Cover Image

Multitask Learning Can Improve Worst-Group Outcomes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kulkarni, Atharva, Dery, Lucio, Setlur, Amrith, Raghunathan, Aditi, Talwalkar, Ameet, Neubig, Graham
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes
by: Kolawole, Steven, et al.
Published: (2024)

Exact Unlearning of Finetuning Data via Model Merging at Scale
by: Kuo, Kevin, et al.
Published: (2025)

Repetition Improves Language Model Embeddings
by: Springer, Jacob Mitchell, et al.
Published: (2024)

Lower Bounds for Public-Private Learning under Distribution Shift
by: Setlur, Amrith, et al.
Published: (2025)

UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptation
by: Shen, Junhong, et al.
Published: (2024)

The Impact of Element Ordering on LM Agent Performance
by: Chi, Wayne, et al.
Published: (2024)

Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
by: Shen, Junhong, et al.
Published: (2025)

Deep Neural Networks Tend To Extrapolate Predictably
by: Kang, Katie, et al.
Published: (2023)

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
by: Wu, Ian, et al.
Published: (2026)

On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
by: Thaker, Pratiksha, et al.
Published: (2023)

Agreement-Based Cascading for Efficient Inference
by: Kolawole, Steven, et al.
Published: (2024)

Scaling Test-Time Compute Without Verification or RL is Suboptimal
by: Setlur, Amrith, et al.
Published: (2025)

FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization
by: Feng, Shengyu, et al.
Published: (2025)

Provably tuning the ElasticNet across instances
by: Balcan, Maria-Florina, et al.
Published: (2022)

CoMind: Towards Community-Driven Agents for Machine Learning Engineering
by: Li, Sijie, et al.
Published: (2025)

Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
by: Khodak, Mikhail, et al.
Published: (2023)

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
by: Qu, Yuxiao, et al.
Published: (2026)

Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows
by: Chen, Valerie, et al.
Published: (2025)

Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning
by: Gai, Jingchu, et al.
Published: (2025)

What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?
by: Kang, Katie, et al.
Published: (2024)

Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs
by: Zhong, Ziqian, et al.
Published: (2025)

Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning
by: Springer, Jacob Mitchell, et al.
Published: (2024)

Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection
by: Li, Sijie, et al.
Published: (2026)

Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance
by: Goyal, Sachin, et al.
Published: (2024)

RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
by: Setlur, Amrith, et al.
Published: (2024)

Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
by: Setlur, Amrith, et al.
Published: (2026)

Challenges and Opportunities in Improving Worst-Group Generalization in Presence of Spurious Features
by: Joshi, Siddharth, et al.
Published: (2023)

Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
by: Johnson, Nari, et al.
Published: (2023)

Why is SAM Robust to Label Noise?
by: Baek, Christina, et al.
Published: (2024)

Understanding Optimization in Deep Learning with Central Flows
by: Cohen, Jeremy M., et al.
Published: (2024)

A Rubric-Supervised Critic from Sparse Real-World Outcomes
by: Wang, Xingyao, et al.
Published: (2026)

Weight Ensembling Improves Reasoning in Language Models
by: Dang, Xingyu, et al.
Published: (2025)

Self-Trained Verification for Training- and Test-Time Self-Improvement
by: Wu, Chen Henry, et al.
Published: (2026)

Early Data Exposure Improves Robustness to Subsequent Fine-Tuning
by: Feng, Lawrence, et al.
Published: (2026)

Understanding Finetuning for Factual Knowledge Extraction
by: Ghosal, Gaurav, et al.
Published: (2024)

ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
by: Zhong, Ziqian, et al.
Published: (2025)

Can Multitask Learning Enhance Model Explainability?
by: Najjar, Hiba, et al.
Published: (2025)

Pre-Generating Multi-Difficulty PDE Data for Few-Shot Neural PDE Solvers
by: Choudhary, Naman, et al.
Published: (2025)

Learn Hard Problems During RL with Reference Guided Fine-tuning
by: Wu, Yangzhen, et al.
Published: (2026)

Multi-label Ranking: Mining Multi-label and Label Ranking Data
by: Dery, Lihi
Published: (2021)