Training Large Language Model to Reason in a Continuous Latent Space

Code for "QUENCH: Measuring the gap between Indic and Non-Indic Contextual General Reasoning in LLMs" (accepted at COLING 2025)

Challenge LLMs to Reason About Reasoning: A Benchmark to Unveil Cognitive Depth in LLMs

Composable building blocks to build Llama Apps

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!

KokoMind: Can LLMs Understand Social Interactions?

BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages

Extracting Cultural Commonsense Knowledge at Scale (WWW 2023)

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

The code used to train and run inference with the ColPali architecture.

OLMoE: Open Mixture-of-Experts Language Models

[EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

Logiqa2.0 dataset - logical reasoning in MRC and NLI tasks

Python package for measuring memorization in LLMs.

The Dataset and Official Implementation for <Discursive Socratic Questioning: Evaluating the Faithfulness of Language Models’ Understanding of Discourse Relations> @ ACL 2024

A library for generative social simulation

Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback

Governance of the Commons Simulation (GovSim)

ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate