The DOI matches its Crossref record; 17 of the 18 references it cites were found in a registry or an index.
Steering Llama 2 via Contrastive Activation Addition
Open accessAbstract
Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, Alexander Turner. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
The cited source says what the claim attributes to it.
In the citing paper
“Currently, the techniques used for this purpose are mostly unrelated to interpretability (e.g.Christiano et al. (2017); Rafailov et al. (2023); inter alia), but sometimes inspired by it (Rimsky et al. (2024), Zou et al. (2024), Kirch et al. (2024); inter alia).”
From Open Problems in Mechanistic Interpretability (2025) · cites this paper as Rimsky et al. (2024)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
Sorted by citations
Open Problems in Mechanistic Interpretability
Sharkey, L., Chughtai, B., Batson, J., Lindsey, J., Wu, J., Bushnaq, L., Goldowsky-Dill, N., Heimersheim, S., Ortega, A., Bloom, J., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.16496 · Cited by 291
Daryanto, T., Ding, X., Wilhelm, L. A., Stil, S., Knutsen, K. M., & Rho, E. H. R. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3701188 · Cited by 67
InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance
Wang, P., Zhang, D., Li, L., Tan, C., Wang, X., Zhang, M., Ren, K. L., Jiang, B., & Qiu, X. (2024) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2024.emnlp-main.585 · Cited by 38
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Templeton, A., Conerly, T., Marcus, J., Lindsey, J., Bricken, T., Chen, B., Pearce, A., Citro, C., Ameisen, E., Jones, A., et al. (2026) · arXiv · doi:10.48550/arxiv.2605.29358 · Cited by 36
Fostering effective hybrid human-LLM reasoning and decision making
Passerini, A., Gema, A. P., Minervini, P., Sayin, B., & Tentori, K. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1464690 · Cited by 39
Metadata
- Authors
- Rimsky, N., Gabrieli, N., Schulz, J., Tong, M., Hubinger, E., & Turner, A.
- Affiliations
- Harvard University (US)
- University of Göttingen (DE)
- Venue
- Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2024
- Pages
- 15504-15522
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4402671231
- Cited by
- 57
- References
- 0
- Citations by year
- 2026: 41 · 2025: 13 · 2024: 3
- FWCI
- 16.82
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- Llama 2, contrastive learning, LLM fine-tuning
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
