Pith. sign in

REVIEW 2 cited by

Tree Prompting: Efficient Task Adaptation without Fine-Tuning

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

arxiv 2310.14034 v1 pith:TCOSWXEB submitted 2023-10-21 cs.CL cs.LG

classification cs.CLcs.LG
keywords promptingtreeaccuracycallfine-tuningtaskadaptationallow
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Prompting language models (LMs) is the main interface for applying them to new tasks. However, for smaller LMs, prompting provides low accuracy compared to gradient-based finetuning. Tree Prompting is an approach to prompting which builds a decision tree of prompts, linking multiple LM calls together to solve a task. At inference time, each call to the LM is determined by efficiently routing the outcome of the previous call using the tree. Experiments on classification datasets show that Tree Prompting improves accuracy over competing methods and is competitive with fine-tuning. We also show that variants of Tree Prompting allow inspection of a model's decision-making process.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Data-Efficient Adaptation of LLMs via Attention Head Reweighting

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Learning a single scalar per attention head lets LLMs adapt to few-shot text classification better than LoRA, with 200–1000x fewer trainable parameters.

  2. Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Data

    cs.AI 2025-05 reject novelty 5.0 of 10

    An LLM-generated set of yes/no founder questions, combined by simple threshold voting, is reported to predict startup success with 13.1% precision versus a 1.9% base rate, though the supporting evidence has significant gaps.

Pith tools