Skip to content
@PKU-PILLAR-Group

Interpretable LLM and Reasoning Group @ PKU

Popular repositories Loading

  1. CoT-Faithfulness-Survey CoT-Faithfulness-Survey Public

    Paper list for our paper "The Mirage of Explainability: A Survey on Chain-of-Thought Faithfulness in Large Language Models".

    8

  2. Mechanism-MultiStep-Reasoning Mechanism-MultiStep-Reasoning Public

    Paper list for our survey paper "Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language Models"

    6 2

  3. Survey-LRM-Mechanisms Survey-LRM-Mechanisms Public

    Forked from AheadOFpotato/Awesome-LRM-Mechanisms

    Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures

    6

  4. AlignSAE AlignSAE Public

    Forked from yminglai/AlignSAE

    Creating a new transformer architecture making LLM have controllable reasoning.

    Python 1

  5. GSM-DC_EMNLP-2025 GSM-DC_EMNLP-2025 Public

    Forked from yminglai/GSM-DC

    This repository contains the GSM-DC benchmark and evaluation framework for analyzing how Large Language Models (LLMs) are distracted by irrelevant context in math reasoning tasks. GSM-DC constructs…

    Python 1

  6. ImplicitReasoning_NeurIPS-2025 ImplicitReasoning_NeurIPS-2025 Public

    Forked from Jiaran-Ye/ImplicitReasoning

    Data and Code for paper 'How does Transformer Learn Implicit Reasoning?' (NeurIPS 2025 Spotlight paper)

    Jupyter Notebook 1

Repositories

Showing 9 of 9 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…