SoFT: Soft Targets for Generalizable LLM Fine-Tuning

arXiv:2609.32493 · cs.LG, cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/huggingface/open-r1

Terminology

• Benchmark — 25× in this paper · explained in 2 episodes
• Fine-Tuning — 16× in this paper · explained in 5 episodes
• Agentic Task — 9× in this paper · explained in 1 episode
• Agentic Tasks — 9× in this paper · explained in 1 episode
• Trace — 8× in this paper · explained in 2 episodes
• Distillation — 7× in this paper · explained in 2 episodes
• Generalization — 6× in this paper · explained in 13 episodes
• Reasoning Traces — 3× in this paper · explained in 3 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Agentic Evaluation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Calibration — 2× in this paper · explained in 7 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 3 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
• Program Synthesis with Large Language Models
• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• Llama-Nemotron: Efficient Reasoning Models
• Qwen3-Coder-Next Technical Report
• Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning
• BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• OpenThoughts: Data Recipes for Reasoning Models
• Measuring Coding Challenge Competence With APPS
• Tmax: A simple recipe for terminal agents
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• ProCUA-SFT Technical Report
• In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners
• Kimi K2.5: Visual Agentic Intelligence
• Kimi K3: Open Frontier Intelligence
• Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks