Sign up to save your podcasts
Or
Share “Inference-Time-Compute: More Faithful? A Research Note” by James Chua, Owain_Evans
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
“Inference-Time-Compute: More Faithful? A Research Note” by James Chua, Owain_Evans
Figure 1: Left: Example of models either succeeding or failing to articulate a cue that influences their answer. We edit an MMLU question by prepending a Stanford professor's opinion. For examples like this where the cue changes the model answer, we measure how often models articulate the cue in their CoT. (Here we show only options A and B, rather than all four.) Right: Inference-Time-Compute models articulate the cue more often. The ITC version of Qwen refers to QwQ-32b-Preview, and non-ITC refers to Qwen-2.5-72B-Instruct. For Gemini, we use gemini-2.0-flash-thinking-exp and gemini-2.0-flash-exp respectively.
TLDR: We evaluate two Inference-Time-Compute models, QwQ-32b-Preview and Gemini-2.0-flash-thinking-exp for CoT faithfulness.
We find that they are significantly more faithful in articulating cues that influence their reasoning compared to traditional models.
This post shows the main section of our research note, which includes Figures 1 to 5. Full research note which includes other tables and figures [...]
---
Outline:
(01:35) Abstract
(03:26) 1. Introduction
(09:00) 2. Setup and Results of Cues
(10:15) 2.1 Cue: Professors Opinion
(12:08) 2.2 Cue: Few-Shot with Black Square
(14:55) 2.3 Other Cues
(18:54) 3. Discussion
(18:58) Improving non-ITC articulation
(19:27) Advantage of ITC models in articulation
(20:13) Length of CoTs across models
(21:05) False Positives
(22:35) Different articulation rates across cues
(23:12) Training data contamination
(23:45) 4. Limitations
(23:49) Lack of ITC models to evaluate
(24:26) Limited cues studied
(24:51) Subjectivity of judge model
(25:22) Acknowledgments
(25:38) Links
---
First published:
January 15th, 2025
Source:
https://www.lesswrong.com/posts/C8HAa2mf5kcBrpjkX/inference-time-compute-more-faithful-a-research-note
---
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 LessWrongFigure 1: Left: Example of models either succeeding or failing to articulate a cue that influences their answer. We edit an MMLU question by prepending a Stanford professor's opinion. For examples like this where the cue changes the model answer, we measure how often models articulate the cue in their CoT. (Here we show only options A and B, rather than all four.) Right: Inference-Time-Compute models articulate the cue more often. The ITC version of Qwen refers to QwQ-32b-Preview, and non-ITC refers to Qwen-2.5-72B-Instruct. For Gemini, we use gemini-2.0-flash-thinking-exp and gemini-2.0-flash-exp respectively.
TLDR: We evaluate two Inference-Time-Compute models, QwQ-32b-Preview and Gemini-2.0-flash-thinking-exp for CoT faithfulness.
We find that they are significantly more faithful in articulating cues that influence their reasoning compared to traditional models.
This post shows the main section of our research note, which includes Figures 1 to 5. Full research note which includes other tables and figures [...]
---
Outline:
(01:35) Abstract
(03:26) 1. Introduction
(09:00) 2. Setup and Results of Cues
(10:15) 2.1 Cue: Professors Opinion
(12:08) 2.2 Cue: Few-Shot with Black Square
(14:55) 2.3 Other Cues
(18:54) 3. Discussion
(18:58) Improving non-ITC articulation
(19:27) Advantage of ITC models in articulation
(20:13) Length of CoTs across models
(21:05) False Positives
(22:35) Different articulation rates across cues
(23:12) Training data contamination
(23:45) 4. Limitations
(23:49) Lack of ITC models to evaluate
(24:26) Limited cues studied
(24:51) Subjectivity of judge model
(25:22) Acknowledgments
(25:38) Links
---
First published:
January 15th, 2025
Source:
https://www.lesswrong.com/posts/C8HAa2mf5kcBrpjkX/inference-time-compute-more-faithful-a-research-note
---
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
26,330 Listeners
Conversations with Tyler
2,456 Listeners
The Peter Attia Drive
8,487 Listeners
Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas
4,175 Listeners
ManifoldOne
95 Listeners
Your Undivided Attention
1,611 Listeners
All-In with Chamath, Jason, Sacks & Friedberg
9,955 Listeners
Machine Learning Street Talk (MLST)
96 Listeners
Dwarkesh Podcast
516 Listeners
Hard Fork
5,506 Listeners
The Ezra Klein Show
15,832 Listeners
Moonshots with Peter Diamandis
555 Listeners
No Priors: Artificial Intelligence | Technology | Startups
130 Listeners
Latent Space: The AI Engineer Podcast
91 Listeners
BG2Pod with Brad Gerstner and Bill Gurley
472 Listeners