Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models
☆15Nov 4, 2023Updated 2 years ago
Alternatives and similar repositories for MechanisticProbe
Users that are interested in MechanisticProbe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for the paper "A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis"☆20Jun 12, 2025Updated 10 months ago
- This is official project in our paper: Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers☆31Jan 13, 2024Updated 2 years ago
- AAAI-22 paper: Synthetic Disinformation Attacks on Automated Fact Verification Systems☆12Feb 23, 2022Updated 4 years ago
- ☆14Jan 6, 2025Updated last year
- What Has Been Enhanced in my Knowledge-Enhanced Language Model?☆13Oct 26, 2022Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Baseline models for the paper: "Modeling Naive Psychology of Characters in Simple Commonsense Stories" by Hannah Rashkin, Antoine Bosselu…☆16Feb 23, 2021Updated 5 years ago
- ☆10Aug 24, 2023Updated 2 years ago
- 从零快速使用Ubuntu，搭建深度学习环境，持续更新中☆11Apr 18, 2023Updated 3 years ago
- [ACL 2025] Adaptive Retrieval without Self-Knowledge? Bringing Uncertainty Back Home☆18May 17, 2025Updated 11 months ago
- [NeurIPS 2025@FoRLM] R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search☆17Jan 24, 2026Updated 3 months ago
- This repository contains a collection of the most influential papers, and benchmarks related to Large Language Models (LLMs) based Agent …☆53Jul 7, 2025Updated 9 months ago
- python file for lilab☆16Sep 11, 2025Updated 7 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆45Jun 30, 2024Updated last year
- [AAAI 2025] Code for paper:Enhancing Multimodal Large Language Models Complex Reasoning via Similarity Computation☆21Jan 14, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆39Feb 27, 2024Updated 2 years ago
- AdaICL: Which Examples to Annotate of In-Context Learning? Towards Effective and Efficient Selection☆19Oct 30, 2023Updated 2 years ago
- Reproduction Code for Paper "Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models"☆14Jun 1, 2024Updated last year
- ☆66Jan 23, 2026Updated 3 months ago
- Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied wit…☆156Jul 12, 2024Updated last year
- ☆12Feb 6, 2021Updated 5 years ago
- Implementation for NeurIPS 2024 oral paper: Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation☆16Jan 27, 2025Updated last year
- CVPR2021: Detecting Human-Object Interaction via Fabricated Compositional Learning☆16Jul 7, 2021Updated 4 years ago
- Train your own GPT2!☆14Apr 11, 2023Updated 3 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆35Jan 7, 2026Updated 3 months ago
- Code for L4DC 2022 paper: Joint Synthesis of Safety Certificate and Safe Control Policy Using Constrained Reinforcement Learning.☆15Jul 31, 2023Updated 2 years ago
- Code for experiments on transformers using Markovian data.☆22Nov 22, 2024Updated last year
- [ICLR 2025] "Training LMs on Synthetic Edit Sequences Improves Code Synthesis" (Piterbarg, Pinto, Fergus)☆19Feb 11, 2025Updated last year
- ☆20Apr 16, 2025Updated last year
- Companion code to https://arxiv.org/abs/2409.03797v2☆19Sep 18, 2025Updated 7 months ago
- To mitigate position bias in LLMs, especially in long-context scenarios, we scale only one dimension of LLMs, reducing position bias and …☆11Jun 18, 2024Updated last year
- ☆12Jul 31, 2025Updated 9 months ago
- ☆12Jan 10, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Source code of “Reinforcement Learning with Token-level Feedback for Controllable Text Generation (NAACL 2024)☆17Dec 8, 2024Updated last year
- ☆18Sep 1, 2025Updated 7 months ago
- [NeurIPS 2024] Mitigating Object Hallucination via Concentric Causal Attention☆65Aug 30, 2025Updated 8 months ago
- Feasibility Consistent Representation Learning for Safe Reinforcement Learning (ICML 2024). Current SOTA model-free safe RL algorithm on …☆16Jul 12, 2024Updated last year
- Plancraft is a minecraft environment and agent suite to test planning capabilities in LLMs☆27Nov 7, 2025Updated 5 months ago
- Like ARC, but code to generate visual puzzles. 1D puzzles first.☆23Aug 17, 2024Updated last year
- This is the official implementation of Multi-Agent PPO.☆144Jan 17, 2023Updated 3 years ago