Pith. sign in

REVIEW 5 cited by

sDPO: Don't Use Your Data All at Once

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 2403.19270 v2 pith:3UJ7O2U2 submitted 2024-03-28 cs.CL cs.AI

classification cs.CLcs.AI
keywords sdpomodelsoncepreferencestepwisethemalignedaligning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As development of large language models (LLM) progresses, aligning them with human preferences has become increasingly important. We propose stepwise DPO (sDPO), an extension of the recently popularized direct preference optimization (DPO) for alignment tuning. This approach involves dividing the available preference datasets and utilizing them in a stepwise manner, rather than employing it all at once. We demonstrate that this method facilitates the use of more precisely aligned reference models within the DPO training framework. Furthermore, sDPO trains the final model to be more performant, even outperforming other popular LLMs with more parameters.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Test-Time Scaling via Error Localization

    cs.LG 2026-07 conditional novelty 6.0 of 10

    TTEL uses feedback-induced token probability drops to localize the first error in a failed reasoning trace and branch a new generation from that prefix, improving pass@k per token on coding and math benchmarks.

  2. TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization

    cs.SD 2024-12 conditional novelty 6.0 of 10

    A fast flow-matching text-to-audio model aligned via CLAP-ranked self-generated preference pairs reports state-of-the-art AudioCaps and human-evaluation scores.

  3. CTR-Driven Ad Text Generation via Online Feedback Preference Optimization

    cs.IR 2025-07 conditional novelty 5.0 of 10

    CTOP combines retrieval-augmented style transfer with DPO weighted by CTR gain and AA-group confidence, achieving +4.76% relative CTR over human-written ad titles in online tests.

  4. PerPO: Perceptual Preference Optimization via Discriminative Rewarding

    cs.AI 2025-02 conditional novelty 5.0 of 10

    PerPO trains multimodal LLMs by ranking their candidate answers with deterministic visual rewards (IoU, edit distance) and using the reward differences as margins in listwise preference optimization.

  5. An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems

    cs.CL 2024-12 unverdicted novelty 3.0 of 10

    A survey and position paper that reviews LLM prompting, RAG, and RL techniques and argues they could support open-ended implementation generation, without presenting new results.

Pith tools