Visual GenAI Summary

DeepSeek-R1: Incentivizing Reasoning capability in LLMs via Reinforcement Learning

Detecting hallucinations in large language models using semantic entropy

Reflexion: Language Agents with Verbal Reinforcement Learning

Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting Over Heterogenous Sources

Chain-of-Symbol Prompting for Spatial Relationships in Large Language Models

Chain-of-Dictionary Prompting Elicits Translation in Large Language Models

From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting

Chain-of-Verification Prompting

Chain of Natural Language Inferencing (CoNLI) Prompting

Self-Refine Prompting

Rephrase and Respond Prompting