The DOI matches its Crossref record.
Post Hoc Explanations of Language Models Can Improve Language Models
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
As detection improves, evasion co-evolves; paraphrasing and prompt engineering can render AI text effectively undetectable.
“As detection improves, evasion co-evolves: paraphrasing and prompt engineering can render AI text effectively undetectable (Krishna et al., 2023).”
From Designing AI-resilient assessment in higher education: a four-pillar conceptual framework (2026) · cites this paper as Krishna et al., 2023
Citations
Cited by
Sorted by citations
Designing AI-resilient assessment in higher education: a four-pillar conceptual framework
Nikolić, D., & Basta Nikolić, M. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1841682 · Cited by 1
Metadata
- Authors
- Krishna, S., Ma, J., Slack, D., Ghandeharioun, A., Singh, S., & Lakkaraju, H.
- Venue
- Advances in Neural Information Processing Systems 36
- Published
- 2023
- Pages
- 65468-65483
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133236803
- Cited by
- 2
- References
- 0
- Citations by year
- 2026: 2
- FWCI
- 0.23
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- neural information processing systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- post-hoc explanation, language models, interpretability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
