Daily Papers of 2023-09-26

1. Exploring Large Language Models' Cognitive Moral Development through Defining Issues Test 38 upvotes, #1 of 2023-09-26
2. DeepSpeed-VisualChat: Multi-Round Multi-Image Interleave Chat via Multi-Modal Causal Attention 23 upvotes, #2 of 2023-09-26
3. Small-scale proxies for large-scale Transformer training instabilities 22 upvotes, #3 of 2023-09-26
4. SCREWS: A Modular Framework for Reasoning with Revisions 18 upvotes, #4 of 2023-09-26
5. Calibrating LLM-Based Evaluator 12 upvotes, #5 of 2023-09-26
6. VidChapters-7M: Video Chapters at Scale 11 upvotes, #6 of 2023-09-26

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.