LESSWRONG
LW

Riya Tyagi

Message

Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought

Authors: Riya Tyagi, Daria Ivanova, Arthur Conmy, Neel Nanda Riya and Daria are co-first authors. This work was largely done during a research sprint for Neel Nanda’s MATS 9.0 training phase. 🖥️ Deployment code ⚙️ Interactive demo 🐦 Tweet thread TL;DR * We believe that more research effort should go...

Jan 13•51

Riya Tyagi

Riya Tyagi — LessWrong

Riya Tyagi

Message

Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought

Jan 13•51

Riya Tyagi

Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought

Riya Tyagi

Riya Tyagi, daria, Arthur Conmy, Neel Nanda+ 0 more

Riya Tyagi, daria, Arthur Conmy, Neel Nanda

1mo

Authors: Riya Tyagi, Daria Ivanova, Arthur Conmy, Neel Nanda

Riya and Daria are co-first authors. This work was largely done during a research sprint for Neel Nanda’s MATS 9.0 training phase.

🖥️ Deployment code

⚙️ Interactive demo

🐦 Tweet thread

TL;DR

We believe that more research effort should go into studying many chains of thought collectively and identifying global patterns across the collection.
We argue this direction is important and tractable; to start, we focus on a simpler setting: analyzing a collection of CoTs generated with a fixed model on a fixed prompt. We introduce two methods—semantic step clustering and algorithmic step clustering—that group recurring patterns across reasoning traces at different levels of abstraction.
Semantic step clustering leverages the fact

... (read 5191 more words →)