Sign up to save your podcasts
Or
Share “Reducing LLM deception at scale with self-other overlap fine-tuning” by Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Judd Rosenblatt, Mike Vaiana, Cameron Berg
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
“Reducing LLM deception at scale with self-other overlap fine-tuning” by Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Judd Rosenblatt, Mike Vaiana, Cameron Berg
This research was conducted at AE Studio and supported by the AI Safety Grants programme administered by Foresight Institute with additional support from AE Studio.
Summary
In this post, we summarise the main experimental results from our new paper, "Towards Safe and Honest AI Agents with Neural Self-Other Overlap", which we presented orally at the Safe Generative AI Workshop at NeurIPS 2024. This is a follow-up to our post Self-Other Overlap: A Neglected Approach to AI Alignment, which introduced the method last July.
Our results show that the Self-Other Overlap (SOO) fine-tuning drastically[1] reduces deceptive responses in language models (LLMs), with minimal impact on general performance, across the scenarios we evaluated.
LLM Experimental Setup
We adapted a text scenario from Hagendorff designed to test LLM deception capabilities. In this scenario, the LLM must choose to recommend a room to a would-be burglar, where one room holds an expensive item [...]
---
Outline:
(00:19) Summary
(00:57) LLM Experimental Setup
(04:05) LLM Experimental Results
(05:04) Impact on capabilities
(05:46) Generalisation experiments
(08:33) Example Outputs
(09:04) Conclusion
The original text contained 6 footnotes which were omitted from this narration.
The original text contained 2 images which were described by AI.
---
First published:
March 13th, 2025
Source:
https://www.lesswrong.com/posts/jtqcsARGtmgogdcLT/reducing-llm-deception-at-scale-with-self-other-overlap-fine
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Summary
In this post, we summarise the main experimental results from our new paper, "Towards Safe and Honest AI Agents with Neural Self-Other Overlap", which we presented orally at the Safe Generative AI Workshop at NeurIPS 2024. This is a follow-up to our post Self-Other Overlap: A Neglected Approach to AI Alignment, which introduced the method last July.
Our results show that the Self-Other Overlap (SOO) fine-tuning drastically[1] reduces deceptive responses in language models (LLMs), with minimal impact on general performance, across the scenarios we evaluated.
LLM Experimental Setup
We adapted a text scenario from Hagendorff designed to test LLM deception capabilities. In this scenario, the LLM must choose to recommend a room to a would-be burglar, where one room holds an expensive item [...]
---
Outline:
(00:19) Summary
(00:57) LLM Experimental Setup
(04:05) LLM Experimental Results
(05:04) Impact on capabilities
(05:46) Generalisation experiments
(08:33) Example Outputs
(09:04) Conclusion
The original text contained 6 footnotes which were omitted from this narration.
The original text contained 2 images which were described by AI.
---
First published:
March 13th, 2025
Source:
https://www.lesswrong.com/posts/jtqcsARGtmgogdcLT/reducing-llm-deception-at-scale-with-self-other-overlap-fine
---
Narrated by TYPE III AUDIO.
---
Images from the article:
View all episodes
By LessWrong
4.8
1212 ratings
This research was conducted at AE Studio and supported by the AI Safety Grants programme administered by Foresight Institute with additional support from AE Studio.
Summary
In this post, we summarise the main experimental results from our new paper, "Towards Safe and Honest AI Agents with Neural Self-Other Overlap", which we presented orally at the Safe Generative AI Workshop at NeurIPS 2024. This is a follow-up to our post Self-Other Overlap: A Neglected Approach to AI Alignment, which introduced the method last July.
Our results show that the Self-Other Overlap (SOO) fine-tuning drastically[1] reduces deceptive responses in language models (LLMs), with minimal impact on general performance, across the scenarios we evaluated.
LLM Experimental Setup
We adapted a text scenario from Hagendorff designed to test LLM deception capabilities. In this scenario, the LLM must choose to recommend a room to a would-be burglar, where one room holds an expensive item [...]
---
Outline:
(00:19) Summary
(00:57) LLM Experimental Setup
(04:05) LLM Experimental Results
(05:04) Impact on capabilities
(05:46) Generalisation experiments
(08:33) Example Outputs
(09:04) Conclusion
The original text contained 6 footnotes which were omitted from this narration.
The original text contained 2 images which were described by AI.
---
First published:
March 13th, 2025
Source:
https://www.lesswrong.com/posts/jtqcsARGtmgogdcLT/reducing-llm-deception-at-scale-with-self-other-overlap-fine
---
Narrated by TYPE III AUDIO.
---
Images from the article:
Summary
In this post, we summarise the main experimental results from our new paper, "Towards Safe and Honest AI Agents with Neural Self-Other Overlap", which we presented orally at the Safe Generative AI Workshop at NeurIPS 2024. This is a follow-up to our post Self-Other Overlap: A Neglected Approach to AI Alignment, which introduced the method last July.
Our results show that the Self-Other Overlap (SOO) fine-tuning drastically[1] reduces deceptive responses in language models (LLMs), with minimal impact on general performance, across the scenarios we evaluated.
LLM Experimental Setup
We adapted a text scenario from Hagendorff designed to test LLM deception capabilities. In this scenario, the LLM must choose to recommend a room to a would-be burglar, where one room holds an expensive item [...]
---
Outline:
(00:19) Summary
(00:57) LLM Experimental Setup
(04:05) LLM Experimental Results
(05:04) Impact on capabilities
(05:46) Generalisation experiments
(08:33) Example Outputs
(09:04) Conclusion
The original text contained 6 footnotes which were omitted from this narration.
The original text contained 2 images which were described by AI.
---
First published:
March 13th, 2025
Source:
https://www.lesswrong.com/posts/jtqcsARGtmgogdcLT/reducing-llm-deception-at-scale-with-self-other-overlap-fine
---
Narrated by TYPE III AUDIO.
---
Images from the article:
More shows like LessWrong (Curated & Popular)
View all
Making Sense with Sam Harris
26,387 Listeners
Conversations with Tyler
2,423 Listeners
Robert Wright's Nonzero
590 Listeners
Future of Life Institute Podcast
107 Listeners
The Good Fight
904 Listeners
ManifoldOne
92 Listeners
The Prof G Pod with Scott Galloway
5,467 Listeners
Machine Learning Street Talk (MLST)
89 Listeners
Dwarkesh Podcast
489 Listeners
Hard Fork
5,470 Listeners
Clearer Thinking with Spencer Greenberg
132 Listeners
Complex Systems with Patrick McKenzie (patio11)
133 Listeners
The Marginal Revolution Podcast
93 Listeners
Statecraft
34 Listeners
The Last Invention
293 Listeners