REVIEW 4 cited by
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
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
We introduce Reprompting, an iterative sampling algorithm that automatically learns the Chain-of-Thought (CoT) recipes for a given task without human intervention. Through Gibbs sampling, Reprompting infers the CoT recipes that work consistently well for a set of training samples by iteratively sampling new recipes using previously sampled recipes as parent prompts to solve other training problems. We conduct extensive experiments on 20 challenging reasoning tasks. Results show that Reprompting outperforms human-written CoT prompts substantially by +9.4 points on average. It also achieves consistently better performance than the state-of-the-art prompt optimization and decoding algorithms.
Forward citations
Cited by 4 Pith papers
-
Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing
A bootstrapping algorithm that trains program synthesis models on their own successful outputs and on repaired failures modestly improves pass@k over regular fine-tuning on MBPP, with mixed results on APPS.
-
Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement
A multi-agent prompt-rewriting loop is claimed to improve LLM emotion diagnosis accuracy, but its evaluation appears to optimize on the test set and lacks replication details.
-
Leveraging LLMs for Formal Software Requirements -- Challenges and Prospects
LLM-based formalisation of software requirements is promising but faces five persistent challenges; the proposed VERIFAI framework plans to address them with human-in-the-loop and tool-neutral pipelines.
-
A Short Survey on Formalising Software Requirements using Large Language Models
A survey summarizing 35 papers on using LLMs to formalize software requirements, but it contains no new experimental results and its classification tables have errors.
Discussion (0). Sign in to comment.