Pith. sign in

REVIEW 5 cited by

From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning

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 2501.11877 v1 pith:7HHJWTOF submitted 2025-01-21 cs.CL cs.AI

Yafu Li , Zhilin Wang , Tingchen Fu , Ganqu Cui , Sen Yang , Yu Cheng This is my paper · ORCID
classification cs.CLcs.AI
keywords modelaggregationdataperformancefine-tuningfurtherincreasingllama3
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Scaling data and model size has been proven effective for boosting the performance of large language models. In addition to training-time scaling, recent studies have revealed that increasing test-time computational resources can further improve performance. In this work, we introduce Aggregation Fine-Tuning (AFT), a supervised finetuning paradigm where the model learns to synthesize multiple draft responses, referred to as proposals, into a single, refined answer, termed aggregation. At inference time, a propose-and-aggregate strategy further boosts performance by iteratively generating proposals and aggregating them. Empirical evaluations on benchmark datasets show that AFT-trained models substantially outperform standard SFT. Notably, an AFT model, fine-tuned from Llama3.1-8B-Base with only 64k data, achieves a 41.3% LC win rate on AlpacaEval 2, surpassing significantly larger LLMs such as Llama3.1-405B-Instruct and GPT4. By combining sequential refinement and parallel sampling, the propose-and-aggregate framework scales inference-time computation in a flexible manner. Overall, These findings position AFT as a promising approach to unlocking additional capabilities of LLMs without resorting to increasing data volume or model size.

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. Efficient Reasoning on the Edge

    cs.LG 2026-03 accept novelty 5.5 of 10

    LoRA adapters, budget-forced GRPO, dynamic switching, parallel verification and FPTQuant enable practical chain-of-thought reasoning on quantized Qwen2.5-7B for edge devices.

  2. Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

    cs.CL 2025-08 conditional novelty 5.0 of 10

    Anchoring rejected responses to the initial model and choosing responses from a future model raises AlpacaEval 2.0 win rate from 19.69 to 29.44 for Llama3.1-8B.

  3. How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs

    cs.MA 2025-07 conditional novelty 5.0 of 10

    A leader LLM trained with a GRPO variant that conditions on frozen agent responses improves both collaborative and zero-shot accuracy on BBH, MATH, and MMLU.

  4. Multilingual Test-Time Scaling via Initial Thought Transfer

    cs.CL 2025-05 reject novelty 5.0 of 10

    MITT, a prefix-tuning method for multilingual test-time scaling, is evaluated on questions whose English reasoning was used for training, confounding the reported gains.

  5. Detection, Classification, and Mitigation of Gender Bias in Large Language Models

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A Chinese gender-bias system using SFT, chain-of-thought, and DPO with GPT-4-generated preference pairs reports top validation scores and first place on all three NLPCC 2025 subtasks.

Pith tools