REVIEW 7 cited by
Thinking LLMs: General Instruction Following with Thought Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
LLMs are typically trained to answer user questions or follow instructions similarly to how human experts respond. However, in the standard alignment framework they lack the basic ability of explicit thinking before answering. Thinking is important for complex questions that require reasoning and planning -- but can be applied to any task. We propose a training method for equipping existing LLMs with such thinking abilities for general instruction following without use of additional human data. We achieve this by an iterative search and optimization procedure that explores the space of possible thought generations, allowing the model to learn how to think without direct supervision. For each instruction, the thought candidates are scored using a judge model to evaluate their responses only, and then optimized via preference optimization. We show that this procedure leads to superior performance on AlpacaEval and Arena-Hard, and shows gains from thinking on non-reasoning categories such as marketing, health and general knowledge, in addition to more traditional reasoning & problem-solving tasks.
Forward citations
Cited by 7 Pith papers
-
Reasoning Up the Instruction Ladder for Controllable Language Models
RLVR on ~7K verifiable system/user conflict examples teaches LLMs to prioritize higher-priority instructions, improving instruction-hierarchy and safety benchmarks.
-
Is Visual in-Context Learning for Compositional Medical Tasks within Reach?
Training on synthetic compositional task sequences with sequence-level masking lets a transformer-based in-context learner follow multi-step medical imaging instructions on held-out images, but well below codebook upp...
-
Bridging Offline and Online Reinforcement Learning for LLMs
Semi-online DPO, which syncs the generation model every few update steps, performs nearly as well as fully online DPO and GRPO, while strongly beating offline DPO.
-
Typhoon T1: An Open Thai Reasoning Model
Structured long-thinking SFT turns a 3B Thai instruct model into a reasoning model that improves on several English benchmarks and can think in Thai, with a fully open recipe.
-
BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning
BRiTE is an EM-style algorithm that uses RL to sample high-likelihood reasoning chains and fine-tunes the LLM on them, with a theoretical 1/T convergence rate and mixed empirical gains.
-
Large Language Models for Planning: A Comprehensive and Systematic Survey
A structured survey of LLM planning methods, benchmarks, and interpretability work, organized around a three-way taxonomy.
-
Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI
A qualitative taxonomy positions vibe coding and agentic coding as complementary paradigms rather than rivals in AI-assisted software development.
Discussion (0). Continue with ORCID to comment.