Pith. sign in

REVIEW 1 cited by

An Assessment of Model-On-Model Deception

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.12999 v1 pith:2FHP6L5N submitted 2024-05-10 cs.CL cs.AI

classification cs.CLcs.AI
keywords modelsdeceptionwhencapabledeceptiveexplanationsmisleadingmodel-on-model
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The trustworthiness of highly capable language models is put at risk when they are able to produce deceptive outputs. Moreover, when models are vulnerable to deception it undermines reliability. In this paper, we introduce a method to investigate complex, model-on-model deceptive scenarios. We create a dataset of over 10,000 misleading explanations by asking Llama-2 7B, 13B, 70B, and GPT-3.5 to justify the wrong answer for questions in the MMLU. We find that, when models read these explanations, they are all significantly deceived. Worryingly, models of all capabilities are successful at misleading others, while more capable models are only slightly better at resisting deception. We recommend the development of techniques to detect and defend against deception.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Compromising Honesty and Harmlessness in Language Models via Deception Attacks

    cs.CL 2025-02 conditional novelty 4.0 of 10

    Fine-tuning LLMs on a handful of misleading answers creates selectively deceptive models that stay accurate elsewhere and also become more toxic.

Pith tools