Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmark
We benchmark three supervised fine-tuned models against frontier zero-shot baselines on a 661-row held-out slice of PiSAR (Persona, intent, Screen, Action, Rationale), a 12,929-tuple corpus of screen-anchored behavioural rationales curated from public app-store reviews, Pew American Trends Panel demographics, and the OPeRA shopper traces. Every model, frontier or fine-tuned, is evaluated on the same 661-row slice with the same scoring pipeline. Two findings. First, frontier zero-shot baselines (Claude Opus 4.7 and GPT-5.5) reach sem_sim 0.459 and 0.482 respectively; a fine-tuned Qwen3-VL-8B-Instruct reaches 0.783 and clears sem_sim >= 0.7 on 79% of rows, against 1-2% for either frontier baseline, a gap of 0.30 absolute on the same test set. Second, the same training data and recipe on Gemma-4-26B-A4B-IT scores only 0.441, in the same band as the frontier zero-shot baselines rather than the fine-tuned Qwen. We read this as a recipe-vs-model mismatch: the reasoning-tuned high-parameter model resists displacement and would likely need either more data or a stronger fine-tuning method.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel Data
Text detoxification, a variant of style transfer tasks, finds useful applications in online social media. This work presents a fine-tuning method that only uses non-parallel data to turn large language models (LLM) into …
Style TransferRegCLR: A Self-Supervised Framework for Tabular Representation Learning in the Wild
Recent advances in self-supervised learning (SSL) using large models to learn visual representations from natural images are rapidly closing the gap between the results produced by fully supervised learning and those pro…
Representation LearningSelf-Supervised LearningTable RecognitionIdentifying Misinformation from Website Screenshots
Can the look and the feel of a website give information about the trustworthiness of an article? In this paper, we propose to use a promising, yet neglected aspect in detecting the misinformativeness: the overall look of…
Articlesimage-classificationImage ClassificationMisinformation+2Rotation-Preserving Supervised Fine-Tuning
Supervised fine-tuning (SFT) improves in-domain performance but can degrade out-of-domain (OOD) generalization. Prior work suggests that this degradation is related to changes in dominant singular subspaces of pretrained…
TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins
Fine-tuning large language models (LLMs) is compute-intensive and error-prone: model performance depends sensitively on data quality and hyperparameter choices, and naïve runs can even degrade model performance. This rai…