trestad / Factual-Recall-MechanismLinks
The code for paper Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models.
☆13Updated last year
Alternatives and similar repositories for Factual-Recall-Mechanism
Users that are interested in Factual-Recall-Mechanism are comparing it to the libraries listed below
Sorting:
- Code for paper 'Are We Falling in a Middle-Intelligence Trap? An Analysis and Mitigation of the Reversal Curse'☆13Updated 10 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆73Updated 4 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆41Updated 11 months ago
- [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"☆61Updated last year
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆112Updated last year
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆48Updated last month
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆73Updated last week
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆86Updated 6 months ago
- A curated list of awesome resources dedicated to Scaling Laws for LLMs☆72Updated 2 years ago
- Code for paper: Aligning Large Language Models with Representation Editing: A Control Perspective☆32Updated 4 months ago
- [arXiv] Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs☆32Updated last month
- Official repository for paper "DeepCritic: Deliberate Critique with Large Language Models"☆30Updated last month
- ☆139Updated last month
- Model merging is a highly efficient approach for long-to-short reasoning.☆65Updated 3 weeks ago
- ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of…☆28Updated 3 weeks ago
- Official code for Guiding Language Model Math Reasoning with Planning Tokens☆13Updated last year
- Official code for SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆28Updated 2 months ago
- AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)☆271Updated last week
- ☆13Updated last year
- A Sober Look at Language Model Reasoning☆74Updated last week
- The repository of the project "Fine-tuning Large Language Models with Sequential Instructions", code base comes from open-instruct and LA…☆29Updated 7 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆156Updated 3 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆88Updated 8 months ago
- Evaluating the Ripple Effects of Knowledge Editing in Language Models☆55Updated last year
- This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers…☆85Updated 6 months ago
- A Framework for LLM-based Multi-Agent Reinforced Training and Inference☆140Updated 2 weeks ago
- Code of paper 'UltraIF: Advancing Instruction Following from the Wild'.☆17Updated 2 months ago
- Lightweight Adapting for Black-Box Large Language Models☆22Updated last year
- The rule-based evaluation subset and code implementation of Omni-MATH☆22Updated 6 months ago
- ☆49Updated last year