technique

Multi-Task Learning

techniqueactiveprovisionalmulti-task-learning-1d051c9a·1 events·first seen 22d ago

Aliases: Multi-Task Learning

Co-occurring entities

MGDA LLM-as-a-Judge Spearman's rho PCGrad Textual Gradient Optimization

More like this (12)

Multimodal Learning In-Context Multiple Instance Learning Multiple Instance Learning (MIL)Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning meta-learning multimodal pretraining instruction-based multitask pretraining Operator Learning Multi-head Latent Attention (MLA)Multimodal Continual Instruction Tuning Multimodal Large Language Models Latent World Recovery for Multimodal Learning with Missing Modalities

Recent events (1)

5arXiv · cs.CL·22d ago·source ↗

Failure Modes of Multi-Objective Prompt Optimization for LLM Judges

This paper investigates multi-objective prompt optimization for LLM-as-judge systems, testing five decomposition modes of textual gradient optimizers across varying levels of cross-task information sharing. In 6 of 10 configurations, optimization fails to improve over the initial prompt, with gradient specificity dropping 59% when multiple criteria are processed jointly. The authors identify two separable failure modes: gradient dilution at optimization time and instruction interference at inference time. These findings constrain the design space for customizing LLM judges via textual feedback across multiple evaluation criteria simultaneously.

Evaluation and Benchmarking Agent and Tool Ecosystem MGDA Multi-Task Learning LLM-as-a-Judge +4 more