Pith. sign in

REVIEW 3 cited by

Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models

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 2508.11953 v1 pith:BLVJMANI submitted 2025-08-16 cs.AI

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

Optimizing data mixtures for supervised fine-tuning (SFT) of large language models (LLMs) is critical for developing general-purpose models, yet this area remains underexplored. In this paper, we frame data mixing as an optimization problem and introduce a novel method designed to minimize validation loss. Our approach parametrizes the loss by modeling effective data transferred and leveraging scaling laws for fine-tuning. By experimenting with various small-scale data mixtures, we fit these parameters and derive the optimal weights. We provide both mathematical proofs and empirical results demonstrating that our algorithm achieves excellent overall and individual performance across all domains. Through controlled experiments, we show that models trained with our optimized weights perform on par with those using optimal weights determined via grid search, with per-domain loss only 0.66% higher than the best domain loss from grid search on average. Additionally, we show that reweighting popular SFT datasets using our method improves both validation loss and downstream performance. Finally, we discuss how our method can generalize to guide data selection for domain-specific models and provide insights into SFT.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Bridging Compute- and Data-Optimal Pretraining

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Pretraining loss obeys a single law in which repeated or paraphrased tokens count as η(N, data-per-parameter, expansion-ratio) fresh tokens, with total effective data saturating as derived tokens grow.

  2. AgentOmnia: Scaling Agentic Models for Full-Scenario Applications

    cs.AI 2026-07 conditional novelty 5.0 of 10

    Post-training an open Qwen3-30B agent on 52,361 verifiable tasks in 5,018 synthesized stateful environments lifts its average across four agent benchmarks from 22.9% to 41.7%.

  3. Learning Task Mixtures from Task Affinities: A Probabilistic Graphical Model for Supervised Fine-Tuning

    cs.LG 2025-07 conditional novelty 5.0 of 10

    TaskPGM optimizes a quadratic energy over task mixtures using PMI/JSD behavioral affinities, yielding mixtures that outperform naive sampling on several 7B LLM fine-tuning benchmarks.

Pith tools