mitmedialab / nmi-ai-2023
A repository for the paper "Beliefs about AI influence human-AI interaction and can be manipulated to increase perceived trustworthiness, empathy, and effectiveness" Nature Machine Intelligence 2023.
☆16Updated last year
Alternatives and similar repositories for nmi-ai-2023:
Users that are interested in nmi-ai-2023 are comparing it to the libraries listed below
- Repo for: When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment☆38Updated last year
- Tasks for describing differences between text distributions.☆16Updated 8 months ago
- ☆23Updated 11 months ago
- code and data associated with CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations☆10Updated last year
- ☆93Updated 11 months ago
- 👻 Code and benchmark for our EMNLP 2023 paper - "FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions"☆54Updated 10 months ago
- ☆34Updated last year
- Evaluating the Moral Beliefs Encoded in LLMs☆25Updated 4 months ago
- This repo contains code for our NeurIPS 2023 spotlight paper: Evaluating and Inducing Personality in Pre-trained Language Models☆52Updated last year
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆60Updated last year
- ☆41Updated last year
- Neuron Activation☆24Updated 5 months ago
- This repo contains code for the paper "Psychologically-informed chain-of-thought prompts for metaphor understanding in large language mod…☆14Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆74Updated last year
- Sotopia-π: Interactive Learning of Socially Intelligent Language Agents (ACL 2024)☆62Updated 11 months ago
- The Prism Alignment Project☆75Updated last year
- Data and code for the paper "Inducing Positive Perspectives with Text Reframing"☆59Updated last year
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- ☆19Updated last year
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated last year
- ☆44Updated 5 months ago
- This repository contains data, code and models for contextual noncompliance.☆21Updated 9 months ago
- ☆106Updated 11 months ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 5 months ago
- Generating and validating natural-language explanations for the brain.☆51Updated 3 weeks ago
- ☆36Updated 2 years ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆45Updated last year
- Recent papers on (1) Psychology of LLMs; (2) Biases in LLMs.☆48Updated last year
- ☆12Updated 2 years ago
- Finding semantically meaningful and accurate prompts.☆46Updated last year