Supervised Fine-Tuning

Also known as SFT

Follow this topic Ask about this topic

Latest papers 211

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

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

Jun 24, 2026

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Tool use enables large language models (LLMs) to perform complex tasks, and recent agentic reinforcement learning (RL) methods show promise for enhancing model capabilities. However, RL alone often leads to instability or limited gains in tool-use tasks. In our experiments, some models exhibit catastrophic collapse, where performance abruptly drops and tool-invocation structures fail. The analysis reveals that these failures stem from unexpected probability spikes in specific control tokens, disrupting structured execution, yet the underlying tool-use capability remains intact, merely obscured by specific formats. To address this, we systematically investigate a diverse set of supervisory signals, including off-policy supervision, hint-based guidance, erroneous example supervision, and others, applied under both synchronous and interleaved training schemes. We find that interleaving supervised fine-tuning (SFT) with RL substantially improves stability, but exhibits degraded performance under format and content out-of-distribution (OOD) evaluation. We also analyze the impact of learning rates and generalization across settings. These results highlight the importance of understanding RL failures and demonstrate how diverse supervisory signals can guide exploratory learning, enabling robust training of LLMs for complex, multi-step tool-use tasks. Our Code is available at https://github.com/hypasd-art/Tool-RL-Box.

Yupu Hao, Zhuoran Jin, Huanxuan Liao +2

1The 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

Supervised Fine-Tuning LLM Reliability RL Fine-Tuning Tool Use RL for Tool Use

Jun 24, 2026

Supervised Post-training of Speech Foundation Models for Robust Adaptation in Speech Deepfake Detection

Large speech foundation models have shown strong potential for speech deepfake detection, but direct fine-tuning is limited by a mismatch between self-supervised pre-training objectives and spoof-specific artifacts. To address this, we propose a mix-frame post-training strategy to create localized spoof-oriented perturbations and use frame-level supervision to encourage the SSL model to learn local inconsistencies that are critical for robust spoof detection. On ASVspoof5, we achieve state-of-the-art EER 4.50% for a single model without data augmentation. On ASVspoof2021 LA/DF, it further achieves only 0.16% absolute EER gap between LA and DF, indicating strong and balanced robustness across distinct distortion conditions. These results show that supervised post-training provides an effective and practical way to adapt speech foundation models for robust deepfake detection.

Zihan Pan, Sailor Hardik, Jinyang Wu

Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, 138632, Singapore

Supervised Fine-Tuning Audio Deepfake Detection

Jun 18, 2026

Train, Retrieve, or Both? A Four-Arm Head-to-Head for Correct Statutory Citation on the Ontario Residential Tenancies Act

Self-represented tenants, landlords, and help-desk staff need to be pointed at the provision of law that actually governs a question, with a correct statutory citation. We study this task on the Ontario Residential Tenancies Act, 2006 (RTA) and its core regulation, asking the operator's question empirically: is fine-tuning enough, or is hybrid retrieval needed? We run a four-arm head-to-head on Qwen2.5-7B-Instruct (base zero-shot, LoRA SFT-only, RAG-only, and an SFT+RAG hybrid), scored on citation exact-match (section+subsection) over a small, human-verification-pending real eval set. The base model cannot cite the RTA and SFT-only mis-recalls sections; retrieval is essential and drives hallucination to zero by construction; and the SFT+RAG hybrid scores highest at 0.481 exact-match with zero hallucinated citations. Its edge comes from SFT making provision selection more robust to the higher-recall candidate sets that hurt zero-shot RAG. Notably, this cheap bge-small hybrid matches or beats a pipeline built on bigger, specialized retrieval models (a larger embedder and a cross-encoder reranker), and a larger/improved training set does not help either: strong statutory-citation performance here does not require specialized retrieval models or more data. The artifact zeroes hallucination and clears the lift-over-base bar but does not reach the aspirational 0.70 exact-match target. All results are on a small, human-verification-pending real eval set and are reported as preliminary.

Ali Asaria, Tony Salomone, Deep Gandhi

Transformer Lab

Supervised Fine-Tuning Retrieval-Augmented Generation Legal IR Legal QA Hybrid Retrieval

Jun 16, 2026

SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR

The standard heuristic of selecting the SFT checkpoint with the highest pass@1 for GRPO can fail when SFT compresses the rollout distribution. For binary rewards, the expected within group advantage variance is

p(1{-}p)(g{-}1)/g

; when early GRPO drives

p

below

p^*(g)

, most groups have identical rewards and provide no group relative signal. We study SFT depth ladders for Qwen2.5-Coder-3B and DeepSeek-Coder-6.7B. We test Qwen2.5-Coder-3B across five depths and three seeds, and DeepSeek-Coder-6.7B across four matched depths and three seeds. On Qwen, pre RL pass@1 rises with SFT depth, but peak GRPO pass@10 falls from

0.806

to

0.481

(3 seed mean,

n{=}20

); pre RL entropy is positively associated with the GRPO outcome (

ρ{=}{+}0.69

). On DeepSeek, pass@1 remains far above

p^*(8){=}0.083

, and GRPO outcomes compress rather than invert. A two stage diagnostic, combining pre RL entropy triage with an early GRPO entropy monitor, flags high risk checkpoints and can stop failing runs early. Simple KL to reference regularisation and label smoothing variants do not rescue the collapsed Qwen checkpoint in our setting, suggesting the failure is not a trivial GRPO hyperparameter artefact.

Siddharth Aphale, Kelly Liu

Stanford University, Stanford, CA, USA.

Supervised Fine-Tuning Group Relative Policy Optimization Reinforcement Learning with Verifiable Rewards RL Post-Training

Jun 16, 2026

Perceptual compensation for tonal context in self-supervised speech models

This study examines the extent to which the wav2vec2.0 architecture exhibits evidence of compensation for phonological context. We conducted a pseudo-replication of a perceptional compensation experiment on Mandarin Chinese tones, and compared the embedding similarities and probing classifier outputs between a purely self-supervised pre-trained model and a model fine-tuned for Mandarin ASR. No evidence of compensation was found in the embedding similarities of the purely pre-trained model. Probing classifiers showed some evidence of compensation in addition to the expected layer-wise improvements in categorization, but failed to replicate human performance on isolated test syllables. Our findings contrast with previous reports of sensitivity to phonological structure emerging through pre-training alone, and suggest that supervised objectives may be necessary to encourage the abstraction of at least some types of phonological regularities.

James Kirby, Ioana Krehan, Michele Gubian

Institute for Phonetics and Speech Processing, LMU Munich, Germany

Supervised Fine-Tuning Speech Prosody Self-Supervised Speech Representation Learning

Jun 16, 2026

DRIFT: Refining Instruction Data via On-Policy Data Attribution

Optimizing the training data distribution for Supervised Fine-Tuning (SFT) dictates the capability of Large Language Models (LLMs). While existing data curation methods excel at accelerating training under constrained budgets, they are less suited to elevating the capability upper bound. The challenge here is no longer to identify a smaller subset that preserves performance, but to refine the data distribution toward instances most capable of improving the final model. To address this problem, we explore instance-level data attribution using Influence Functions (IF). We identify that standard IF formulations struggle in this setting due to two structural limitations: a proximity gap caused by off-policy validation targets, and a severe bias towards gradient norm. We propose DRIFT (Data Refinement via On-Policy Influence Functions for Supervised Fine-Tuning). Instead of relying on external reference data, DRIFT utilizes the model's on-policy rollouts as validation targets, which empirically minimizes the parameter proximity gap and better aligns with the local neighborhood assumption of IF. It further applies signed weighting based on trajectory correctness and debiases influence scores against the gradient hacking issue, allowing a small set of validation queries to act as reliable anchors for attributing the full dataset. Experiments on 7B-parameter instruction and reasoning models show that DRIFT consistently raises the performance ceiling on both, outperforming existing data curation baselines.

Zefan Wang, Lincheng Li, Tianyu Yu +1

Tsinghua University

Supervised Fine-Tuning Training Data Curation Influence Functions Training Data Attribution

Jun 15, 2026

ProCUA-SFT Technical Report

Training computer-use agents (CUAs) -- models that interact with graphical desktops through screenshots and keyboard/mouse actions -- requires large-scale, diverse trajectory data collected in full desktop environments. The largest public resource, AgentNet (22.5K human trajectories), leads to negative transfer when used for supervised fine-tuning (SFT): continuing training UI-TARS 7B on AgentNet causes OSWorld success rate to fall from 26.3% to 8-10%. We present ProCUA-SFT, a dataset of 3.1M step-level SFT samples distilled from 93K synthetic trajectories across 2,484 application combinations. The dataset is produced by a fully automated pipeline that (i) synthesizes grounded tasks on live desktops seeded with real-world content -- 912 spreadsheets from SpreadsheetBench, approximately 10K permissively-licensed presentations from Zenodo10K, and multi-application OSWorld configs -- and (ii) verifies each task's feasibility through binary precondition checking before rollout. A single VLM (Kimi-K2.5) serves as goal generator, precondition judge, and trajectory executor, eliminating planner-actor capability gaps. Each trajectory is expanded into step-prefix samples that exactly reproduce the context layout seen at inference time. Fine-tuning UI-TARS 7B on ProCUA-SFT for one epoch yields 45.0% on OSWorld -- an 18.7 percentage-point improvement over the base model and over 35% above AgentNet-trained counterparts. A subset of ProCUA was incorporated into the training data for the Nemotron 3 Nano Omni model, contributing to its computer-use capabilities.

Jaehun Jung, Ximing Lu, Brandon Cui +11

1NVIDIA · University of Washington

Supervised Fine-Tuning Computer-Use Agents LLM Agent Trajectory Synthesis LLM Agent Training

Jun 15, 2026

How Post-Training Shapes Biological Reasoning Models

Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins. These models are built through post-training, yet how each stage shapes reasoning and generalization remains poorly understood. We study when post-training improves performance and when it induces over-specialization. Across genomics, transcriptomics, and proteins, we train and evaluate more than 100 biological reasoning models under controlled variation in backbone, continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL), measuring both in-domain (ID) and out-of-domain (OOD) performance. We find that each post-training stage reshapes generalization in a distinct way rather than contributing uniform gains. CPT improves downstream performance by aligning models with biological language. SFT consistently increases ID performance but causes OOD performance to peak early and decline as models fit the training distribution. RL, when applied to strong SFT checkpoints with aligned rewards, improves OOD performance and partially recovers generalization. These results show that biological reasoning does not improve monotonically with additional supervision or compute. Instead, performance depends on how training stages are composed. Under fixed post-training budgets, the strongest ID-OOD trade-off comes from brief SFT, larger RL allocations, and asymmetric adaptation capacity across stages.

Lukas Fesser, Hanlin Zhang, Michelle M. Li +5

Harvard University · Google DeepMind · Google Research

Neural Network Generalization Supervised Fine-Tuning RL Post-Training Language Model Post-Training

Jun 11, 2026

Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding

Automated International Classification of Diseases (ICD) coding is a core medical-coding task for billing, epidemiology, and clinical decision support. Generative large language models (LLMs) are often reported as weak medical coders, but this finding mainly comes from inference-time settings such as prompting, retrieval, reranking, or tool use, leaving the role of task-specific post-training underexplored. We present a controlled empirical study of post-training for generative ICD coding, comparing discriminative baselines with LLM coders across prompting, supervised fine-tuning, and reinforcement learning under a common protocol and metric set. To our knowledge, this is the first study to evaluate RL-based post-training for generative LLM coders in ICD coding. We further introduce PHI, a diagnostic curriculum that extends GRPO to refine missed-code cases. Our results show that prompting-only evaluation substantially underestimates the potential of LLMs for ICD coding. SFT provides the main capability jump, GRPO further improves code-set prediction beyond SFT, and PHI provides targeted gains on macro-level performance. These findings suggest that the main bottleneck is not the generative formulation alone, but how the model is adapted and optimized for full-taxonomy recall. We release our code, data splits, and checkpoints at https://github.com/AlexandreWANG915/LLM4ICD.

Ziqing Wang, Weihao Li, Shijie Chen +2

Northwestern University

Supervised Fine-Tuning Automated Medical Coding RL for Generative Models LLM Post-Training Medical LLMs

Jun 10, 2026

CODEBLOCK: Learning to Supervise Code at the Right Granularity

Supervised fine-tuning of code LLMs typically applies uniform cross-entropy loss to all response tokens, implicitly assuming that every token provides equally useful learning signals. Recent token-level selection methods challenge this assumption in natural-language SFT by supervising only high-value tokens. However, such pointwise selection can fragment the syntactic structures and program dependencies of code, leaving supervision scattered across incomplete code units. In experiments on 30K code instruction-response pairs, under the same 10% token budget, supervising complete coding blocks improves average performance by 11.7 points over prior approaches that supervise isolated tokens. Motivated by this observation, we propose CodeBlock, a structure-aware sparse supervision framework that uses complete, parser-aligned coding items as the basic units of supervision. CodeBlock constructs coding items from high-quality code instruction data, estimates their supervision utility using GCE, which is more robust to low-probability tokens, and further adjusts their supervision priority using data-flow reach and bridge signals. During training, the full response is retained as context, while loss is applied only to the selected supervision units. Experiments show that partial supervision over only about 6.9% of response tokens consistently outperforms full-token SFT across all five model settings, suggesting that effective code SFT depends not only on identifying high-value supervision, but also on allocating it at the appropriate structural granularity.

Zhijie Deng, Ling Li, Jinlong Pang +5

Hong Kong University of Science and Technology (Guangzhou) · UC Santa Cruz · Ant Group +1

Supervised Fine-Tuning Code Language Models LLM Code Generation

Jun 9, 2026

A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design

Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory. However, an observed token can be non-unique, noisy, or misaligned with the model prior. Strictly fitting toward this one-hot target may be suboptimal, especially when the pretrained model encodes a rich knowledge prior. In this work, we reinterpret SFT as target distribution design: instead of studying only the loss objective, we analyze the token-level target that the loss drives the model to match. We introduce the Q-target framework, which decomposes SFT supervision into two explicit choices: (1) how strongly to rely on the observed token, and (2) how to allocate the remaining probability mass over alternatives. This perspective unifies many existing SFT variants as implicit choices of the target distribution Q. Building on this view, we propose Target-SFT which constructs the training objective directly from the desired target distribution. This method consistently outperforms across the ten reasoning dataset-model settings evaluated, showing the effectiveness of this target-based approach. Overall, our formulation reveals a more fundamental design principle for SFT training and opens a broader search space for SFT objectives.

Tong Xie, Yuanhao Ban, Yunqi Hong +3

University of California, Los Angeles (UCLA) · Arena

Supervised Fine-Tuning Fine-Tuning LLM Fine-Tuning

Jun 9, 2026

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It

Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-context recall in hybrid linear-attention models. Across architectures including HypeNet and Jet-Nemotron, retrieval performance on Needle-In-A-Haystack (NIAH) deteriorates substantially after CoT-SFT, and the degradation becomes more severe under harder retrieval settings and longer context windows. For example, HypeNet-9B on NIAH-S2@256K decreases from

67.2\%

to

9.4\%

. We attribute this to CoT-SFT biasing attention gradients toward short-range patterns, disrupting query-key projections (

W_Q, W_K

) that are responsible for long-range routing. Motivated by this observation, we propose QK-Restore, a training-free method that restores only

W_Q

and

W_K

from the pre-SFT checkpoint while preserving all other post-SFT parameters. We further introduce a Procrustes variant to balance routing preservation and reasoning adaptation. Across architectures, QK-Restore consistently restores long-context capability at zero training cost while preserving reasoning performance; for instance, on HypeNet-5B it improves S3@256K from

65.4\%

to

76.4\%

while maintaining strong reasoning performance.

Xinyu Zhou, Boyu Zhu, Yi Xu +4

1LARK, HKUST(GZ) · 2UCL · 3Mistral AI +3

Long-Context Retrieval Supervised Fine-Tuning Linear Attention Hybrid Attention

Jun 9, 2026

Don't waste SAM

Meta AI has recently released the Segment Anything Model (SAM), which demonstrates exceptional zero-shot image segmentation performance across various tasks with remarkable accuracy. Despite its inability to provide accurate segmentation across multiple research fields, SAM still serves as a valuable starting point for supporting the segmentation pipeline process, particularly for tasks that require extensive and senior skills annotations. This study aims to evaluate the generalization of SAM and fine-tuning SAM models using three waste segmentation datasets. Although they are captured from real scenes as SAM was pretrained on, these datasets present several challenges, including occlusions, deformable objects, transparency, and objects easily confused with backgrounds. In our findings, the fine-tuned SAM-ViT-H model outperforms the state-ofthe-art Zerowaste, and TACO datasets with a significant increase of +30 in IoU, and it closely approaches performance levels of TrashCan 1.0, with only a -1.44 difference. After evaluating these popular waste datasets, it became evident that fine-tuning SAM as a foundational model is a crucial step for providing better generalization for downstream waste segmentation tasks. Therefore, SAM should not be disregarded or wasted.

Nermeen Abou Baker, Uwe Handmann

1- Ruhr West University of Applied Sciences - Dept of Computer Science Lutzowstrassse 5, 46236 Bottrop - Germany

Supervised Fine-Tuning Promptable Image Segmentation Vision Foundation Model Adaptation Semantic Segmentation

Jun 9, 2026

Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction

Supervised fine-tuning with synthetic rationale data is widely assumed to improve language model performance on clinical prediction tasks by teaching models not just what to predict but why. We test this assumption on five-year Alzheimer's disease and related dementias (ADRD) prediction from longitudinal health histories. Across a large-scale controlled experiment of 504 configurations, we find that rationale-based SFT consistently and substantially hurts prediction performance relative to label-only fine-tuning. The degradation persists across model families and data scales, and is not resolved by using a reasoning-oriented base model. Crucially, the failure is not explained by poor rationale quality: human expert annotation confirms that the generated rationales are medically accurate and faithfully grounded in patient-specific evidence, and few-shot experiments show that the same rationales improve performance when used as inference-time demonstrations rather than training targets. We identify the root cause as a structural conflict between narrative plausibility and discriminative optimization. We hope our work paves the path toward a more precise understanding of when and how rationale-based supervision helps and when it does not, guiding the responsible development of language models for high-stakes clinical prediction.

Buxin Su, Bingxuan Li, Cheng Qian +3

University of Pennsylvania · University of Illinois Urbana-Champaign · University of California, Merced

Supervised Fine-Tuning Clinical Outcome Prediction Clinical Risk Prediction

Jun 8, 2026

PriFT: Prior-Support Guided Supervised Fine-Tuning

Supervised fine-tuning (SFT) is an efficient approach for downstream task adaptation and often serves as the initialization stage for reinforcement learning (RL), but it can show weaker generalization than RL. A key limitation is its off-policy objective: SFT fits fixed demonstrations token by token, including targets poorly aligned with the model's pretrained distribution, which can lead to overfitting. A recent line of work addresses this issue by assigning larger training weights to tokens better aligned with the current model's predictive distribution, with the intuition that fitting these tokens are less distortive to the model's pretrained knowledge and representations. However, computing the token weights from the model that is currently fine-tuned entangles token weights with the optimization trajectory, inducing a self-reinforcing dynamics as the distribution rapidly departs from the pretrained model. To address this, we propose PriFT (Prior-support guided Fine-Tuning), which derives token weights from a frozen pretrained reference to obtain a stable reweighting signal unaffected by fine-tuning. This signal estimates prior support: the extent to which each target token is supported by the pretrained distribution. Across multiple existing token-reweighting rules, replacing the reweighting signal from the online model to pretrained model consistently improves performance. We introduce two instantiations: PriFT-prob uses pretrained token probability, while PriFT-mass selects tokens by cumulative probability mass under the pretrained distribution. Extensive experiments on mathematical reasoning, code generation, and medical question answering show that PriFT achieves state-of-the-art results among SFT baselines and provides a better initialization for subsequent RL training.

Ke Wang, Shuangqi Li, Mathieu Salzmann +1

EPFL, Lausanne, Switzerland

Supervised Fine-Tuning Fine-Tuning LLM Fine-Tuning

Jun 8, 2026

Stage-1 Controls the Entropy Regime, Not the Outcome

Two-stage post-training -- a Stage-1 warm-start (supervised fine-tuning, SFT, or on-policy distillation, OPD) followed by Stage-2 reinforcement learning (RL) -- is increasingly used for vision-language models (VLMs). We ask what Stage-1 actually controls in a small-data study using Qwen2.5-VL-7B with a same-modality 72B VLM teacher for OPD. First, the three warm-starts reach a narrow

53

--

54\%

band on Geometry3K internal validation, consistent with the narrow range reported by recent specialized methods; this setup provides little evidence that Stage-1 changes the in-domain endpoint. Second, a matched-recipe, early-stopped SFT improves out-of-domain MathVista by

+2.1

points, reversing the

-9.5

-point drop of an over-trained variant. The clearest difference is the entropy regime: OPD enters RL with substantially higher policy entropy than either SFT initialization, and the separation remains visible through the available trajectories. At the in-domain initialization, OPD also has higher answer diversity and pass@16 (

+2.0

to

+5.2

points over SFT), although problem-level bootstrap intervals show that the smaller contrast is uncertain. The advantage is absent after RL (endpoint pass@16 values within

1.1

points) and on MathVista (six models within

1.2

points). Our contribution is therefore a bounded empirical characterization: Stage-1 is strongly associated with the entropy regime in this setup, but the downstream payoff is small, localized, and not evidence that OPD is a better RL warm-start.

Jianxiong Shen

Supervised Fine-Tuning VLM Reasoning On-Policy Distillation RL for VLMs

Jun 7, 2026

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff

Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training. SFT is expected to provide a useful behavioral prior for RL to further enhance model capabilities. However, checkpoints with excessive SFT often show limited improvement during RL. We attribute this failure to the loss of model plasticity: the reduced ability of an SFT-initialized policy to be effectively reshaped by subsequent RL. To better understand this phenomenon, we conduct detailed analysis from multiple perspectives, including parameter changes, output spaces, and RL optimization dynamics. Our results show that models from excessive SFT tend to produce over-confident token distributions and exhibit sharp parameter landscapes, which make them harder to optimize in the RL stage. To enable a more robust SFT-to-RL handoff, we propose Rejuvenation, a simple yet effective method that restores plasticity while preserving useful SFT-acquired priors. Rejuvenation leverages base-anchored model fusion to reduce excessive SFT-induced drift with targeted neuron reset to mitigate model rigidity. Experimental results on both math reasoning tasks and agentic tasks demonstrate that our approach consistently improves RL performance on over-trained SFT models, while also enhancing generalization to out-of-distribution tasks.

Runze Liu, Jiashun Liu, Xu Wan +2

Hong Kong University of Science and Technology · Zhejiang University · State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA

Supervised Fine-Tuning RL Post-Training

Jun 5, 2026

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

Supervised fine-tuning (SFT) is a prevailing method for adapting large language models to reasoning tasks by imitating offline expert demonstrations, often treating a single expert trajectory as the target behavior. However, reasoning is not simple path imitation: rigidly following one demonstrated solution may overfit to surface forms and suppress the model's own reasoning distribution. We propose Rollout-Adaptive Supervised Fine-Tuning (RASFT), a policy-aware SFT framework that calibrates expert supervision according to problem-level solvability estimated from verified on-policy rollouts. For each problem, RASFT strengthens expert guidance when the current policy struggles, while relaxing rigid imitation and incorporating correct self-generated trajectories when the model already exhibits reliable reasoning behavior. To preserve useful reasoning priors, RASFT further introduces a clipped inverse ratio between the frozen reference model and the current policy to constrain excessive policy drift. Experiments across multiple models on six mathematical reasoning benchmarks and two code reasoning benchmarks show that RASFT achieves better overall performance than SFT, SFT variants, and representative RL methods. The code is available at https://github.com/zjd1sq/RASFT.

Yongliang Miao, Fengyuan Liu, Wei Shi +4

The Chinese University of Hong Kong, Shenzhen · Shanghai Artificial Intelligence Laboratory · New Jersey Institute of Technology +1

Supervised Fine-Tuning LLM Mathematical Reasoning LLM Reasoning

Jun 5, 2026

TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models

Targeted post-training aims to improve reasoning, math, and code without degrading strengths. Low-rank adapters are efficient but task-global; activation interventions are input-aware but often require separate probes, vectors, or inference-time steering. We introduce TALAN (Task-Aligned Latent Adaptation Networks), a sequence-conditioned latent side path inserted into a transformer's residual stream and co-trained with a low-rank adapter in one SFT loop. TALAN compresses the active sequence into latent memory, remixes it into token-level perturbations, and writes them back through a controlled residual update. It is configured along six axes: insertion location, memory size, mixer, writeback rule, trainability scope, and gradient scale. Across four Qwen3-family backbones and four STEM/code benchmarks, TALAN improves matched LoRA and DoRA baselines. With LoRA, it yields a +1.41 point cross-model mean gain, positive on all four backbones and non-negative on all 16 model-benchmark cells. With DoRA, it yields a +1.85 point mean gain, positive on all backbones and on 13 of 16 cells. Paired seed checks support positive average effects but show nontrivial variance, so we treat them as sensitivity checks. Cost is small: <1% trainable parameters relative to the backbone and 1.01-1.02x inference overhead versus matched LoRA. A Llama-3.2-1B transfer probe is also positive under LoRA and rsLoRA across seven paired seeds, supporting a transfer beyond Qwen. Internal-state analyses suggest TALAN is a small complementary activation intervention. The matched adapter update is 80-1,700x larger than the TALAN perturbation, yet their directions have near-zero cosine; per-layer measurements show this small orthogonal perturbation propagates and amplifies through depth. TALAN offers a practical platform for studying steerable activation-level adaptation within standard adapter-based post-training.

Chengkai Zhang, Ziteng Liu, Junpu Wang +4

Meta AI

Supervised Fine-Tuning Adapter Tuning Low-Rank Adaptation LLM Post-Training Activation Steering LLM Reasoning

Jun 3, 2026

Learning What to Learn: Stage-Specific Data Sets for SFT-then-RL in Small Language Model Reasoning

Post-training Small Language Models (SLMs) for reasoning typically follows an SFT-then-RL pipeline, yet existing work rarely considers what data should be learned at each stage. We argue that data strategy should be aligned with the distinct roles of SFT and RL: SFT is better suited for acquiring not-yet-mastered reasoning skills, while RL is better suited for consolidating skills that the model can already partially access. Based on this principle, we propose a difficulty-aware SFT-then-RL framework that organizes training data into stage-specific sets. For hard samples in the SFT stage, we introduce a Bridge mechanism that transforms raw teacher-generated reasoning traces into more learnable supervision for SLMs. For hard samples that remain unsolved during RL, we apply Critique Fine-Tuning by converting all-zero-reward failures into diagnostic, repair, and new reasoning trace supervision for the next SFT stage. Experiments on two SLMs across five reasoning benchmarks show that our method consistently improves over representative SFT, distillation, and RL baselines. Our results highlight the importance of coordinating data difficulty across SFT and RL for effective SLM reasoning post-training.

Chongyang He, Rui Zhang, Zixuan Wang +1

1Tsinghua University · 2National University of Singapore · 3DiDi +1

Supervised Fine-Tuning RL for Language Model Reasoning Small Language Models Curriculum Learning Language Model Post-Training

Jun 3, 2026

(Mis)generalization of Helpful-only Fine-tuning

Helpful-only models, that is, models that are trained to always follow user intent, are valuable for dangerous capability evaluations and other areas of AI R&D where refusals would be an obstacle. Little is known about the generalization properties of helpful-only training: helpful-only models refuse less than their harmless counterparts, but previous work has not studied other dimensions of their alignment. We study the shortcomings of existing helpful-only models. We find that some show emergent misalignment, others have residual refusal behaviors, and most show poor steerability, sycophancy, and incoherent character. We show that simple anti-refusal training can cause many of these issues. None of these problems are necessary consequences of helpful-only training, though: we show that synthetic document fine-tuning and adding character-related questions to SFT and RL can mitigate them.

Mohammad Omar Khursheed, Baram Sosis, Fabien Roger

Anthropic Fellows Program MATS · Anthropic

Supervised Fine-Tuning LLM Sycophancy Fine-Tuning LLM Alignment LLM Refusal Behavior

Jun 2, 2026

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training

The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT). We question this status quo by training a LLM from scratch and applying RL, SFT, and SFT followed by RL directly to intermediate pre-training checkpoints. We find that RL is effective very early, and often matches the full SFT

\to

RL pipeline early as well. Through experiments on harder problems, we find that targeted pre-training data composition is a strong lever for RL effectiveness, even more so than model scale. Beyond reasoning accuracy, applying RL directly to base checkpoints expands the model's distribution; the sharpening effect reported in recent work arises only when RL follows SFT. The general capabilities of the model remain essentially unchanged by RL, while they degrade following SFT. Finally, we merge RL and SFT objectives by parallel averaging, which outperforms across all other training methods discussed, across metrics, while preserving general capabilities. Together, these results suggest that LLM training might benefit from an expanded use of RL.

Rachit Bansal, Clara Mohri, Tian Qin +2

Harvard University

Language Model Pretraining Supervised Fine-Tuning RL for Language Models Reinforcement Learning RL Post-Training

Jun 2, 2026

A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners

Supervised fine-tuning (SFT) improves end-to-end classical planning in large language models (LLMs), but do these models also learn to represent and reason about the planning problems they are solving? Due to the relative complexity of classical planning problems and the challenge that end-to-end plan generation poses for LLMs, it has been difficult to explore this question. In our work, we devise and perform a series of interpretability experiments that holistically interrogate world model recovery by examining both internal representations and generative capabilities of fine-tuned LLMs. We find that: a) Supervised fine-tuning on valid action sequences enables LLMs to linearly encode action validity and some state predicates. b) Models that struggle to use output probabilities for classifying action validity may still learn internal representations that separate valid from invalid actions. c) Broader state space coverage during fine-tuning, such as from random walk data, yields more accurate recovery of the underlying world model. In summary, this work contributes a recipe for applying interpretability techniques to planning LLMs and generates insights that shed light on open questions about how knowledge is represented in LLMs.

Patrick Emami, Nan Qiang, Peter Graf

National Laboratory of the Rockies · Epic Systems

Supervised Fine-Tuning LLM Planning LLM Interpretability

Jun 1, 2026

BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks

Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks. Recent work has shown that this paradigm is highly vulnerable to backdoor attacks, and that existing defenses are ineffective in open-ended generation settings. In response, we propose BYORn, a backdoor-robust fine-tuning framework motivated by the observation that poisoned target responses are often semantically implausible given the corresponding image-text inputs and a pretrained model. BYORn identifies such misaligned responses and dynamically replaces them with alternative responses generated by the model, thereby breaking the correlation between triggers and target outputs. The resulting objective gradient corresponds to the gradient of the empirical estimate of the population risk upper bound over the clean data distribution. Empirically, BYORn consistently improves robustness to backdoor attacks while preserving clean-task performance, establishing a new trade-off frontier between generalization and attack success rate. Finally, we demonstrate that BYORn remains effective against adaptive attacks specifically designed to circumvent the proposed defense.

Ivan Sabolić, Marin Oršić, Josip Šarić +1

Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia.

Supervised Fine-Tuning VLM Robustness Large Vision-Language Models Backdoor Attacks on VLMs

May 31, 2026

Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning

Emergent misalignment (EM) occurs when narrow finetuning induces dangerous behavior outside the finetuning task. Detecting this shift through repeated behavioral evaluation is costly, motivating our checkpoint-level monitoring from internal representations. We define a fixed coordinate system from seven alignment-relevant activation directions and use it to track representational drift during LoRA finetuning of four open-source 7-9B language models. Finetuning drift in this space exhibits a dominant axis that explains 78.6% of variance and remains stable across datasets, extraction choices, and parameter-update capacities. Across 468 checkpoints from three EM-relevant held-out datasets, the resulting monitors attain 1.8% FNR, 2.0% FPR, and 0.989 AUROC, outperforming semantic, random, PCA, and SAE feature baselines. On a fourth dataset, a matched benign-dangerous control shows that substantial representational drift can also occur under benign finetuning, while changes across the 7D profile still distinguish dangerous from benign runs. Stress tests across two 14B models, full finetuning, longer training horizons, and misaligned starting states show that the signal can persist across shifts in training configuration, while reliable deployment may require recalibration.

Huy Nghiem, Sy-Tuyen Ho, Sarah Wiegreffe +1

University of Maryland

Supervised Fine-Tuning Emergent Misalignment in Language Models LLM Safety Alignment Emergent Misalignment Language Model Auditing

May 29, 2026

DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization

Large language models are increasingly deployed in multi-turn interactive settings where users or environments can iteratively provide lightweight feedback. Unfortunately, optimizing such behavior presents a sharp dilemma in practice: online reinforcement learning is able to effectively address multi-turn dynamics but is prohibitively expensive due to the cost of generating full correction trajectories at every update, whereas offline supervised fine-tuning (SFT) is efficient but suffers from distribution shift and behavioral collapse. To this end, we novelly propose DRIFT (Decoupled Rollouts and Importance-Weighted Fine-Tuning), a framework that operationalizes the theoretical insight that the KL-regularized RL objective is equivalent to importance-weighted supervised learning. DRIFT decouples rollout from optimization by sampling offline interaction trajectories from a fixed reference policy, deriving return-based importance weights, and optimizing the policy via weighted SFT on the resulting dataset. Empirically, we demonstrate that DRIFT matches or exceeds the performance of multi-turn reinforcement learning baselines while maintaining the training efficiency and simplicity of standard supervised fine-tuning. Code is available at https://github.com/2020-qqtcg/DRIFT.

Jian Mu, Tianyi Lin, Chengwei Qin +2

The Hong Kong University of Science and Technology (Guangzhou) · The Chinese University of Hong Kong, Shenzhen.

Supervised Fine-Tuning RL for Language Models Reinforcement Learning Offline RL RL Fine-Tuning

May 29, 2026

RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting

Domain-specific supervised fine-tuning (SFT) often improves in-domain performance at the cost of degrading a model's general capabilities. We view this degradation through two practical gaps in domain SFT: a supervision-compatibility gap, where domain targets differ in style and reasoning format from the original model's natural responses, and a trajectory-preservation gap, where teacher-forced SFT optimizes fixed target tokens without constraining the model's behavior on its own generated prefixes. This process fails to preserve the model's original behavior. We propose RAFT (Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting), a two-stage framework that addresses both factors. First, RAFT constructs model-compatible supervision through self-conditioned rewriting, semantic filtering, and answer fusion. Second, RAFT performs Answer-Conditioned On-Policy Distillation, where the original instruction-tuned model provides soft targets on student-generated trajectories while being conditioned on the fused answer as helpful context. We further introduce top-K temperature distillation and EMA-based adaptive loss balancing to stabilize the domain-general trade-off. Across three instruction-tuned backbones and five domains, RAFT improves average domain accuracy by 23.2% over standard SFT, while recovering part of the SFT-induced degradation on MS-Bench and IFEval, with relative improvements of 18.2% and 10.2%, respectively. These results show that coupling data refinement with trajectory-level preservation provides an effective recipe for domain fine-tuning with alleviated forgetting.

Yuduo Li, Xiaofeng Shi, Qian Kou +2

Beijing Academy of Artificial Intelligence (BAAI) · Beijing Jiaotong University (BJTU)

Supervised Fine-Tuning Fine-Tuning Domain Adaptation for LLMs On-Policy Distillation Catastrophic Forgetting

May 28, 2026

On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training

Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a bottleneck for end-to-end visual reasoning. To investigate this gap, we introduce a controlled diagnostic framework with two synthetic tasks that disentangle perception from reasoning. Our analysis reveals a consistent perception-reasoning asymmetry: post-training improves reasoning more substantially than perception, though the underlying mechanism differs across training paradigms. For supervised fine-tuning (SFT), this asymmetry stems from token imbalance, with perception occupying a smaller fraction of tokens in chain-of-thought supervision. Reweighting the loss boosts end-to-end performance by up to 18.2 points. For reinforcement learning (RL), the asymmetry instead arises from reward coupling, as outcome rewards correlate more strongly with reasoning than perception. Adding a perception-aware reward improves end-to-end accuracy by up to 6.0 points; when ground-truth perception rewards are unavailable, a reliable surrogate provides useful signal, yielding gains of 2.2 points. Beyond the controlled setting, these strategies also improve real-world visual reasoning, with gains of up to 3.3 points across three benchmarks. Overall, we diagnose the causes of asymmetric optimization and provide actionable guidance that benefits both synthetic and realistic settings.

Xueqing Wu, Yu-Chi Lin, Kai-Wei Chang +1

University of California, Los Angeles

Supervised Fine-Tuning Vision-Language Models VLM Reasoning RL for VLMs