Pith. sign in

REVIEW 4 cited by

Boosted Prompt Ensembles for Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2304.05970 v1 pith:NCRT4WY7 submitted 2023-04-12 cs.CL cs.LG

Silviu Pitis , Michael R. Zhang , Andrew Wang , Jimmy Ba This is my paper · ORCID
classification cs.CLcs.LG
keywords promptboostedensembleslanguageensembleexampleslargemodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Methods such as chain-of-thought prompting and self-consistency have pushed the frontier of language model reasoning performance with no additional training. To further improve performance, we propose a prompt ensembling method for large language models, which uses a small dataset to construct a set of few shot prompts that together comprise a ``boosted prompt ensemble''. The few shot examples for each prompt are chosen in a stepwise fashion to be ``hard'' examples on which the previous step's ensemble is uncertain. We show that this outperforms single-prompt output-space ensembles and bagged prompt-space ensembles on the GSM8k and AQuA datasets, among others. We propose both train-time and test-time versions of boosted prompting that use different levels of available annotation and conduct a detailed empirical study of our algorithm.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 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. Visual Instance-aware Prompt Tuning

    cs.CV 2025-07 conditional novelty 5.0 of 10

    ViaPT generates instance-aware prompts per image, fuses them with dataset-level prompts, and applies PCA compression to outperform VPT-Deep and other PEFT baselines on FGVC, HTA, and VTAB-1k.

  3. An Adversary-Resistant Multi-Agent LLM System via Credibility Scoring

    cs.MA 2025-05 conditional novelty 5.0 of 10

    A credibility-scoring framework for multi-agent LLM systems, learning agent trustworthiness on the fly and weighting outputs accordingly, improves accuracy under adversarial conditions in some benchmarks.

  4. Ensembles of Low-Rank Expert Adapters

    cs.CL 2025-01 conditional novelty 5.0 of 10

    ELREA clusters instruction-tuning data by gradient direction, trains one LoRA expert per cluster, and routes new instructions to experts via gradient similarity, giving modest benchmark gains over full-data LoRA.

Pith tools