Lei Xu, Aparna Elangovan, Saket Dingliwal, Mohammed Karim
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large language models (LLMs) can generate fluent summaries across domains using prompting techniques, reducing the need to train models for summarization applications. However, crafting effective prompts that guide LLMs to generate summaries with the appropriate level of detail and writing style remains a challenge. In this paper, we explore the use of salient information extracted from the source document to enhance summarization prompts. We show that adding keyphrases in prompts can improve ROUGE F1 and recall, making the generated summaries more similar to the reference and more complete. The number of keyphrases can control the precision-recall trade-off. Furthermore, our analysis reveals that incorporating phrase-level salient information is superior to word-or sentence-level. However, the impact on hallucination is not universally positive across LLMs. To conduct this analysis, we introduce Keyphrase Signal Extractor (SigExt), a lightweight model that can be finetuned to extract salient keyphrases. By using SigExt, we achieve consistent ROUGE improvements across datasets and open-weight and proprietary LLMs without any LLM customization. Our findings provide insights into leveraging salient information in building prompt-based summarization systems.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.02741")
get_code_for_paper("2410.02741")
have("2410.02741")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2410.02741.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2410.02741)
Connect an agent — have() is free.