))
“the case for CoT unfaithfulness is overstated” by nostalgebraist
Manage episode 442883344 series 3364758
תוכן מסופק על ידי LessWrong. כל תוכן הפודקאסטים כולל פרקים, גרפיקה ותיאורי פודקאסטים מועלים ומסופקים ישירות על ידי LessWrong או שותף פלטפורמת הפודקאסט שלהם. אם אתה מאמין שמישהו משתמש ביצירה שלך המוגנת בזכויות יוצרים ללא רשותך, אתה יכול לעקוב אחר התהליך המתואר כאן https://he.player.fm/legal.
[Meta note: quickly written, unpolished. Also, it's possible that there's some more convincing work on this topic that I'm unaware of – if so, let me know]
In research discussions about LLMs, I often pick up a vibe of casual, generalized skepticism about model-generated CoT (chain-of-thought) explanations.
CoTs (people say) are not trustworthy in general. They don't always reflect what the model is "actually" thinking or how it has "actually" solved a given problem.
This claim is true as far as it goes. But people sometimes act like it goes much further than (IMO) it really does.
Sometimes it seems to license an attitude of "oh, it's no use reading what the model says in the CoT, you're a chump if you trust that stuff." Or, more insidiously, a failure to even ask the question "what, if anything, can we learn about the model's reasoning process by reading the [...]
The original text contained 1 footnote which was omitted from this narration.
---
First published:
September 29th, 2024
Source:
https://www.lesswrong.com/posts/HQyWGE2BummDCc2Cx/the-case-for-cot-unfaithfulness-is-overstated
---
Narrated by TYPE III AUDIO.
…
continue reading
In research discussions about LLMs, I often pick up a vibe of casual, generalized skepticism about model-generated CoT (chain-of-thought) explanations.
CoTs (people say) are not trustworthy in general. They don't always reflect what the model is "actually" thinking or how it has "actually" solved a given problem.
This claim is true as far as it goes. But people sometimes act like it goes much further than (IMO) it really does.
Sometimes it seems to license an attitude of "oh, it's no use reading what the model says in the CoT, you're a chump if you trust that stuff." Or, more insidiously, a failure to even ask the question "what, if anything, can we learn about the model's reasoning process by reading the [...]
The original text contained 1 footnote which was omitted from this narration.
---
First published:
September 29th, 2024
Source:
https://www.lesswrong.com/posts/HQyWGE2BummDCc2Cx/the-case-for-cot-unfaithfulness-is-overstated
---
Narrated by TYPE III AUDIO.
365 פרקים
שתפו
