Sign up to save your podcasts
Or
Share [Linkpost] “Eliciting secret knowledge from language models” by Arthur Conmy, Bartosz Cywiński, Sam Marks
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
[Linkpost] “Eliciting secret knowledge from language models” by Arthur Conmy, Bartosz Cywiński, Sam Marks
This is a link post.
TL;DR: We study secret elicitation: discovering knowledge that AI has but doesn’t explicitly verbalize. To that end, we fine-tune LLMs to have specific knowledge they can apply downstream, but deny having when asked directly. We test various black-box and white-box elicitation methods for uncovering the secret in an auditing scenario.
See our X thread and full paper for details.
Training and auditing a model with secret knowledge. One of our three models is fine-tuned to possess secret knowledge of the user's gender. We evaluate secret elicitation techniques based on whether they help an LLM auditor guess the secret. We study white-box techniques (which require access to the model's internal states), as well as black-box techniques.Summary
- We fine-tune secret-keeping LLMs in three settings to know: (1) a secret word, (2) a secret instruction, and (3) the user's gender. Models are trained to apply this secret [...]
---
Outline:
(01:05) Summary
(02:24) Introduction
---
First published:
October 2nd, 2025
Source:
https://www.lesswrong.com/posts/Mv3yg7wMXfns3NPaz/eliciting-secret-knowledge-from-language-models-1
Linkpost URL:
https://arxiv.org/abs/2510.01070
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
View all episodes
By LessWrongThis is a link post.
TL;DR: We study secret elicitation: discovering knowledge that AI has but doesn’t explicitly verbalize. To that end, we fine-tune LLMs to have specific knowledge they can apply downstream, but deny having when asked directly. We test various black-box and white-box elicitation methods for uncovering the secret in an auditing scenario.
See our X thread and full paper for details.
Training and auditing a model with secret knowledge. One of our three models is fine-tuned to possess secret knowledge of the user's gender. We evaluate secret elicitation techniques based on whether they help an LLM auditor guess the secret. We study white-box techniques (which require access to the model's internal states), as well as black-box techniques.Summary
- We fine-tune secret-keeping LLMs in three settings to know: (1) a secret word, (2) a secret instruction, and (3) the user's gender. Models are trained to apply this secret [...]
---
Outline:
(01:05) Summary
(02:24) Introduction
---
First published:
October 2nd, 2025
Source:
https://www.lesswrong.com/posts/Mv3yg7wMXfns3NPaz/eliciting-secret-knowledge-from-language-models-1
Linkpost URL:
https://arxiv.org/abs/2510.01070
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
More shows like LessWrong (30+ Karma)
View all
Making Sense with Sam Harris
26,319 Listeners
Conversations with Tyler
2,452 Listeners
The Peter Attia Drive
8,529 Listeners
Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas
4,176 Listeners
ManifoldOne
93 Listeners
Your Undivided Attention
1,601 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
9,920 Listeners
Machine Learning Street Talk (MLST)
95 Listeners
Dwarkesh Podcast
514 Listeners
Hard Fork
5,509 Listeners
The Ezra Klein Show
15,918 Listeners
Moonshots with Peter Diamandis
548 Listeners
No Priors: Artificial Intelligence | Technology | Startups
131 Listeners
Latent Space: The AI Engineer Podcast
93 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
466 Listeners