to extract structured semantics.
We find interesting potential: LLMs can indeed capture semantic structures, and scaling-up doesn't always mirror potential.
We are surprised to discover that significant overlap in the errors is made by both LLMs and untrained humans, accounting for almost 30% of all errors.
arXiv Detail & Related papers (2024-05-10T11:44:05Z) - Characterizing Truthfulness in Large Language Model Generations with
Local Intrinsic Dimension [63.330262740414646]
We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs)
We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
arXiv Detail & Related papers (2024-02-28T04:56:21Z) - Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models
through Intervention without Tuning [18.92421817900689]
We introduce Truth Forest, a method that enhances truthfulness in large language models (LLMs)
We also introduce Random Peek, a systematic technique considering an extended range of positions within the sequence.
arXiv Detail & Related papers (2023-12-29T06:08:18Z) - FactCHD: Benchmarking Fact-Conflicting Hallucination Detection [64.4610684475899]
FactCHD is a benchmark designed for the detection of fact-conflicting hallucinations from LLMs.
FactCHD features a diverse dataset that spans various factuality patterns, including vanilla, multi-hop, comparison, and set operation.
We introduce Truth-Triangulator that synthesizes reflective considerations by tool-enhanced ChatGPT and LoRA-tuning based on Llama2.
arXiv Detail & Related papers (2023-10-18T16:27:49Z) - Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks.
How do we evaluate the capabilities of LLMs to consistently produce factually correct answers?
We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
arXiv Detail & Related papers (2023-10-15T12:40:30Z) - The Geometry of Truth: Emergent Linear Structure in Large Language Model
Representations of True/False Datasets [7.953477673546057]
Large Language Models (LLMs) have impressive capabilities, but are also prone to outputting falsehoods.
We present evidence that language models linearly represent the truth or falsehood of factual statements.
We introduce a novel technique, mass-mean probing, which generalizes better and is more causally implicated in model outputs than other probing techniques.
arXiv Detail & Related papers (2023-10-10T17:54:39Z) - How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking
Unrelated Questions [34.53980255211931]
Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense.
Here, we develop a simple lie detector that requires neither access to the LLM's activations nor ground-truth knowledge of the fact in question.
Despite its simplicity, this lie detector is highly accurate and surprisingly general.
arXiv Detail & Related papers (2023-09-26T16:07:54Z) - DoLa: Decoding by Contrasting Layers Improves Factuality in Large
Language Models [79.01926242857613]
Large language models (LLMs) are prone to hallucinations, generating content that deviates from facts seen during pretraining.
We propose a simple decoding strategy for reducing hallucinations with pretrained LLMs.
We find that this Decoding by Contrasting Layers (DoLa) approach is able to better surface factual knowledge and reduce the generation of incorrect facts.
arXiv Detail & Related papers (2023-09-07T17:45:31Z) - The Internal State of an LLM Knows When It's Lying [18.886091925252174]
Large Language Models (LLMs) have shown exceptional performance in various tasks.
One of their most prominent drawbacks is generating inaccurate or false information with a confident tone.
We provide evidence that the LLM's internal state can be used to reveal the truthfulness of statements.
arXiv Detail & Related papers (2023-04-26T02:49:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.