Don't throw away your value model! Making PPO even better via Value-Guided Monte-Carlo Tree Search decoding Paper • 2309.15028 • Published Sep 26, 2023 • 1
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts Paper • 2310.02255 • Published Oct 3, 2023 • 2
Crystal: Introspective Reasoners Reinforced with Self-Feedback Paper • 2310.04921 • Published Oct 7, 2023 • 1
NaturalProofs: Mathematical Theorem Proving in Natural Language Paper • 2104.01112 • Published Mar 24, 2021
Minds versus Machines: Rethinking Entailment Verification with Language Models Paper • 2402.03686 • Published Feb 6, 2024 • 1
NaturalProver: Grounded Mathematical Proof Generation with Language Models Paper • 2205.12910 • Published May 25, 2022
Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering Paper • 2210.03078 • Published Oct 6, 2022 • 1
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback Paper • 2406.09279 • Published Jun 13, 2024 • 2
AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text Paper • 2410.04265 • Published Oct 5, 2024
Establishing Task Scaling Laws via Compute-Efficient Model Ladders Paper • 2412.04403 • Published Dec 5, 2024 • 3
MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities Paper • 2408.00765 • Published Aug 1, 2024 • 14
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing Paper • 2406.08464 • Published Jun 12, 2024 • 67
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs Paper • 2402.11753 • Published Feb 19, 2024 • 6
SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding Paper • 2402.08983 • Published Feb 14, 2024 • 4