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
Sorting:
- Bird’s Eye: Probing for Linguistic Graph Structureswith a Simple Information-Theoretic Approach☆11Aug 1, 2021Updated 4 years ago
- Source Code for "Adapters for Enhanced Modeling of Multilingual Knowledge and Text"☆12Oct 28, 2022Updated 3 years ago
- Implementation of the paper "WToE: Learning When to Explore in Multi-Agent Reinforcement Learning"☆21Aug 17, 2024Updated last year
- Official PyTorch code for "Sample Efficient Offline-to-Online Reinforcement Learning" in TKDE'23.☆16Aug 14, 2023Updated 2 years ago
- ☆15Oct 11, 2022Updated 3 years ago
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)☆57Oct 28, 2024Updated last year
- 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
- ☆13Mar 7, 2025Updated 11 months ago
- e☆43Apr 23, 2025Updated 10 months ago
- 从零快速使用Ubuntu，搭建深度学习环境，持续更新中☆10Apr 18, 2023Updated 2 years ago
- Image reconstruction from human brain activity by VAE and adversarial learning☆12May 21, 2022Updated 3 years ago
- Reproduction Code for Paper "Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models"☆13Jun 1, 2024Updated last year
- [WACV 2025] High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer☆21Jan 14, 2026Updated last month
- ☆10Aug 24, 2023Updated 2 years 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
- ☆14Jan 6, 2025Updated last year
- ☆12Feb 6, 2021Updated 5 years ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆46Jun 30, 2024Updated last year
- ☆13Dec 22, 2021Updated 4 years ago
- The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.☆12May 2, 2024Updated last year
- 很多东西无法发布在csdn或者b站，因为涉及黑客技术，过于恐怖，或者涉及ipynb，无法正常展示。我发布到这里，总有允许记录这些内容的地方！☆12Dec 4, 2025Updated 2 months ago
- 适合科研人员的Python绘图工具☆14Jun 13, 2024Updated last year
- python file for lilab☆16Sep 11, 2025Updated 5 months ago
- [ACL 2025] Adaptive Retrieval without Self-Knowledge? Bringing Uncertainty Back Home☆16May 17, 2025Updated 9 months ago
- ☆12Jan 10, 2025Updated last year
- ☆12Feb 26, 2025Updated last year
- 关于LLM和Multimodal LLM的paper list☆57Feb 18, 2026Updated last week
- ☆66Jan 23, 2026Updated last month
- ☆20Dec 3, 2025Updated 2 months ago
- Extension of Neural Radiance Feilds (Mildenhall et al 2020) to perform 3D style transfer. Implementation in PyTorch Lightning.☆13Oct 18, 2021Updated 4 years ago
- An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.☆14Aug 25, 2023Updated 2 years ago
- Multi-camera calibration (intrinsics, extrinsics, and bundle adjustment)☆14Nov 2, 2025Updated 3 months ago
- Plancraft is a minecraft environment and agent suite to test planning capabilities in LLMs☆26Nov 7, 2025Updated 3 months ago
- Feasibility Consistent Representation Learning for Safe Reinforcement Learning (ICML 2024). Current SOTA model-free safe RL algorithm on …☆13Jul 12, 2024Updated last year
- BNUDC: A Two-Branched Deep Neural Network for Restoring Images from Under-Display Cameras☆10Jun 13, 2022Updated 3 years ago
- [ASE 2025] CoSIL: Software Issue Localization via LLM-Driven Code Repository Graph Searching☆18Dec 30, 2025Updated 2 months ago
- What Has Been Enhanced in my Knowledge-Enhanced Language Model?☆13Oct 26, 2022Updated 3 years ago
- Source code of “Reinforcement Learning with Token-level Feedback for Controllable Text Generation (NAACL 2024)☆17Dec 8, 2024Updated last year
- A benchmark for assessing the strength of causal relationships between real-world events (EMNLP 2023).☆14Nov 23, 2023Updated 2 years ago