8 papers
Training Large Language Models to Reason in a Continuous Latent Space
Shibo Hao, Sainbayar Sukhbaatar, DiJia Su +4
Large language models (LLMs) are typically constrained to reason in the language space, where they express the reasoning process through a chain-of-thought (CoT) to solve complex p…
CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks
Ping Yu, Jack Lanchantin, Tianlu Wang +6
We propose CoT-Self-Instruct, a synthetic data generation method that instructs LLMs to first reason and plan via Chain-of-Thought (CoT) based on given seed tasks, and then generat…
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
DiJia Su, Sainbayar Sukhbaatar, Michael Rabbat +2
In cognition theory, human thinking is governed by two systems: the fast and intuitive System 1 and the slower but more deliberative System 2. Analogously, Large Language Models (L…
Self-Consistency Preference Optimization
Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang +6
Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex…
Self-Rewarding Language Models
Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho +4
We posit that to achieve superhuman agents, future models require superhuman feedback in order to provide an adequate training signal. Current approaches commonly train reward mode…
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
Yifei Zhou, Song Jiang, Yuandong Tian +4
Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks. However, existing multi-turn RL algorithms for optimizing LLM agents fail to perform…