REVIEW 2 cited by
Summarization with Precise Length Control
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
Signed reviews
read the original abstract
Many applications of text generation such as summarization benefit from accurately controlling the text length. Existing approaches on length-controlled summarization either result in degraded performance or can only control the length approximately. In this work, we present a framework to generate summaries with precisely the specified number of tokens or sentences, while maintaining or even improving the text quality. In addition, we jointly train the models to predict the lengths, so our model can generate summaries with optimal length. We evaluate the proposed framework on the CNNDM dataset and show improved performance compared to existing methods.
Forward citations
Cited by 2 Pith papers
-
Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs
Appending visible descending countdown markers to the prompt makes off-the-shelf LLMs hit exact word or character targets far more often, with exact-match rates reaching 30 to 96 percent across four benchmarks, eleven...
-
Controlling Summarization Length Through EOS Token Weighting
Weighting the EOS token in the loss during fine-tuning reduces too-long summaries on CNN/DailyMail and fixed-length XL-sum, but not on dynamic-length XL-sum.
Discussion (0). Continue with ORCID to comment.