ACL survey unifies weight-, prompt-, and embedding-based LLM task adaptation in one taxonomy
kalyan_kpl · x · 2026-11-09
A survey published at AACL/IJCNLP 2026 (short paper, pp.600-631) by Jungwon Park, Changin Choi, Jimyeong Kim, Nojun Kwak, and Wonjong Rhee systematizes efficient task adaptation in LLMs. It proposes a unified framework categorizing methods by where task information is encoded — model weights (parameter-efficient fine-tuning), input prompts (in-context learning), or injected task embeddings (an emerging paradigm) — provides a comprehensive taxonomy integrating the three paradigms, analyzes their strengths, limitations, and cross-paradigm relationships, and highlights open problems for future research.
More from Research
- Perplexity Frontier Research agenda: multi-agent orchestration, continual learning, next-gen architectures — andrewgwils · 2026-11-09
- Perplexity Frontier Research commits to open papers, code, and real-product testing — andrewgwils · 2026-11-09
- Perplexity launches Frontier Research group to openly advance models, data, and algorithms — andrewgwils · 2026-11-09
- Formulate a problem as alternating convex optimization and solvers follow naturally — caglar_ee · 2026-11-09
- GitHub study: engineer productivity rises 2.8% per 10% growth of local tech cluster — lemire · 2026-11-09
- 5 PEFT techniques explained: what LoRA, VeRA, Delta-LoRA actually do to model weights — techNmak · 2026-11-09