Sign up to save your podcasts
Or
Share “Learning to Interpret Weight Differences in Language Models” by avichal
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
“Learning to Interpret Weight Differences in Language Models” by avichal
Audio note: this article contains 38 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description.
Paper | Github | Demo Notebook
This post is about our recent paper Learning to Interpret Weight Differences in Language Models (Goel et al. Oct. 2025). We introduce a method for training a LoRA adapter that gives a finetuned model the ability to accurately describe the effects of its finetuning.
Figure 1: A demonstration of our method on Qwen3-8B. With the adapter applied, a model is able to answer questions about its finetuning changes. Try it yourself here.WeightDiffQA
Our paper introduces and attempts to solve a task we call WeightDiffQA[1]:
Given a language model _M_, a weight diff _delta_, and a natural language question _q_ about _delta_, output a correct natural language answer to _q_.
Here, a "weight [...]
---
Outline:
(00:57) WeightDiffQA
(03:17) Diff Interpretation Tuning
(05:09) Eval #1: Reporting hidden behaviors
(07:17) Eval #2: Summarizing finetuned knowledge
(08:26) Limitations
(09:50) Takeaways
The original text contained 8 footnotes which were omitted from this narration.
---
First published:
October 23rd, 2025
Source:
https://www.lesswrong.com/posts/EKhTrhrCz2rNg7FmG/learning-to-interpret-weight-differences-in-language-models-1
---
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 LessWrong
Audio note: this article contains 38 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description.
Paper | Github | Demo Notebook
This post is about our recent paper Learning to Interpret Weight Differences in Language Models (Goel et al. Oct. 2025). We introduce a method for training a LoRA adapter that gives a finetuned model the ability to accurately describe the effects of its finetuning.
Figure 1: A demonstration of our method on Qwen3-8B. With the adapter applied, a model is able to answer questions about its finetuning changes. Try it yourself here.WeightDiffQA
Our paper introduces and attempts to solve a task we call WeightDiffQA[1]:
Given a language model _M_, a weight diff _delta_, and a natural language question _q_ about _delta_, output a correct natural language answer to _q_.
Here, a "weight [...]
---
Outline:
(00:57) WeightDiffQA
(03:17) Diff Interpretation Tuning
(05:09) Eval #1: Reporting hidden behaviors
(07:17) Eval #2: Summarizing finetuned knowledge
(08:26) Limitations
(09:50) Takeaways
The original text contained 8 footnotes which were omitted from this narration.
---
First published:
October 23rd, 2025
Source:
https://www.lesswrong.com/posts/EKhTrhrCz2rNg7FmG/learning-to-interpret-weight-differences-in-language-models-1
---
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
The Daily
112,214 Listeners
Astral Codex Ten Podcast
131 Listeners
Interesting Times with Ross Douthat
7,239 Listeners
Dwarkesh Podcast
559 Listeners
The Ezra Klein Show
16,276 Listeners
AI Article Readings
4 Listeners
Doom Debates!
14 Listeners
LessWrong posts by zvi
2 Listeners