QASE Enhanced PLMs: Improved Control in Text Generation for MRC

Lin Ai, Zheng Hui, Zizhou Liu, Julia Hirschberg
2/26/2024
cs.CL

No confident code implementation found for this paper.

Abstract

To address the challenges of out-of-control generation in generative models for machine reading comprehension (MRC), we introduce the Question-Attended Span Extraction (QASE) module. Integrated during the fine-tuning of pre-trained generative language models (PLMs), QASE enables these PLMs to match SOTA extractive methods and outperform leading LLMs like GPT-4 in MRC tasks, without significant increases in computational costs.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Enhancing Pre-Trained Generative Language Models with Question Attended Span Extraction on Machine Reading Comprehension

93% match1 repo42024

PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metrics

79% match2024

GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs

79% match2024

MRCEval: A Comprehensive, Challenging and Accessible Machine Reading Comprehension Benchmark

79% match1 repo42025

From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation

78% match2024

Exploring the Limits of Model Compression in LLMs: A Knowledge Distillation Study on QA Tasks

78% match2025

Cite this paper

@article{ai2024qase,
  title  = {QASE Enhanced PLMs: Improved Control in Text Generation for MRC},
  author = {Lin Ai and Zheng Hui and Zizhou Liu and Julia Hirschberg},
  year   = {2024},
  eprint = {2403.04771},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.04771v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.04771.svg)](https://codeofpaper.com/paper/2403.04771)

Discussion