ninodimontalcino / moralchoice
Evaluating the Moral Beliefs Encoded in LLMs
β24Updated 3 months ago
Alternatives and similar repositories for moralchoice:
Users that are interested in moralchoice are comparing it to the libraries listed below
- datasets from the paper "Towards Understanding Sycophancy in Language Models"β73Updated last year
- β38Updated last year
- π» Code and benchmark for our EMNLP 2023 paper - "FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions"β54Updated 10 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"β67Updated 9 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".β71Updated last year
- β82Updated 7 months ago
- Repo for: When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgmentβ38Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spacesβ91Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasksβ41Updated 4 months ago
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Caβ¦β59Updated last year
- The Prism Alignment Projectβ70Updated 11 months ago
- [EMNLP 2023, Findings] GRACE: Discriminator-Guided Chain-of-Thought Reasoningβ47Updated 5 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineeringβ52Updated 4 months ago
- β20Updated last year
- Inspecting and Editing Knowledge Representations in Language Modelsβ114Updated last year
- β35Updated 2 years ago
- β34Updated last year
- β23Updated last month
- Evaluate the Quality of Critiqueβ34Updated 10 months ago
- Algebraic value editing in pretrained language modelsβ63Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.β71Updated 3 weeks ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"β103Updated last year
- Augmenting Statistical Models with Natural Language Parametersβ23Updated 6 months ago
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Mergingβ97Updated last year
- Tasks for describing differences between text distributions.β16Updated 7 months ago
- RΓΆttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"β95Updated last month
- A library for efficient patching and automatic circuit discovery.β62Updated last month
- Exploring the Limitations of Large Language Models on Multi-Hop Queriesβ24Updated last month
- β40Updated last month
- β19Updated last year