lingo-mit / lm-truthfulness
☆15Updated last year
Alternatives and similar repositories for lm-truthfulness:
Users that are interested in lm-truthfulness are comparing it to the libraries listed below
- Align your LM to express calibrated verbal statements of confidence in its long-form generations.☆23Updated 10 months ago
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆29Updated 3 months ago
- ☆40Updated last year
- ☆13Updated last year
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆11Updated 3 months ago
- Augmenting Statistical Models with Natural Language Parameters☆26Updated 7 months ago
- ☆29Updated 11 months ago
- ☆42Updated last year
- This is the official repo for Towards Uncertainty-Aware Language Agent.☆24Updated 8 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆53Updated 5 months ago
- ☆25Updated 2 years ago
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆16Updated 3 months ago
- Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)☆17Updated 3 weeks ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated last month
- ☆44Updated 7 months ago
- Official implementation of Bootstrapping Language Models via DPO Implicit Rewards☆43Updated last week
- ☆93Updated last year
- AbstainQA, ACL 2024☆25Updated 6 months ago
- ☆28Updated last year
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆25Updated last month
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated 2 months ago
- ☆30Updated 9 months ago
- ☆53Updated last year
- Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts☆16Updated last year
- Self-Supervised Alignment with Mutual Information☆17Updated 11 months ago
- ☆28Updated last year
- General-purpose activation steering library☆61Updated 3 months ago
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- The code of “Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning”☆16Updated last year
- EMNLP 2024: Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue☆35Updated 5 months ago