Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations
cs.CL
Submitted: 2026-10-01
Updated: 2026-10-01
Code: https://github.com/Jungwona/Awesome-Task-Adaptation-for-Large-Language-Models
Terminology
Sources
- GPT-4 Technical Report
- EvoSkill: Automated Skill Discovery for Multi-Agent Systems
- Program Synthesis with Large Language Models
- LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
- LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters
- MathArena: Evaluating LLMs on Uncontaminated Math Competitions
- Doc-to-LoRA: Learning to Instantly Internalize Contexts
- Evaluating Large Language Models Trained on Code
- DialogSum: A Real-Life Scenario Dialogue Summarization Dataset
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Hate Speech Dataset from a White Supremacy Forum
- KronA: Parameter Efficient Tuning with Kronecker Adapter
- Cartridges: Lightweight and general-purpose long context representations via self-study
- Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models
- PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra
- Parameter-Efficient Fine-Tuning with Discrete Fourier Transform
- RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
- FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering