TrustedLLM / UnKELinks
☆20Updated 6 months ago
Alternatives and similar repositories for UnKE
Users that are interested in UnKE are comparing it to the libraries listed below
Sorting:
- A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enab…☆99Updated 2 weeks ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆76Updated 8 months ago
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆41Updated 9 months ago
- Official code for SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆40Updated 4 months ago
- ☆34Updated 11 months ago
- Implementation code for ACL2024:Advancing Parameter Efficiency in Fine-tuning via Representation Editing☆14Updated last year
- Official repository for ICML 2024 paper "On Prompt-Driven Safeguarding for Large Language Models"☆94Updated 3 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆29Updated 5 months ago
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆82Updated 5 months ago
- ☆66Updated 4 months ago
- ☆49Updated last month
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆82Updated 11 months ago
- Project of ACL 2025 "UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models"☆13Updated 5 months ago
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆153Updated 2 weeks ago
- ☆26Updated 4 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆61Updated last year
- [ICLR 2025] Official codebase for the ICLR 2025 paper "Multimodal Situational Safety"☆22Updated 2 months ago
- Code for paper: Aligning Large Language Models with Representation Editing: A Control Perspective☆32Updated 7 months ago
- ☆43Updated last week
- Model merging is a highly efficient approach for long-to-short reasoning.☆80Updated 2 months ago
- ☆41Updated 11 months ago
- Code for "CREAM: Consistency Regularized Self-Rewarding Language Models", ICLR 2025.☆25Updated 6 months ago
- [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style☆59Updated last month
- ☆59Updated last year
- [ACL 2024] Learning to Edit: Aligning LLMs with Knowledge Editing☆36Updated last year
- ☆17Updated 4 months ago
- SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types☆20Updated 9 months ago
- [2025-TMLR] A Survey on the Honesty of Large Language Models☆58Updated 8 months ago
- awesome SAE papers☆43Updated 3 months ago
- ☆30Updated 4 months ago