-
Chain-of-Verification Reduces Hallucination in Large Language Models
Paper • 2309.11495 • Published • 39 -
CodePlan: Repository-level Coding using LLMs and Planning
Paper • 2309.12499 • Published • 79 -
SCREWS: A Modular Framework for Reasoning with Revisions
Paper • 2309.13075 • Published • 17 -
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Paper • 2309.08532 • Published • 53
Shruti Patel
shrutipatel
AI & ML interests
None yet
Organizations
logical reasoning with llms
-
Language Models can be Logical Solvers
Paper • 2311.06158 • Published • 22 -
Fusion-Eval: Integrating Evaluators with LLMs
Paper • 2311.09204 • Published • 6 -
Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation
Paper • 2311.08877 • Published • 7 -
Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
Paper • 2311.07587 • Published • 5
general agents
-
JaxMARL: Multi-Agent RL Environments in JAX
Paper • 2311.10090 • Published • 8 -
ToolTalk: Evaluating Tool-Usage in a Conversational Setting
Paper • 2311.10775 • Published • 10 -
Contrastive Chain-of-Thought Prompting
Paper • 2311.09277 • Published • 36 -
Testing Language Model Agents Safely in the Wild
Paper • 2311.10538 • Published • 11
diffusion models
coding with llms
-
Chain-of-Verification Reduces Hallucination in Large Language Models
Paper • 2309.11495 • Published • 39 -
CodePlan: Repository-level Coding using LLMs and Planning
Paper • 2309.12499 • Published • 79 -
SCREWS: A Modular Framework for Reasoning with Revisions
Paper • 2309.13075 • Published • 17 -
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Paper • 2309.08532 • Published • 53
audiobook
logical reasoning with llms
-
Language Models can be Logical Solvers
Paper • 2311.06158 • Published • 22 -
Fusion-Eval: Integrating Evaluators with LLMs
Paper • 2311.09204 • Published • 6 -
Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation
Paper • 2311.08877 • Published • 7 -
Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
Paper • 2311.07587 • Published • 5
automl with llms
general agents
-
JaxMARL: Multi-Agent RL Environments in JAX
Paper • 2311.10090 • Published • 8 -
ToolTalk: Evaluating Tool-Usage in a Conversational Setting
Paper • 2311.10775 • Published • 10 -
Contrastive Chain-of-Thought Prompting
Paper • 2311.09277 • Published • 36 -
Testing Language Model Agents Safely in the Wild
Paper • 2311.10538 • Published • 11
finetuning
diffusion models
local llm