Large Language Model
Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery Katie Z Luo
Instead of labels, we use simple heuristics to mimic human feedback.
Composing Parameter-Efficient Modules with Arithmetic Operations
Our approach requires no additional training and enables highly flexible module composition.
Learning to Reason and Memorize with Self-Notes
Large language models have been shown to struggle with multi-step reasoning, and do not retain previous reasoning steps for future use. We propose a simple method for solving both of these problems by allowing the model to take Self-Notes . Unlike recent chain-of-thought or scratchpad approaches, the model can deviate from the input context at any time to explicitly think and write down its thoughts.
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Language models are increasingly being deployed for general problem solving across a wide range of tasks, but are still confined to token-level, left-to-right decision-making processes during inference.