Image de couverture de livre

A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nayak, Nihal V., Rodriguez-Diaz, Paula, Hulkund, Neha, Beery, Sara, Alvarez-Melis, David
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
par: Dang, Quy-Anh, et autres
Publié: (2025)

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
par: Cooper, A. Feder, et autres
Publié: (2024)

What is the Right Notion of Distance between Predict-then-Optimize Tasks?
par: Rodriguez-Diaz, Paula, et autres
Publié: (2024)

Boomerang Distillation Enables Zero-Shot Model Size Interpolation
par: Kangaslahti, Sara, et autres
Publié: (2025)

MedCalc-Bench Doesn't Measure What You Think: A Benchmark Audit and the Case for Open-Book Evaluation
par: Krohn-Grimberghe, Artus
Publié: (2026)

Semantics at an Angle: When Cosine Similarity Works Until It Doesn't
par: You, Kisung
Publié: (2025)

Testing Autonomous Driving Systems -- What Really Matters and What Doesn't
par: Li, Changwen, et autres
Publié: (2025)

Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn't Matter (Much)
par: Yu, Zony, et autres
Publié: (2025)

Infinite Width Models That Work: Why Feature Learning Doesn't Matter as Much as You Think
par: Sernau, Luke
Publié: (2024)

Recurrent Off-Policy Deep Reinforcement Learning Doesn't Have to be Slow
par: Clark, Tyler, et autres
Publié: (2025)

When More Data Doesn't Help: Limits of Adaptation in Multitask Learning
par: Hanneke, Steve, et autres
Publié: (2026)

Teach AI What It Doesn't Know
par: Sean Du
Publié: (2026)

Library Learning Doesn't: The Curious Case of the Single-Use "Library"
par: Berlot-Attwell, Ian, et autres
Publié: (2024)

Privacy-preserving data release leveraging optimal transport and particle gradient descent
par: Donhauser, Konstantin, et autres
Publié: (2024)

Library Designs Revisited: What Works--What Doesn't.
par: Metz, T. John, et autres
Publié: (1987)

Explorations of the Softmax Space: Knowing When the Neural Network Doesn't Know
par: Sikar, Daniel, et autres
Publié: (2025)

When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
par: Xu, Haotian, et autres
Publié: (2025)

One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
par: He, Di, et autres
Publié: (2026)

In-Service and the School Library Media Specialist: What Works and What Doesn't.
par: Turner, Philip M.
Publié: (1988)

Understanding the Role of Functional Diversity in Weight-Ensembling with Ingredient Selection and Multidimensional Scaling
par: Rojas, Alex, et autres
Publié: (2024)

Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
par: Falahati, Ali, et autres
Publié: (2026)

Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation
par: Nayak, Nihal V., et autres
Publié: (2024)

Continuous Language Model Interpolation for Dynamic and Controllable Text Generation
par: Kangaslahti, Sara, et autres
Publié: (2024)

Why Prompt Optimization Works, and Why It Sometimes Doesn't: A Causal-Inspired Edit-Level Analysis
par: Gong, Shuzhi, et autres
Publié: (2026)

DataS^3: Dataset Subset Selection for Specialization
par: Hulkund, Neha, et autres
Publié: (2025)

Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies
par: Liu, Ming
Publié: (2026)

Strongly Isomorphic Neural Optimal Transport Across Incomparable Spaces
par: Sotiropoulou, Athina, et autres
Publié: (2024)

When Online Instruction Doesn't Measure Up: How Can You Tell, and What Should You Do?
par: Rapchak, Marcia
Publié: (2019)

What Matters in Data for DPO?
par: Pan, Yu, et autres
Publié: (2025)

Consciousness Doesn't Do That
par: Matthias Michel
Publié: (2026)

Learning What Matters: Probabilistic Task Selection via Mutual Information for Model Finetuning
par: Chanda, Prateek, et autres
Publié: (2025)

Decomposing Elements of Problem Solving: What "Math" Does RL Teach?
par: Qin, Tian, et autres
Publié: (2025)

What Really Matters in Matrix-Whitening Optimizers?
par: Frans, Kevin, et autres
Publié: (2025)

"Something Comes through or It Doesn't": Intensive Reading in Post-Qualitative Inquiry
par: Maggie MacLure
Publié: (2024)

Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
par: Koh, Seunghee, et autres
Publié: (2026)

Consensus-Driven Active Model Selection
par: Kay, Justin, et autres
Publié: (2025)

How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not
par: Verdini, Francesco, et autres
Publié: (2024)

AVEX: What Matters for Animal Vocalization Encoding
par: Miron, Marius, et autres
Publié: (2025)

What Matters in Hierarchical Search for Combinatorial Reasoning Problems?
par: Zawalski, Michał, et autres
Publié: (2024)

The Category Mistake of Cislunar Time: Why NASA Cannot Synchronize What Doesn't Exist
par: Borrill, Paul
Publié: (2026)