EPIC trains LLMs to treat continuous embeddings as in-context prompts, yielding state-of-the-art text embedding performance on MTEB with or without prompts at inference and lower compute.
ELI 5: Long Form Question Answering
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PUPPET jointly optimizes LLM outputs for high detectability and task performance via RL rewards from a detector and a task evaluator, outperforming watermarking on tasks while matching detectability.
citing papers explorer
-
Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders
EPIC trains LLMs to treat continuous embeddings as in-context prompts, yielding state-of-the-art text embedding performance on MTEB with or without prompts at inference and lower compute.
-
LLM Output Detectability and Task Performance Can be Jointly Optimized
PUPPET jointly optimizes LLM outputs for high detectability and task performance via RL rewards from a detector and a task evaluator, outperforming watermarking on tasks while matching detectability.