Researchers · Interviewed at COLM 2026

Chandreyi (Zini) Chakraborty

Georgia Tech

Where Does an LLM's Social Reasoning Come From? Tracing It to Pre-training Data | COLM 2026

COLM 2026 · October 19, 2026 · 7 min

Where Does an LLM's Social Reasoning Come From? Tracing It to Pre-training Data | COLM 2026

Language models are surprisingly good at social reasoning. But which parts of the pre-training data actually produce that ability?

At COLM 2026 in San Francisco, Chandreyi (Zini) Chakraborty from Mark Riedl's lab at Georgia Tech presents a provenance audit of social reasoning in OLMo 3 7B. The team used influence functions to attribute model capabilities across 5 million pre-training documents. They organized the documents with WebOrganizer into 576 topic × format buckets and averaged influence within each bucket, because attribution at the level of single documents is too noisy to interpret.

More from COLM 2026

All event interviews →