Highlights
- Pro
Pinned Loading
-
microsoft/llm-steer-instruct
microsoft/llm-steer-instruct PublicA method for steering llms to better follow instructions
-
lm-arithmetic
lm-arithmetic PublicCode for the paper "A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis"
-
bpwu1/confidence-regulation-neurons
bpwu1/confidence-regulation-neurons PublicConfidence Regulation Neurons in Language Models (NeurIPS 2024)
-
causal-math
causal-math PublicCode Repository for "A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models".
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.



