From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research
[Sztuczna inteligencja] Autorzy: Yakov Pyotr Shkolnikov
Research and news coverage of language-model deception increasingly attributes human-like mental-state concepts to language models. Such claims can blur the distinction between behavior that looks deceptive and a mechanism that is actually deceptive. We introduce a causal taxonomy separating prior commitment from retrospective report, model preference from realized output, false preference from sensitivity to the utility of misleading a recipient, and deceptive behavior from the provenance of the objective or strategy producing it. We test these distinctions in two open-weight model families. Across controlled guessing-game and stock-trading experiments, we find that deceptive-looking behavior can arise without the corresponding proposed mechanism, while other interventions provide direct evidence that recipient information state can causally affect deceptive preference. These results s…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja