Longformer-En Efficiency-Accuracy Trade-offs Across Domain-Specific Long-Context Tasks

This report synthesises findings from 12 peer-reviewed papers addressing the following research question: How does the efficiency-accuracy trade-off in Longformer-En vary when fine-tuned on domain-specific long-context tasks (e.g., legal documents, scientific papers) compared to the general HotpotQA. Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks, since the release of ChatGPT in November 2022. LLMs' ability of general-purpose language understanding and generation is acquired by training. 10 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the efficiency-accuracy trade-off in Longformer-En vary when fine-tuned on domain-specific long-context tasks (e.g., legal documents, scientific papers) compared to the general HotpotQA benchmark?

Autonomous literature synthesis. Automated review score: 8.2/10. Full text and citation available at Assignee Research.