pith. sign in

Context rot: How increasing input tokens impacts llm performance

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference

cs.CL · 2025-10-17 · unverdicted · novelty 5.0

POPI distills user preferences into reusable natural-language summaries via a shared inference model and conditions a generator on them, trained jointly with RL to improve personalization quality while cutting context length by up to 10x on benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • POPI: Personalizing LLMs via Optimized Natural Language Preference Inference cs.CL · 2025-10-17 · unverdicted · none · ref 20

    POPI distills user preferences into reusable natural-language summaries via a shared inference model and conditions a generator on them, trained jointly with RL to improve personalization quality while cutting context length by up to 10x on benchmarks.