HannahKirk / prism-alignmentLinks
The Prism Alignment Project
☆77Updated last year
Alternatives and similar repositories for prism-alignment
Users that are interested in prism-alignment are comparing it to the libraries listed below
Sorting:
- ☆106Updated last year
- Inspecting and Editing Knowledge Representations in Language Models☆116Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆81Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆60Updated 7 months ago
- ☆51Updated last year
- ☆85Updated 10 months ago
- ☆95Updated last year
- How do transformer LMs encode relations?☆48Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆95Updated 3 weeks ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆93Updated 3 years ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 3 months ago
- ☆22Updated last year
- This repository contains data, code and models for contextual noncompliance.☆23Updated 11 months ago
- Data and code for the Corr2Cause paper (ICLR 2024)☆105Updated last year
- ☆44Updated last year
- Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering"☆84Updated 10 months ago
- [ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"☆108Updated last year
- ☆44Updated 9 months ago
- ☆25Updated last year
- ☆34Updated 3 years ago
- ☆69Updated last year
- AbstainQA, ACL 2024☆26Updated 8 months ago
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.☆41Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆70Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆94Updated last year
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆24Updated 3 months ago
- Repository for the Bias Benchmark for QA dataset.☆118Updated last year
- ☆78Updated 2 years ago
- ☆62Updated 2 years ago
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago