Cover Image

The Harder The Better: Maintaining Supervised Fine-tuning Generalization with Less but Harder Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shang, Zhaoyang, Wei, Sibo, Guo, Jianbin, Zhou, Rui, Dong, Lifeng, Luo, Yin
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Overtrained Language Models Are Harder to Fine-Tune
by: Springer, Jacob Mitchell, et al.
Published: (2025)

Reasoning Gets Harder for LLMs Inside A Dialogue
by: Kartáč, Ivan, et al.
Published: (2026)

Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation
by: Dai, Yanqi, et al.
Published: (2026)

Adaptive Loops and Memory in Transformers: Think Harder or Know More?
by: Frey, Markus, et al.
Published: (2026)

Code-Switched Language Identification is Harder Than You Think
by: Burchell, Laurie, et al.
Published: (2024)

Generating Harder Cross-document Event Coreference Resolution Datasets using Metaphoric Paraphrasing
by: Ahmed, Shafiuddin Rehan, et al.
Published: (2024)

Think Multilingual, Not Harder: A Data-Efficient Framework for Teaching Reasoning Models to Code-Switch
by: Lin, Eleanor M., et al.
Published: (2026)

Harder to Defend: Towards Chinese Toxicity Attacks via Implicit Enhancement and Obfuscation Rewriting
by: Kang, Jingyi, et al.
Published: (2026)

BIOME-Bench: A Benchmark for Biomolecular Interaction Inference and Multi-Omics Pathway Mechanism Elucidation from Scientific Literature
by: Wei, Sibo, et al.
Published: (2025)

Can Language Models Be Tricked by Language Illusions? Easier with Syntax, Harder with Semantics
by: Zhang, Yuhan, et al.
Published: (2023)

Fine-tune Smarter, Not Harder: Parameter-Efficient Fine-Tuning for Geospatial Foundation Models
by: Marti-Escofet, Francesc, et al.
Published: (2025)

Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?
by: Yang, Zhe, et al.
Published: (2024)

Using Perspectival Words Is Harder Than Vocabulary Words for Humans and Even More So for Multimodal Language Models
by: Dong, Dota Tianai, et al.
Published: (2025)

A benchmark dataset for evaluating Syndrome Differentiation and Treatment in large language models
by: Li, Kunning, et al.
Published: (2025)

Simpler becomes Harder: Do LLMs Exhibit a Coherent Behavior on Simplified Corpora?
by: Anschütz, Miriam, et al.
Published: (2024)

Harder Tasks Need More Experts: Dynamic Routing in MoE Models
by: Huang, Quzhe, et al.
Published: (2024)

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems
by: Walder, Christian, et al.
Published: (2025)

Work Smarter...Not Harder: Efficient Minimization of Dependency Length in SOV Languages
by: Ranjan, Sidharth, et al.
Published: (2024)

Formalization of Harder-Narasimhan theory
by: Yuan, Yijun
Published: (2025)

Hint Tuning: Less Data Makes Better Reasoners
by: Fan, Siqi, et al.
Published: (2026)

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models
by: Yao, Kai, et al.
Published: (2024)

Facts are Harder Than Opinions -- A Multilingual, Comparative Analysis of LLM-Based Fact-Checking Reliability
by: Saju, Lorraine, et al.
Published: (2025)

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition
by: Dong, Guanting, et al.
Published: (2023)

SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving
by: Tao, Chaofan, et al.
Published: (2026)

The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models
by: Tan, Yuqiao, et al.
Published: (2025)

Two-stage LLM Fine-tuning with Less Specialization and More Generalization
by: Wang, Yihan, et al.
Published: (2022)

Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement
by: Dong, Yichen, et al.
Published: (2025)

Multi-Party Supervised Fine-tuning of Language Models for Multi-Party Dialogue Generation
by: Wang, Xiaoyu, et al.
Published: (2024)

Data-efficient LLM Fine-tuning for Code Generation
by: Lv, Weijie, et al.
Published: (2025)

RoMa v2: Harder Better Faster Denser Feature Matching
by: Edstedt, Johan, et al.
Published: (2025)

FormCoach: Lift Smarter, Not Harder
by: Zuo, Xiaoye, et al.
Published: (2025)

Pensez: Less Data, Better Reasoning -- Rethinking French LLM
by: Ha, Huy Hoang
Published: (2025)

Explain Less, Understand More: Jargon Detection via Personalized Parameter-Efficient Fine-tuning
by: Wu, Bohao, et al.
Published: (2025)

Financial Sentiment Analysis: Leveraging Actual and Synthetic Data for Supervised Fine-tuning
by: Atsiwo, Abraham
Published: (2024)

RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response
by: Luo, Junyu, et al.
Published: (2024)

Fine-tuning Quantized Neural Networks with Zeroth-order Optimization
by: Shang, Sifeng, et al.
Published: (2025)

Better Process Supervision with Bi-directional Rewarding Signals
by: Chen, Wenxiang, et al.
Published: (2025)

Coarse-to-fine Alignment Makes Better Speech-image Retrieval
by: Zhou, Lifeng, et al.
Published: (2024)

Rejection in Abstract Argumentation: Harder Than Acceptance?
by: Fichte, Johannes K., et al.
Published: (2024)

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
by: Zhou, Huichi, et al.
Published: (2025)