REVIEW 2 cited by
Latent Prompt Tuning for Text Summarization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Prompts with different control signals (e.g., length, keywords, etc.) can be used to control text summarization. When control signals are available, they can control the properties of generated summaries and potentially improve summarization quality (since more information are given). Unfortunately, control signals are not already available during inference time. In this paper, we propose Lotus (shorthand for Latent Prompt Tuning for Summarization), which is a single model that can be applied in both controlled and uncontrolled (without control signals) modes. During training, Lotus learns latent prompt representations from prompts with gold control signals using a contrastive learning objective. Experiments show Lotus in uncontrolled mode consistently improves upon strong (uncontrollable) summarization models across four different summarization datasets. We also demonstrate generated summaries can be controlled using prompts with user specified control tokens.
Forward citations
Cited by 2 Pith papers
-
Hansel: Output Length Controlling Framework for Large Language Models
Periodic hidden special tokens that count remaining words during finetuning give LLMs accurate and extrapolatable output length control without hurting output quality.
-
Precise Length Control in Large Language Models
Adding a reversed, scaled sinusoidal positional encoding to a fine-tuned decoder-only LLM lets it end responses within about three tokens of a requested length.
Discussion (0). Continue with ORCID to comment.