ContextCite: Attributing Model Generation to Context
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914949169676288 |
|---|---|
| author | Cohen-Wang, Benjamin Shah, Harshay Georgiev, Kristian Madry, Aleksander |
| author_facet | Cohen-Wang, Benjamin Shah, Harshay Georgiev, Kristian Madry, Aleksander |
| contents | How do language models use information provided as context when generating a response? Can we infer whether a particular generated statement is actually grounded in the context, a misinterpretation, or fabricated? To help answer these questions, we introduce the problem of context attribution: pinpointing the parts of the context (if any) that led a model to generate a particular statement. We then present ContextCite, a simple and scalable method for context attribution that can be applied on top of any existing language model. Finally, we showcase the utility of ContextCite through three applications: (1) helping verify generated statements (2) improving response quality by pruning the context and (3) detecting poisoning attacks. We provide code for ContextCite at https://github.com/MadryLab/context-cite. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00729 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ContextCite: Attributing Model Generation to Context Cohen-Wang, Benjamin Shah, Harshay Georgiev, Kristian Madry, Aleksander Machine Learning Computation and Language How do language models use information provided as context when generating a response? Can we infer whether a particular generated statement is actually grounded in the context, a misinterpretation, or fabricated? To help answer these questions, we introduce the problem of context attribution: pinpointing the parts of the context (if any) that led a model to generate a particular statement. We then present ContextCite, a simple and scalable method for context attribution that can be applied on top of any existing language model. Finally, we showcase the utility of ContextCite through three applications: (1) helping verify generated statements (2) improving response quality by pruning the context and (3) detecting poisoning attacks. We provide code for ContextCite at https://github.com/MadryLab/context-cite. |
| title | ContextCite: Attributing Model Generation to Context |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2409.00729 |