paper-with-me

홈 › Papers

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition

2023-10-09 · Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou

Large language models (LLMs) with enormous pre-training tokens and parameters emerge diverse abilities, including math reasoning, code generation, and instruction following. These abilities are further enhanced by supervised fine-tuning (SFT). While the open-source community has explored ad-hoc SFT for enhancing individual capabilities, proprietary LLMs exhibit versatility across various skills. Therefore, understanding the facilitation of multiple abilities via SFT is paramount. In this study, we specifically focuses on the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during SFT. We propose four intriguing research questions to explore the association between model performance and various factors including data amount, composition ratio, model size and SFT strategies. Our experiments reveal that distinct capabilities scale differently and larger models generally show superior performance with same amount of data. Mathematical reasoning and code generation consistently improve with increasing data amount, whereas general abilities plateau after roughly a thousand samples. Moreover, we observe data composition appears to enhance various abilities under limited data conditions, yet can lead to performance conflicts when data is plentiful. Our findings also suggest the amount of composition data influences performance more than the composition ratio. In analysis of SFT strategies, we find that sequentially learning multiple skills risks catastrophic forgetting. Our proposed Dual-stage Mixed Fine-tuning (DMT) strategy offers a promising solution to learn multiple abilities with different scaling patterns.

📄 PDF Abstract BibTeX arXiv:2310.05492

Code (2)

ofa-sys/gsm8k-screl 공식 구현 pytorch
wangrongsheng/caregpt

Tasks

Code GenerationInstruction FollowingMathMathematical Reasoning

Methods 이 논문이 사용한 방법론

SFT Shrink and Fine-Tune, or SFT, is a type of distillation that avoids explicit distillation by copying parameters to a student student model and then fine-tuning.…
Focus 설명 없음

Similar Papers 제목 키워드 기반

On the capabilities of LLMs for classifying and segmenting time series of fruit picking motions into primitive actions

2025-07-10 · Eleni Konstantinidou, Nikolaos Kounalakis, Nikolaos Efstathopoulos, Dimitrios Papageorgiou arxiv

Despite their recent introduction to human society, Large Language Models (LLMs) have significantly affected the way we tackle mental challenges in our everyday lives. From optimizing our linguistic communication to assi…

Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models

2025-05-06 · Bin Yu, Hang Yuan, Haotian Li, Xueyin Xu 외

Recent advances in large language models have demonstrated that Supervised Fine-Tuning (SFT) with Chain-of-Thought (CoT) reasoning data distilled from large reasoning models (e.g., DeepSeek R1) can effectively transfer r…

Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models

2024-05-01 · Leonardo Ranaldi, Andrè Freitas

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although th…

Math

The Poison of Alignment

2023-08-25 · Aibek Bekbayev, Sungbae Chun, Yerzat Dulat, James Yamazaki

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs se…

MMLU

OpenCodeReasoning: Advancing Data Distillation for Competitive Coding

2025-04-02 · Wasi Uddin Ahmad, Sean Narenthiran, Somshubra Majumdar, Aleksander Ficek 외

Since the advent of reasoning-based large language models, many have found great success from distilling reasoning capabilities into student models. Such techniques have significantly bridged the gap between reasoning an…

Diversity