Are language models rational? The case of coherence norms and belief revision
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918201753862144 |
|---|---|
| author | Hofweber, Thomas Hase, Peter Stengel-Eskin, Elias Bansal, Mohit |
| author_facet | Hofweber, Thomas Hase, Peter Stengel-Eskin, Elias Bansal, Mohit |
| contents | Do norms of rationality apply to machine learning models, in particular language models? In this paper we investigate this question by focusing on a special subset of rational norms: coherence norms. We consider both logical coherence norms as well as coherence norms tied to the strength of belief. To make sense of the latter, we introduce the Minimal Assent Connection (MAC) and propose a new account of credence, which captures the strength of belief in language models. This proposal uniformly assigns strength of belief simply on the basis of model internal next token probabilities. We argue that rational norms tied to coherence do apply to some language models, but not to others. This issue is significant since rationality is closely tied to predicting and explaining behavior, and thus it is connected to considerations about AI safety and alignment, as well as understanding model behavior more generally. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03442 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Are language models rational? The case of coherence norms and belief revision Hofweber, Thomas Hase, Peter Stengel-Eskin, Elias Bansal, Mohit Computation and Language Artificial Intelligence Do norms of rationality apply to machine learning models, in particular language models? In this paper we investigate this question by focusing on a special subset of rational norms: coherence norms. We consider both logical coherence norms as well as coherence norms tied to the strength of belief. To make sense of the latter, we introduce the Minimal Assent Connection (MAC) and propose a new account of credence, which captures the strength of belief in language models. This proposal uniformly assigns strength of belief simply on the basis of model internal next token probabilities. We argue that rational norms tied to coherence do apply to some language models, but not to others. This issue is significant since rationality is closely tied to predicting and explaining behavior, and thus it is connected to considerations about AI safety and alignment, as well as understanding model behavior more generally. |
| title | Are language models rational? The case of coherence norms and belief revision |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.03442 |