Pith. sign in

REVIEW 3 cited by

LenAtten: An Effective Length Controlling Unit For Text Summarization

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2106.00316 v1 pith:LEQHC6RF submitted 2021-06-01 cs.CL

Zhongyi Yu , Zhenghao Wu , Hao Zheng , Zhe XuanYuan , Jefferson Fong , Weifeng Su This is my paper · ORCID
classification cs.CL
keywords lengthcontrollabilitylenattenunitcontrollingeffectivegeneratingsummarization
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Fixed length summarization aims at generating summaries with a preset number of words or characters. Most recent researches incorporate length information with word embeddings as the input to the recurrent decoding unit, causing a compromise between length controllability and summary quality. In this work, we present an effective length controlling unit Length Attention (LenAtten) to break this trade-off. Experimental results show that LenAtten not only brings improvements in length controllability and ROGUE scores but also has great generalization ability. In the task of generating a summary with the target length, our model is 732 times better than the best-performing length controllable summarizer in length controllability on the CNN/Daily Mail dataset.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Precise Length Control in Large Language Models

    cs.CL 2024-12 conditional novelty 6.0 of 10

    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.

  2. Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs

    cs.CL 2025-08 conditional novelty 5.0 of 10

    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...

  3. Controlling Summarization Length Through EOS Token Weighting

    cs.CL 2025-06 conditional novelty 5.0 of 10

    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.

Pith tools