paper-with-me

Papers

What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering

2019-09-19 · IJCNLP 2019 11 · Tushar Khot, Ashish Sabharwal, Peter Clark

Multi-hop textual question answering requires combining information from multiple sentences. We focus on a natural setting where, unlike typical reading comprehension, only partial information is provided with each question. The model must retrieve and use additional knowledge to correctly answer the question. To tackle this challenge, we develop a novel approach that explicitly identifies the knowledge gap between a key span in the provided knowledge and the answer choices. The model, GapQA, learns to fill this gap by determining the relationship between the span and an answer choice, based on retrieved knowledge targeting this gap. We propose jointly training a model to simultaneously fill this knowledge gap and compose it with the provided partial knowledge. On the OpenBookQA dataset, given partial knowledge, explicitly identifying what's missing substantially outperforms previous approaches.

📄 PDF Abstract BibTeX arXiv:1909.09253

Code (1)

allenai/missing-fact 공식 구현 pytorch

Tasks

Multi-hop Question AnsweringQuestion AnsweringReading Comprehension

Similar Papers 제목 키워드 기반

Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge

2021-04-14 · NAACL 2021 4 · Bodhisattwa Prasad Majumder, Sudha Rao, Michel Galley, Julian McAuley

The ability to generate clarification questions i.e., questions that identify useful missing information in a given context, is important in reducing ambiguity. Humans use previous experience with similar contexts to for…

Question GenerationQuestion-Generation

LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation

2024-04-22 · Keheng Wang, Feiyu Duan, Peiguang Li, Sirui Wang 외

Retrieval-Augmented Generation (RAG) demonstrates great value in alleviating outdated knowledge or hallucination by supplying LLMs with updated and relevant knowledge. However, there are still several difficulties for RA…

HallucinationRAGRe-RankingRetrieval+2

What is Normal, What is Strange, and What is Missing in a Knowledge Graph: Unified Characterization via Inductive Summarization

2020-03-23 · Caleb Belth, Xinyi Zheng, Jilles Vreeken, Danai Koutra

Knowledge graphs (KGs) store highly heterogeneous information about the world in the structure of a graph, and are useful for tasks such as question answering and reasoning. However, they often contain errors and are mis…

Knowledge GraphsQuestion Answering

Question-Guided Evidence Acquisition for Multimodal Visual Question Answering

2026-08-20 · Alin-Ionut Popa arxiv

Multimodal LLMs can see a document, but they often can't read it reliably. Small text, tables, visual cues, and topological elements still trip them up under direct visual inference, even when the page is already sitting…

Visual Question Answering

Knowing What's Missing: Assessing Information Sufficiency in Question Answering

2025-12-06 · Akriti Jain, Aparna Garimella arxiv

Determining whether a provided context contains sufficient information to answer a question is a critical challenge for building reliable question-answering systems. While simple prompting strategies have shown success o…

Question Answering