paper-with-me

Papers

Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension

2021-09-14 · EMNLP 2021 11 · Naoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian, Kentaro Inui

How can we generate concise explanations for multi-hop Reading Comprehension (RC)? The current strategies of identifying supporting sentences can be seen as an extractive question-focused summarization of the input text. However, these extractive explanations are not necessarily concise i.e. not minimally sufficient for answering a question. Instead, we advocate for an abstractive approach, where we propose to generate a question-focused, abstractive summary of input paragraphs and then feed it to an RC system. Given a limited amount of human-annotated abstractive explanations, we train the abstractive explainer in a semi-supervised manner, where we start from the supervised model and then train it further through trial and error maximizing a conciseness-promoted reward function. Our experiments demonstrate that the proposed abstractive explainer can generate more compact explanations than an extractive explainer with limited supervision (only 2k instances) while maintaining sufficiency.

📄 PDF Abstract BibTeX arXiv:2109.06853

Code (1)

stonybrooknlp/suqa 공식 구현 pytorch

Tasks

2kMulti-Hop Reading ComprehensionReading Comprehension

Similar Papers 제목 키워드 기반

DIFFQG: Generating Questions to Summarize Factual Changes

2023-03-01 · Jeremy R. Cole, Palak Jain, Julian Martin Eisenschlos, Michael J. Q. Zhang 외

Identifying the difference between two versions of the same article is useful to update knowledge bases and to understand how articles evolve. Paired texts occur naturally in diverse situations: reporters write similar n…

ArticlesChange DetectionQuestion GenerationQuestion-Generation

Long-form Question Answering: An Iterative Planning-Retrieval-Generation Approach

2023-11-15 · Pritom Saha Akash, Kashob Kumar Roy, Lucian Popa, Kevin Chen-Chuan Chang

Long-form question answering (LFQA) poses a challenge as it involves generating detailed answers in the form of paragraphs, which go beyond simple yes/no responses or short factual answers. While existing QA models excel…

FormLong Form Question AnsweringQuestion AnsweringRetrieval

The Sufficiency-Conciseness Trade-off in LLM Self-Explanation from an Information Bottleneck Perspective

2026-02-15 · Ali Zahedzadeh, Behnam Bahrak arxiv

Large Language Models increasingly rely on self-explanations, such as chain of thought reasoning, to improve performance on multi step question answering. While these explanations enhance accuracy, they are often verbose…

Question Answering

Concise Answers to Complex Questions: Summarization of Long-form Answers

2023-05-30 · Abhilash Potluri, Fangyuan Xu, Eunsol Choi

Long-form question answering systems provide rich information by presenting paragraph-level answers, often containing optional background or auxiliary information. While such comprehensive answers are helpful, not all in…

Extractive SummarizationFormLong Form Question AnsweringQuestion Answering

Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering

2025-09-18 · Yangyi Li, Mengdi Huai arxiv

Large language models (LLMs) have shown strong capabilities, enabling concise, context-aware answers in question answering (QA) tasks. The lack of transparency in complex LLMs has inspired extensive research aimed at dev…

Question Answering