most citedReasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2025

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering

Marco Valentino, Geonhee Kim, Dhairya Dalal +2

Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, wh…