Supervised Fine-Tuning

Also known as SFT

Follow this topic Ask about this topic

Latest papers 208

29 papers in the last four weeks, up 12% on the four weeks before. 0.2% of all new papers.

Aug 16, 2026

Self-Specialized Teachers for Domain Post-Training

Target-only post-training can improve performance in a specialized domain while degrading behaviors that a general-purpose base model acquired before adaptation. We study this problem when target-domain data are available but a representative replay corpus is not. We propose self-specialized teacher distillation (SSTD), a two-stage procedure that first trains a copy of the base model into a domain teacher, then distills its token distribution to a student on prefixes sampled from the student itself. Teacher training combines standard target supervision with base-aware key-token weighting and distribution alignment to the frozen base model; on-policy distillation then places domain feedback on states the student can encounter at inference time. On financial numerical reasoning, medical question answering, and legal holding identification, SSTD retains much of the target improvement of direct fine-tuning while improving the mean score on the evaluated general suite by 4.8--5.0 points at the reported operating point. The pattern persists across Qwen3 sizes and on Gemma backbones. SSTD requires neither an external teacher nor general replay data.

Yifei Li, Rongman Xu, Lingling Zhang +5

School of Computer Science and Technology, Xi’an Jiaotong University · MOE KLNN Lab, Xi’an Jiaotong University

Domain Adaptation for LLMs Catastrophic Forgetting Knowledge Distillation Supervised Fine-Tuning

Aug 13, 2026

Capacity-Dependent Effects of Data Selection for Reasoning

In reasoning supervised fine-tuning, candidate responses for the same instruction can differ substantially in how well they match the student's current distribution. Recent likelihood-based response selection methods suggest that responses closer to the student distribution provide more effective supervision, motivating the hypothesis that high-likelihood responses may generally be preferable for fine-tuning. In this paper, we revisit this intuition and show that the value of likelihood-based data selection depends critically on model capacity and training duration. Through controlled experiments on mathematical reasoning, using students ranging from 1.5B to 8B parameters and supervision generated by stronger teacher models, we observe a clear capacity-dependent ``{\color{SMALLCOLOR}Fast-Fit} / {\color{LARGECOLOR}Slow-Gain}'' pattern. High-likelihood data provides faster and more stable early improvements, especially for smaller models, but low-likelihood data becomes increasingly beneficial for larger models when training is allowed to continue longer. To explain this phenomenon, we analyze learning dynamics, showing that small models often fail to absorb low-likelihood supervision and instead fall into shallow or repetitive behaviors, while larger models are better able to move toward the teacher distribution under such data. We further provide a capacity-constrained theoretical view of distillation that clarifies how data difficulty, data span, and student capacity jointly govern transfer. Overall, our findings show that effective data selection for reasoning should be aware of model capacity and computing budget rather than based on a single universal preference for high-likelihood supervision.

Cuong Dang, Hoang Anh Just, Ruoxi Jia

Department of Electrical and Computer Engineering Virginia Tech Blacksburg, VA, USA

Instruction-Tuning Data Selection Supervised Fine-Tuning Selective Knowledge Distillation LLM Reasoning Knowledge Distillation

Aug 13, 2026

Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?

Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought (CoT) reasoning has become the dominant approach, with HumanOmniV2 and its IntentBench benchmark as a prominent reference point. In this context, we report three findings. First, IntentBench is highly noisy:

\sim

7% of questions are broken and

\sim

23% are trivially answerable without the video input. We remove the affected questions and release Intentbench-Prime. Second, current reasoning approaches are expensive and surprisingly ineffective. A simple Vanilla SFT baseline matches or outperforms existing reasoning methods across three benchmarks at a fraction of the cost, establishing it as an essential baseline for evaluating novel fine-tuning techniques. Third, our analysis reveals that substantial priors can be learned solely from the text modality and that using a textual caption instead of the video yields performance on par with Vanilla SFT. These surprising findings reveal the limitations of current MLLMs when it comes to social understanding. IntentBench-Prime, Vanilla SFT model, and code are publicly available.

Koen P. de Vries, Xavier Alameda-Pineda, Estefanía Talavera +1

Inria at Univ. Grenoble Alpes, CNRS, LJK, France · University of Twente, The Netherlands

Supervised Fine-Tuning Multimodal Large Language Models Audio-Visual QA

Aug 12, 2026

When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use

The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings. A common failure occurs when a model selects the correct tool but generates argument values in an inconsistent language, which we term Argument Language Mismatch (ALM). Although semantically correct, such outputs are operationally invalid and not captured by standard API-calling metrics. We revisit post-training strategies for mitigating ALM and find that, in our benchmark, supervised fine-tuning (SFT) provides a strong baseline, substantially improving argument language consistency and end-to-end function call accuracy. Under consistent model selection, SFT achieves performance comparable to, and sometimes exceeding more complex reinforcement learning (RL) approaches. We further examine whether RL with structured, argument-aware rewards offers additional benefits. While methods such as Group Relative Policy Optimization (GRPO) can improve language consistency and better preserve general reasoning ability, these gains are incremental and most pronounced in generalization and multi-objective trade-offs. Overall, our results suggest that much of the performance in multilingual API grounding can be achieved through careful supervised training, with RL providing targeted rather than fundamental improvements.

Siddharth Chauhan, Thomas Butler, Abhishek Singhania +2

Amazon.

Supervised Fine-Tuning Multilingual Language Model Evaluation RL for Language Models Cross-Lingual Consistency in Language Models

Aug 11, 2026

Weightless Fine-Tuning: Personalizing LLMs via Logit-Space Transport

Supervised fine-tuning (SFT) is a standard approach for adapting LLMs to a target distribution, but in settings such as personalization, where each author requires separate weight access, optimization, storage, and retraining, its costs become prohibitive. We propose Weightless Fine-Tuning (WFT), a training-free decoding-time method that approximates the distributional effect of SFT without weight updates. WFT computes supervised residuals on an author's training sequence and transports them to the current prompt through a cross-prefix transport operator estimated from dropout-induced cross-covariance. The operator captures how a perturbation at one context propagates to predictions at another, replacing gradient-based parameter updates with logit-space corrections. On three LaMP personalization benchmarks, WFT achieves the best average performance across datasets, matches or exceeds SFT on individual tasks, and outperforms other lightweight baselines on average. In a budget-controlled comparison, WFT approaches SFT performance using less than 7% of the effective computation. Logit-level analysis shows a cosine similarity of 0.875 between the logit shifts induced by WFT and SFT over 95% of the next-token probability mass, suggesting that WFT captures the distributional effect of supervised adaptation without modifying model weights.

Bohan Zhang, Anqi Ni, Yixin Wang +1

University of Michigan · University of Chicago

Supervised Fine-Tuning LLM Personalization LLM Fine-Tuning Inference-Time Language Model Alignment

Aug 8, 2026

Adaptive Supervised Anchoring for On-Policy Self-Distillation

On-policy self-distillation (OPSD) adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student. Its effectiveness, however, depends critically on the quality of those trajectories. We show that when student rollouts drift from target trajectories, conditioning the teacher on off-target prefixes substantially weakens its task-relevant supervision. Controlled prefix-corruption experiments expose this failure mode, which we term rollout-conditioned signal degradation. To address this problem, we propose a unified training framework that separates two complementary supervision pathways. The first retains rollout-conditioned distribution matching, providing guidance on states the student actually visits. The second applies supervised cross-entropy on canonical ground-truth contexts, avoiding the incompatibility of imposing target tokens on erroneous rollout prefixes. Token-level rollout-target alignment is used to adapt the strength of the canonical-context anchor, emphasizing it during cold start and relaxing it as rollout quality improves. Experiments across multiple model scales, two task families, and general-reasoning benchmarks show that the proposed approach improves task acquisition over OPSD while preserving general capabilities, resulting in a more favorable empirical plasticity-stability trade-off. These findings identify context quality as a central bottleneck in on-policy self-distillation and demonstrate the value of separating rollout-conditioned guidance from canonical supervision.

Meilin Yang, Zixuan Ding, Jianhao Nie +5

Renmin University of China, Beijing, China · Renmin University of China, Beijing, China.

Supervised Fine-Tuning On-Policy Self-Distillation Language Model Distillation LLM Reasoning

Aug 5, 2026

Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training

Procedural generators produce useful verifiable reasoning problems at scale, but have received less attention as data for completion-supervised fine-tuning. We introduce Reasoning Core, a collection of 50 generators spanning mathematics, logic, planning, state tracking, formal languages, structured data, games, causality, and code, with semantic scorers, difficulty controls, and task evaluators. Under a matched completion-supervised protocol, we compare Reasoning Core with Procedural Warmup, Reasoning Gym, and SynLogic across four base-model settings and multiple training durations. In the primary 3B comparison, Reasoning Core achieves the highest mean scores on DROP, LogiQA, and ARC-Challenge, exceeding both the baseline without procedural data and all three alternative procedural collections. Task-level analyses show that semantic validity alone does not ensure training utility, highlighting compact targets and calibrated difficulty as important design factors. We ran audits combining model-assisted review, human adjudication, and regression testing. Applied throughout Reasoning Core development and to the other collections, they reveal subtle mismatches among generation, rendering, targets, and scoring, a reminder that procedural generation alone does not guarantee correctness. The library, generated datasets, and audit material are publicly available.

Damien Sileo, Valentin Lacombe, Dimitri Kachler

Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 - CRIStal, F-59000 Lille, France

Supervised Fine-Tuning Synthetic Data Generation for Language Models LLM Reasoning

Aug 5, 2026

Beyond Full-Model Rollback: AuroSFT for Adapter-State Multi-Task Fine-Tuning

Multi-task supervised fine-tuning (SFT) often casts a heterogeneous data mixture as a single optimization problem, even though different tasks may reach their best generalization at different times. msft exposes this mismatch through task-wise roll-out, exclusion, and rollback, but its original formulation materializes the scheduler state as full-model checkpoints, making stage transitions costly to store, restore, and deploy. This paper introduces AuroSFT, a parameter-efficient framework that recasts the carried state of overfitting-aware multi-task SFT as a compact, mergeable adapter state. AuroSFT freezes the pretrained backbone, trains only injected adapters, rolls back adapter checkpoints at task-wise peaks, and continues on the remaining active mixture. At the layer level, each adapter applies an AuroRA-inspired adaptive nonlinear layer to a low-rank weight factor rather than to the sample representation. The resulting update remains linear in the input, rank-bounded, and exactly mergeable into the frozen projection. Under the retained-backbone comparison protocol, AuroSFT achieves 61.36% average accuracy, compared with 59.85% for the corresponding msft reference row, and obtains higher accuracy on all five backbones. Our code is available at the anonymous repository: https://anonymous.4open.science/r/AuroSFT-80D1.

Yue Han, Ziniu Liu

College of Systems Engineering, National University of Defense Technology · College of Computer Science and Technology, National University of Defense Technology

Supervised Fine-Tuning Multi-Task Learning Adapter Tuning Low-Rank Adaptation Multi-Task Optimization Parameter-Efficient Fine-Tuning

Aug 5, 2026

Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent

Scaling supervision for multi-turn medical agents is difficult because expert dialogue annotation is costly and clinical conversations are privacy-restricted. We introduce Guideline-as-Oracle (GAO), which compiles American Academy of Ophthalmology guidance into a 70-row operational rule table and uses it as the sole source of instance-level supervision for 3,000 training dialogues, reserving human labeling for evaluation. Because converting rules into dialogues is itself a design problem, we catalog eight construction strategies, including cited-row tier assignment, one-fact boundary pairs, metadata-only repair, and label repair, and characterize the evidential status of each: labeling mechanism, null, confounded, or evaluated only as a package. Fine-tuning a 9B backbone on this corpus yields GAO-Triage, improving agreement with a 201-case operational reference from 61.7% to 74.1% (exact McNemar p=0.0046) and emergent-case recall from 9.5% to 69.0%; the gains persist across a second seed and patient simulator. None of the seven general-purpose systems we test dominates GAO-Triage on both metrics, and GAO-Triage requires no frontier model at inference time. Permuting label-dialogue assignments collapses the model to a constant-routine predictor, indicating that the signal lies in guideline-derived assignment rather than dialogue surface form. Label repair coincides with the disappearance of a late-training safety degradation.

Chenyu Wang, Yi Liu, Baoqing Li +2

Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences · Shanghai Artificial Intelligence Laboratory · ByteDance Inc.

Supervised Fine-Tuning Clinical Triage Synthetic Data Generation Medical LLMs

Aug 4, 2026

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) exhibit fundamentally different behaviors in enhancing multi-task reasoning for large language models (LLMs). Our preliminary experiments revealed a phenomenon: SFT suffers from severe task conflicts under multi-stage training, whereas RL enables stable coexistence across diverse tasks. Empirically, we trace this to the parameter level, observing that RL induces sparse and approximately orthogonal updates across tasks. We provide a theoretical explanation for this mechanism by analyzing multi-task gradient interference. Our results reveal a distinction: interference in SFT is norm-limited, scaling with the absolute gradient magnitude, whereas interference in RL is variance-limited, bounded by the gradient variance induced by advantage normalization and on-policy optimization. This small variance bound yields near-orthogonal optimization directions across tasks. Leveraging this insight, we propose Parallel-RL, a paradigm that decouples multi-task training, significantly improving efficiency and flexibility.

Kejian Zhu, Zhuoran Jin, Shangqing Tu +5

The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Tsinghua University, Beijing, China

Supervised Fine-Tuning Gradient Interference Multi-Task Learning Multi-Task RL RL Fine-Tuning

Aug 3, 2026

Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge

Enterprise question answering requires models to acquire proprietary knowledge without discarding general capabilities. We present Wnuan, a three-stage pipeline that constructs task-oriented supervision from documents, performs supervised fine-tuning with general-data replay, and applies reinforcement learning to residual errors. On the 707-question WnuanBench, the primary 32B route raises acceptable-answer rate (AAR) from 52.76% before adaptation to 80.06% after SFT and 91.51% after RL. Under a matched 100-update protocol, residual-error sampling outperforms full-pool and size-matched random sampling by 3.11 and 2.97 points, respectively. Source-cluster bootstrap intervals remain above zero for both contrasts, and a same-domain validation set preserves the ordering. The general-benchmark average decreases by 5.17 points across the route, concentrated in instruction following. The automatic evaluation ensemble agrees with an authoritative domain expert on 90.5% of a stratified Wnuan-Inst response sample. These results characterize both the gains and the general-capability cost of staged enterprise adaptation.

Xiaofeng Shi, Xiaosong Qiu, Wenxin Ma +6

Beijing Academy of Artificial Intelligence (BAAI) · Beijing District Heating Group Co., Ltd. (BDHG) · Beijing University of Posts and Telecommunications (BUPT)

Supervised Fine-Tuning Knowledge Augmentation for Language Models LLM Post-Training

Jul 31, 2026

CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning

While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-source, limiting downstream users' ability to adapt them to new tasks, embodiments, and deployment settings. Following the LLM community, an emerging access paradigm for closed-weight robot foundation models is the managed supervised fine-tuning (SFT) API, where users submit training data and receive a tuned policy without access to model weights, gradients, or training internals. While such APIs let downstream users leverage powerful proprietary foundation models, they restrict policy improvement to pure imitation, ruling out reinforcement learning and other closed-loop methods that rely on internal training signals. This limitation is particularly acute for agile, contact-rich humanoid manipulation, where the gap between policy outputs and deployed behavior is large due to novel states, action tracking dynamics, latency, and controller-specific failure modes. We study how effective this managed-API regime is for humanoid adaptation, and how closed-loop improvement can be realized within it to push policies toward task mastery. We conduct one of the first empirical studies of managed-API adaptation on a real humanoid, instantiated on Gemini Robotics On-Device (GROD). We find that direct SFT through the API substantially outperforms a leading open-weight VLA trained on the same demonstrations, yet still falls short of deployment-level mastery on agile, contact-rich tasks. To close this gap, we introduce CLIFT: Closed-Loop Iterative Fine-Tuning, which turns deployment-time reward feedback into API-compatible supervised data and enables closed-loop policy improvement without accessing weights, gradients, likelihoods, or losses-pushing GROD to near-perfect success after two flywheel cycles, all without "opening the model box."

Yuxin Chen, Hari Srikanth, Nathan Jew +7

University of California, Berkeley · Google DeepMind · NVIDIA Research

Supervised Fine-Tuning Fine-Tuning Robot Policy Adaptation Robot Skill Learning Robot Foundation Models Humanoid Robot Control

Jul 30, 2026

Objective-Aligned Direct Answer SFT for Robust Multi-Frame Medical VQA

Multi-frame medical VQA appears to reward increasingly complex adaptation: controller-style inference, localization-aware reranking, static hard-negative mixing, and staged continuation all appear plausible from first principles. We test a simpler competing hypothesis on MedFrameQA: methods that remain tightly aligned with the benchmark's final answer objective should be the strongest robust adaptation family once evaluation is controlled across fixed splits, matched budgets, repeated seeds, and calibration. We compare controller-based methods, scaffold evolution, static mixed supervision, continuation-heavy variants, and direct answer-only supervised fine-tuning (SFT). The strongest robust family is direct decoder-only answer SFT on MedGemma-1.5-4B. Empirically, this family yields substantial improvements in held-out report accuracy over frozen baselines while remaining remarkably stable across repeated seeds and matched controls, ensuring our claims reflect true family-level robustness rather than an isolated hyperparameter peak. Furthermore, post-hoc calibration effectively repairs confidence estimation without compromising accuracy, and the core approach transfers consistently to secondary backbones like Qwen2.5-VL-3B. The main result is therefore not that a complex auxiliary mechanism wins, but that objective-aligned direct answer SFT is the strongest robust adaptation family we found for MedFrameQA. By establishing this strong, minimalist baseline, we hope to redirect community focus toward fundamentally robust optimization rather than architectural complexity.

Site Li, Jianyi Hao, Xiaofeng Liu

Yale University

Supervised Fine-Tuning VLM Robustness Medical VQA Medical VLMs

Jul 28, 2026

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models

Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised fine-tuning (SFT) to pursue the same underlying goals. When projects share a goal, we should test whether lessons learned from one area transfer to the other areas. We study three such transfers, each taking a lesson developed in one SFT setting and testing it in another. First, we port a lesson about behavior generalization from alignment training into toy models. Training on the reason for a behavior, as in Teaching Claude Why, can make the behavior generalize better than training on examples of the behavior alone. Second, we port a lesson about capability preservation from model organisms into the Model-Spec Midtraining alignment setting. SFT on outputs written by a model other than the student (off-model outputs) can damage capabilities when trained on. Mixing in benign on-model (and on-policy) data into our training can prevent most of this damage while still embedding the target behavior. Third, we port a lesson about robustness from model organisms into the same alignment setting. We find that follow-up benign SFT can erase the alignment behavior while preserving capabilities, showing that capability preservation alone does not ensure robustness to subsequent training. Our work illustrates how porting SFT lessons between different research fields can uplift them all, suggesting more researchers should borrow techniques from outside their own areas.

Anton de la Fuente, Arthur Conmy

Supervised Fine-Tuning LLM Alignment

Jul 24, 2026

DomainPilot: Domain-Level Loss-Guided Two-Stage Data Mixture Optimization for Efficient Language Model Fine-Tuning

The training efficacy of large language models (LLMs) is fundamentally constrained by the quality and composition of training data. Existing dynamic data scheduling methods face critical limitations in industrial-scale pretraining and supervised fine-tuning (SFT): data selection incurs prohibitive O(N) costs on terabyte-scale corpora, mixture optimization schemes introduce severe I/O bottlenecks or require training auxiliary reference models, and sample-level reweighting strategies rely on loss signals that conflate noise, difficulty, and novelty. We present DomainPilot, a domain-level loss-guided two-stage data mixture optimization framework. DomainPilot introduces token-level domain loss monitoring to capture per-domain learning dynamics during training without halting the data pipeline. Building on these signals, we propose a Scaling Law guided coarse optimization stage that fits domain-specific convergence curves and derives a principled prior for mixture adjustment. A subsequent Mixing Law guided fine optimization stage refines the mixture by modeling cross-domain interaction effects through controlled sweep experiments. The entire mechanism is realized via a patch-based architecture that injects domain-aware loss computation into existing training frameworks (e.g., MindSpeed/Megatron-LM) with only ~30 lines of framework-specific adapter code. We validate DomainPilot on the Qwen3-1.7B model during SFT. Compared to the original data mixture, our optimized mixture achieves improvements of +2% on MMLU-Redux, +1.8% on AIME24, +3.8% on LiveCodeBench v5, and +3.6% on BFCL v3, without increasing total data volume or training cost. These results demonstrate that domain-level training signals provide an effective, lightweight alternative to expensive data selection or auxiliary model training for mixture optimization.

He Zhang

Tsinghua University

Supervised Fine-Tuning Large Language Model-Guided Optimization Efficient Language Model Training Data Mixture Optimization

Jul 21, 2026

SFGA: A Statistics-First Gating Architecture with Adjudicative Escalation for Trustworthy SFT Data Procurement

Procuring supervised fine-tuning (SFT) data forces a buyer to decide, before any downstream training, whether a candidate corpus is worth acquiring. We present \sys{}, a statistics-first gating architecture that treats procurement as a cost-aware routing problem over three intrinsic quality axes -- diversity, utility, and redundancy. Cheap blind measurements are summarised into per-axis estimates with confidence intervals; a gate accepts a decision only when intervals are tight, sample sizes are adequate, and the axes agree, otherwise it escalates the case to an adjudicative debate between a buy-advocate and a reject-advocate judge, resolved by a presiding verdict. On a controlled benchmark of 12 datasets (

2{\times}3{\times}2

grid over the three axes) with 5 seeds, the gate reaches 0.90 accuracy and 0.83

F_1

at $0.017 per unit, sitting between an always-verify baseline (0.75) and an oracle upper bound (0.98) while spending less than always-escalate ($0.020). We further report honest negative diagnostics of the debate path: a con-side win rate of 0.80 (

p\approx3{\times}10^{-6}

) and a 52% position-flip rate under advocate swapping expose negativity and positional biases that a naive LLM-judge would hide. We frame the injected-knob evaluation explicitly as a controlled synthetic benchmark for measurement fidelity and routing calibration, and delimit external validity as future work.

Arther Tian, Alex Ding, Simon Wu +1

DGrid AI

Supervised Fine-Tuning LLM-as-a-Judge Selective Prediction

Jul 20, 2026

A Dual-Hypothesis Reasoning Framework for LLM Guardrails

We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardrails that explicitly considers both safe and unsafe interpretations of a prompt before making a safety decision, and (ii) multi-component supervised fine-tuning (MC-SFT), a structured training loss for reasoning-based guardrails that decomposes LLM outputs into logical components and weights them according to their importance. Existing reasoning-based guardrails often rely on expensive procedures, such as generating reasoning traces using larger or closed-source teacher models and applying full-parameter fine-tuning. In contrast, ARBITER uses a cost-effective self-generation strategy for reasoning traces and LoRA-based parameter-efficient fine-tuning while still achieving better performance than these expensive approaches. Additionally, ARBITER provides faithful evidence-phrase explanations for unsafe decisions, enabling a more transparent and interpretable guardrail method. Experiments on three safety moderation benchmarks show that ARBITER outperforms existing reasoning-based and non-reasoning guardrail baselines, with clear gains in out-of-domain evaluations.

Md Asiful Islam, Fahmida Alam, Mihai Surdeanu

Department of Computer Science University of Arizona, USA

Supervised Fine-Tuning Language Model Safety Evaluation LLM Guardrails Content Moderation

Jul 19, 2026

A Systematic Evaluation of Trajectory Data Curation for LoRA Fine-Tuning of Code Agents

Supervised fine-tuning (SFT) of open-weight LLMs on expert agent trajectories has emerged as a prominent approach to building capable code agents without reliance on proprietary models. A central yet underexplored question is how trajectory quality and quantity jointly shape model performance. We present a systematic empirical study of trajectory data filtering for LoRA fine-tuning of Qwen2.5-Coder-7B-Instruct on the SWE-trajectory dataset (67,074 trajectories, of which 32,161 are resolved). We propose a two-axis quality scoring framework -- Efficiency and Style -- and evaluate it through 16 controlled experiments spanning strategy, scale, and ablation analyses. Since 7B-scale models attain near-zero SWE-bench resolve rates, we adopt cross-entropy (CE) loss on held-out trajectories as the primary metric, validated via first-action generation: CE loss and ROUGE-L are perfectly rank-correlated (Spearman

ρ

= -1.00), with limited-sample evidence supporting but not conclusively establishing this proxy. Our results reveal a scale-dependent quality-quantity trade-off: at small scales, doubling the dataset (500 to 1,000) yields ~12.7% CE-loss reduction whereas the TopQ-Random gap stays <1% (Mann-Whitney p > 0.10); at 2,000 trajectories this same gap widens to 3.6% (p = 0.016). Ablation further identifies error-retry rate as the dominant sub-dimension, performing comparably to the full composite (

Δ

< 0.2%). Together, these findings establish trajectory-level quality scoring as a viable but scale-sensitive lever for code-agent SFT and offer a proxy-validated evaluation protocol for the regime where end-to-end resolve rate is statistically infeasible.

Yunze Han

Vdynamics GmbH, 80935 Munich, Germany

Supervised Fine-Tuning LLM Evaluation AI Coding Agents

Jul 15, 2026

Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion

Large Language Models (LLMs) have revolutionized AI services, but a critical tension emerges: while personalization improves model performance, it consumes scarce computational resources that users must share. When should a user invest in expensive Supervised Fine-Tuning (SFT) versus lightweight In-Context Learning (ICL)? How does congestion from other users' personalization choices reshape these incentives? And what strategies should platforms adopt when offering multiple personalization algorithms? We develop a tractable framework for LLM serving that captures the statistical-economic trade-offs users face. Our analysis yields several surprising insights. First, we show that ICL and SFT dominate in different regimes, determined by an interplay between pretraining coverage and data signal-to-noise ratios, but congestion can flip these rankings. Second, equilibrium resource consumption exhibits pronounced non-monotonicity: improving pretraining precision reduces the congestion, while broader pretraining coverage and harder tasks sometimes increase it. Third, we prove that offering both personalization methods never hurts the platform's maximal profits, despite potentially increasing computational load. Experiments with GPT-2 on linear regression tasks validate our theoretical predictions about algorithm performance. Complementing these results, our review of documentation from 21 major AI platforms shows that the share offering both SFT and ICL increased from 9.5% in 2021 to 71.4% in 2025, consistent with our platform-design implications.

Fengzhuo Zhang, Zhuoran Yang, Dirk Bergemann

Yale University, 30 Hillhouse Ave., New Haven, CT 06520, USA

Supervised Fine-Tuning LLM Serving LLM Personalization Cost-Aware Inference In-Context Learning

Jul 15, 2026

Rethinking Speech Foundation Model Fine-tuning: Better SFT or Better Match?

Supervised fine-tuning (SFT) is widely used to adapt self-supervised speech representations to downstream classification tasks. Small gains observed under a single pretrained checkpoint are often interpreted as method-level improvements, i.e., a higher attainable performance ceiling. We show that such conclusions are not always reliable because SFT outcomes depend strongly on the specific pretrained instance. We conduct a systematic study on 3 SUPERB classification tasks, evaluating 8 SFT variants across 9 pretrained checkpoints from wav2vec~2.0, HuBERT, and WavLM, with multi-seed repetitions on representative base-scale models. We find that the identity of the statistically indistinguishable top-group SFT recipe is often checkpoint-dependent, with limited transferability across pretrained instances. These findings suggest that many reported downstream gains reflect instance and seed dependent elicitation match, rather than universally improving the attainable performance ceiling.

Wangjin Zhou, Yizhou Zhang, Yichi Wang +1

Graduate School of Informatics, Kyoto University, Kyoto, Japan

Supervised Fine-Tuning Fine-Tuning Speech Foundation Models Self-Supervised Speech Representation Learning

Jul 14, 2026

Self-Supervised Visual Representation Learning: Pretrain-Finetuning or Joint Training?

Self-supervision is a powerful technique for learning visual representations from unlabeled data. Existing techniques primarily adopt a two-stage approach for self-supervised learning (SSL): a pretraining stage on unlabeled data followed by a finetuning stage on labeled data. While this pipeline has demonstrated extreme effectiveness, the interaction between self-supervised and supervised learning objectives remains insufficiently understood. In this work, we systematically investigate whether jointly optimizing the self-supervised and supervised objectives during training provides a better alternative. We compare two training paradigms: (1) the aforementioned pretraining followed by finetuning (PFT) and (2) joint training (JT), where self-supervised and supervised losses are optimized simultaneously in the same network. Across eight representative SSL methods and diverse computer vision tasks on natural, medical, crisis response, and remote sensing data, we evaluate performance under varying percentages of labeled data. Our results reveal that the relative effectiveness of PFT and JT depends strongly on the task at hand, the availability of labeled data, and the complexity of the domain. We find that JT consistently improves data and training efficiency while being robust in low-label settings, while PFT is more reliable in more specialized domains. We further analyze representation quality, robustness, and cross-domain generalization, providing new insights into how self-supervised and supervised objectives interact during optimization. We establish a comprehensive empirical benchmark for hybrid SSL-based semi-supervised learning and offer practical guidance for selecting appropriate training strategies across diverse vision applications.

Nusrat Munia, Tyler Ward, Nishat Nayla +2

Department of Computer Science University of Kentucky Lexington, KY 40506, USA · Kentucky Geological Survey University of Kentucky Lexington, KY 40506, USA

Supervised Fine-Tuning Semi-Supervised Learning Self-Supervised Visual Representation Learning

Jul 8, 2026

Online Data Selection Is Implicit Alignment

Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning. This separation is incomplete: when examples are scored and kept online during fine-tuning, the choice of which data to train on already changes the model's behavioral preferences. We study online data selection as an implicit alignment mechanism. Given the same base model, optimizer, and selected-token budget, we compare random, loss-based, quality-based, and diversity-based online selectors and measure the behavioral drift they induce without any preference optimization. The proposed evaluation tracks helpfulness, refusal rate, verbosity, truthfulness, sycophancy, calibration, and jailbreak robustness, together with diagnostics for which behavioral modes are over-represented in the selected data. We formalize online selection as a reweighted SFT objective whose weights define an implicit preference over response styles and safety postures, so that an online scorer plays the role usually assigned to a reward model. This view predicts that high-scoring data can systematically favor longer, more assertive, more compliant, or more refusal-prone behaviors depending on how the online score is defined. Empirically, selectors that are statistically indistinguishable in task accuracy diverge sharply in refusal rate, verbosity, and sycophancy, and we show that the direction of the shift is predictable from the attribute mixture of the selected data. We introduce Alignment Drift Auditing (ADA), a controlled protocol for quantifying selection-induced behavioral movement, and Alignment-Aware Selection (AAS), a diagnostic online selector that retains data efficiency while constraining drift along safety and style axes.

Aoxiong Zeng, Yuxin Yang, Xiangquan Yang

East China Normal University · Shanghai University

Supervised Fine-Tuning LLM Alignment LLM Auditing Instruction-Tuning Data Selection Training Data Selection Selective Fine-Tuning

Jul 6, 2026

LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure

Supervised fine-tuning (SFT) is the standard approach for adapting pretrained language models to downstream domains, yet it often improves target-domain behavior at the cost of degrading pre-existing capabilities. Standard cross-entropy fine-tuning promotes only the observed label token and leaves unconstrained how probability mass is redistributed over other plausible alternatives, potentially distorting the rich local preference structure learned during pretraining. We first analyze next-token predictions using Shannon and Renyi entropies, revealing that pretrained models exhibit a regular multimodal entropy structure. These entropy peaks correspond to varying numbers of plausible alternatives, indicating that the base model intrinsically encodes rich distributional knowledge beyond the single supervised token. Motivated by this observation, we propose LP-SFT, a Local-Preserving Supervised Fine-Tuning objective designed to explicitly protect this inherent entropy structure. At each step, LP-SFT constructs an adaptive support of alternative tokens and applies a locally normalized preservation loss to maintain the base model's relative structure among them, while standard cross-entropy independently optimizes the supervised token. Across mixed-domain and single-domain fine-tuning experiments, LP-SFT improves overall performance over vanilla SFT and recent SFT-enhancement baselines, achieving the best balance between pass@1 accuracy and pass@k performance. These results suggest that local preservation helps mitigate capability degradation without collapsing sampling-accessible diversity.

Yueyang Wang, Baolong Bi, Shuo Lu +1

School of Mathematical Sciences, Peking University · Institute of Computing Technology, Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences +1

Supervised Fine-Tuning Fine-Tuning LLM Fine-Tuning

Jul 6, 2026

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training

For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on. Pure behavioral cloning uses full teacher demonstrations, creating a mismatch between teacher-induced contexts seen in training and student-induced contexts encountered at test time. Recent work addresses this mismatch by querying a teacher at contexts reached by the student, often with increasingly elaborate filtering of the teacher's continuations. We instead frame on-policy data construction as a budget-allocation problem: under matched supervision resources, should teacher output be spent on more start-to-finish demos, longer continuations, outcome filtering, or broader coverage of learner-induced contexts? We formalize this design space through the rollout policy, switch-time distribution, continuation horizon, filtering rules, and two complementary costs: teacher inference generated before filtering and teacher supervision retained for SFT. Across HotpotQA, ALFWorld, and Terminal-Bench-Dev, bounded unfiltered teacher continuations at learner-induced contexts improve over pure behavioral cloning at matched budgets. On HotpotQA and ALFWorld, where we run the full comparison, few-step continuations match or exceed success-filtered and critical-context-filtered alternatives. Our findings suggest that a few teacher steps, placed at learner-induced contexts, can be a more cost-efficient supervision allocation than longer or more heavily curated teacher completions.

Junze Ye, Jiayi Cheng, Miao Lu +3

Stanford University · New York University

Supervised Fine-Tuning Data Augmentation LLM Agent Training LLM Post-Training

Jul 5, 2026

NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation

Recent agentic approaches to LLM-based kernel generation have achieved impressive results on CUDA. For emerging AI accelerators such as AWS Trainium and Inferentia, automated kernel generation and optimization remain largely unaddressed. Writing kernels for these chips via the Neuron Kernel Interface (NKI) is particularly challenging: developers must navigate a multi-engine architecture, tile-based programming, and explicit data movement across multi-level memory hierarchy. Moreover, no publicly-available training data, benchmarks, or tool-augmented agents exist for this domain. We introduce NKI-Agent, the first system combining domain-specific supervised fine-tuning (SFT) with a compile-verify-fix agent loop for NKI kernel generation. We adapt the existing CUDA-Agent framework to Neuron hardware, curate 6,000 NKI kernel generation tasks for training, and construct NKIBench, a 250-task benchmark across three difficulty levels. Evaluated on real Trn1 hardware, NKI-Agent with Claude Opus 4.8 and a rank-aware system prompt achieves a 77.3% pass rate on the 150-task NKIBench. We show that tool use is critical: Opus 4.8 scores 6% in single-shot mode without agent tools. On a 60-task subset, we show that an SFT-trained Qwen3-Coder-30B-A3B achieves 25.0% pass rate at 1/100th the cost, outperforming Claude Sonnet 4 (15.0%). We also report that Group Relative Policy Optimization (GRPO) with binary compilation reward fails to improve over SFT, providing guidance on reward design for RL-based kernel generation.

Junjie Tang, Jun Huan, Hao Zhou +2

Amazon Web Services

Supervised Fine-Tuning AI Coding Agents

Jun 29, 2026

Defending Against Harmful Supervision Hidden in Benign Samples

Existing defenses are effective when harmful content is explicitly mixed into downstream fine-tuning data, but crafted samples can instead hide harmful supervision inside benign tasks. We propose Embedded Attack, where harmful QA pairs are embedded within benign training samples, and show that representative guardrails often fail to detect them at the example level. To address this, we propose Dual-Reference SFT (DR-SFT), which adapts DPO-style contrastive objective design to SFT through token-level regularization, mitigating harmful fine-tuning beyond coarse data filtering.

Bang An, Yibo Yang, Dandan Guo +3

1King Abdullah University of Science and Technology · School of Artificial Intelligence, Jilin University

Supervised Fine-Tuning Fine-Tuning Data Contamination in Language Models LLM Safety

Jun 28, 2026

Do We Still Need Fine Tuning? Turkish Sentiment Analysis in the Era of Large Language Model

This study examines whether supervised fine-tuning remains necessary for Turkish sentiment analysis in the era of large language models. We compare classical machine learning methods, fine-tuned pretrained language models, and prompted large language models on a Turkish e-commerce review dataset with negative, neutral, and positive labels. Fine-tuned BERTurk models perform best overall and outperform all prompted large language models in the full three-class task. The neutral class emerges as the main difficulty: while several large language models are much more competitive in binary positive--negative classification, they degrade substantially in the three-class setting by collapsing neutral reviews into polarized categories. The findings suggest that, in realistic Turkish sentiment classification, prompted large language models do not yet match supervised fine-tuning in the zero-shot setting, and that including the neutral class is crucial for robust evaluation.

Sercan Karakaş, Yusuf Şimşek

University of Chicago · Fırat University

Supervised Fine-Tuning LLM Evaluation Zero-Shot Text Classification Sentiment Analysis

Jun 27, 2026

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture? Large Language Models (LLMs) integrated into evolutionary search have recently produced state-of-the-art solutions on optimization tasks, including open mathematical conjectures, GPU kernel design, scientific law discovery, and combinatorial puzzles. To achieve this, prior work applied search scaffolds to one target task at a time, so every new problem is approached from scratch and the experience accumulated during search is discarded once the model finishes its attempt. This leaves the capability of iteratively evolving a solution (e.g., knowing which part to mutate and how, deciding when to backtrack) entirely in the scaffold rather than in the model itself. Whether the model itself could acquire this capability and reuse it across different tasks has been largely unexamined. To address this, we introduce Evolution Fine-Tuning (EFT), a mid-training paradigm that teaches LLMs to evolve solutions across tasks by converting evolutionary search trajectories into supervision. We construct Finch Collection, a 156K-trajectory dataset spanning 10 domains and 371 optimization tasks, and fine-tune open-source LLMs from 2B to 9B parameters. Empirically, EFT confers cross-task generalization: across 22 held-out tasks, our models surpass their base counterparts by 10.22% on average. Furthermore, when paired with test-time RL, our model matches state-of-the-art performance on two circle-packing tasks and outperforms its base-model counterpart on the Erdős minimum-overlap problem. EFT thus serves as a "practice phase" for general-purpose discovery agents that do not solve new problems from scratch.

Young-Jun Lee, Seungone Kim, Minki Kang +5

University of Minnesota · Carnegie Mellon University · KAIST +3

Supervised Fine-Tuning Evolutionary Optimization LLM Fine-Tuning Large Language Model-Guided Optimization Learning to Optimize Large Language Model-Guided Scientific Discovery

Jun 26, 2026

TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment

Fine-Tuning-as-a-Service (FTaaS) platforms let users perform supervised fine-tuning (SFT) on customized data, but this pipeline can erode model safety alignment. To recover safety without re-running full alignment, existing realignment methods focus on calibrating the integration of safety patches into fine-tuned models. These methods exhibit a persistent safety-utility trade-off: weak repair leaves harmful behavior intact, while stronger repair increasingly damages the benign task. This paper shifts the focus from online calibration to offline patch learning and aims to learn a safety patch that restores safety while preserving task-specific capabilities. To this end, we propose TRACE, which simulates harmful SFT trajectories to produce progressively corrupted model states, and optimizes a safety patch simultaneously across these states. TRACE trains the safety patch during the offline stage, and reuses it across all user checkpoints without per-user calibration. We evaluate two representative models using three harmful SFT datasets, together with three utility benchmarks. Across six benchmarks and two models, TRACE consistently dominates the safety-utility frontier. TRACE improves the safety rate by up to 77 percentage points over the best baselines, while maintaining comparable utility to the undefended fine-tuned model.

Changyue Li, Jiaming He, Youliang Yuan +4

The Chinese University of Hong Kong, Shenzhen · Ant Group · Lero the Research Ireland Centre for Software, University of Limerick

Supervised Fine-Tuning LLM Safety Alignment LLM Safety LLM Post-Training

Jun 25, 2026

NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization. This work presents NebulaExp, a fully transparent, ablation-driven post-training pipeline built on Qwen3-8B-base, covering two orthogonal model branches: general instruct model and complex reasoning-specialized model. We curate a raw corpus of 3.84M multi-source SFT samples and a 200K verifiable RL candidate pool, and design an end-to-end data processing stack including response distillation, multi-dimensional cross-verification filtering, fine-grained difficulty grading, task classification and diversity-aware sampling. For the Instruct branch, our three-stage optimized supervised fine-tuning approach NebulaExp-Ins-SFT improves the average benchmark score from the 55.01 baseline of Qwen3-8B-nothink to 60.99. GRPO reinforcement learning then further elevates the average score to 61.85. For the Reasoning branch, medium-difficulty GRPO RL improves average reasoning score from 73.88 to 75.17. To address RL's dependency on task verifiers, we systematically investigate single-teacher and multi-teacher OPD (MOPD): utilizing merely 4K instruction-following samples and outperforms RL baseline by 3.26 points on IFEval with +4.43 average overall gain; MOPD fuses four domain-specialist teachers with merely 10K samples, lifting average performance by 4.18 over the base model. This report provides a fully reproducible empirical post-training recipe for 8B-scale LLMs, and comprehensively dissects the capability trade-offs among instruction adherence, mathematical reasoning, code generation and general knowledge.

Qiaobo Hao, Yangqian Wu, Shunyi Wang +5

ZTE NebulaL0 Post-Training Team

Supervised Fine-Tuning RL for Language Models LLM Alignment On-Policy Distillation LLM Post-Training