Papers Extractive Question-Answering
“Extractive Question-Answering” 태그가 달린 논문 102편 · 필터 해제
HalluMix: A Task-Agnostic, Multi-Domain Benchmark for Real-World Hallucination Detection
As large language models (LLMs) are increasingly deployed in high-stakes domains, detecting hallucinated content$\unicode{x2013}$text that is not grounded in supporting evidence$\unicode{x2013}$has become a critical chal…
Extractive Question-AnsweringHallucinationQuestion AnsweringRAG+2When is dataset cartography ineffective? Using training dynamics does not improve robustness against Adversarial SQuAD
In this paper, I investigate the effectiveness of dataset cartography for extractive question answering on the SQuAD dataset. I begin by analyzing annotation artifacts in SQuAD and evaluate the impact of two adversarial …
Adversarial RobustnessExtractive Question-AnsweringQuestion AnsweringOn Mechanistic Circuits for Extractive Question-Answering
Large language models are increasingly used to process documents and facilitate question-answering on them. In our paper, we extract mechanistic circuits for this real-world language modeling task: context-augmented lang…
Extractive Question-AnsweringLanguage ModelingLanguage ModellingQuestion AnsweringFoQA: A Faroese Question-Answering Dataset
We present FoQA, a Faroese extractive question-answering (QA) dataset with 2,000 samples, created using a semi-automated approach combining Large Language Models (LLMs) and human validation. The dataset was generated fro…
ArticlesExtractive Question-AnsweringQuestion AnsweringAmaSQuAD: A Benchmark for Amharic Extractive Question Answering
This research presents a novel framework for translating extractive question-answering datasets into low-resource languages, as demonstrated by the creation of the AmaSQuAD dataset, a translation of SQuAD 2.0 into Amhari…
Extractive Question-AnsweringQuestion AnsweringXLM-RPassage Segmentation of Documents for Extractive Question Answering
Retrieval-Augmented Generation (RAG) has proven effective in open-domain question answering. However, the chunking process, which is essential to this pipeline, often receives insufficient attention relative to retrieval…
ChunkingExtractive Question-AnsweringOpen-Domain Question AnsweringPassage Retrieval+4SynFinTabs: A Dataset of Synthetic Financial Tables for Information and Table Extraction
Table extraction from document images is a challenging AI problem, and labelled data for many content domains is difficult to come by. Existing table extraction datasets often focus on scientific tables due to the vast a…
ArticlesDataset GenerationExtractive Question-AnsweringLarge Language Model+3Learning-to-Defer for Extractive Question Answering
Pre-trained language models have profoundly impacted the field of extractive question-answering, leveraging large-scale textual corpora to enhance contextual language understanding. Despite their success, these models st…
Computational EfficiencyDecision MakingExtractive Question-AnsweringQuestion AnsweringTowards Robust Extractive Question Answering Models: Rethinking the Training Methodology
This paper proposes a novel training method to improve the robustness of Extractive Question Answering (EQA) models. Previous research has shown that existing models, when trained on EQA datasets that include unanswerabl…
Extractive Question-AnsweringQuestion AnsweringExploring Language Model Generalization in Low-Resource Extractive QA
In this paper, we investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift, i.e., can LLMs generalize to domains that require specific knowledge such as medicine and law in a z…
Domain GeneralizationExtractive Question-AnsweringLanguage ModelingLanguage Modelling+1Integrating SPARQL and LLMs for Question Answering over Scholarly Data Sources
The Scholarly Hybrid Question Answering over Linked Data (QALD) Challenge at the International Semantic Web Conference (ISWC) 2024 focuses on Question Answering (QA) over diverse scholarly sources: DBLP, SemOpenAlex, and…
Extractive Question-AnsweringQuestion AnsweringOMoS-QA: A Dataset for Cross-Lingual Extractive Question Answering in a German Migration Context
When immigrating to a new country, it is easy to feel overwhelmed by the need to obtain information on financial support, housing, schooling, language courses, and other issues. If relocation is rushed or even forced, th…
Extractive Question-AnsweringLanguage ModellingLarge Language ModelQuestion AnsweringClinical Reading Comprehension with Encoder-Decoder Models Enhanced by Direct Preference Optimization
Extractive question answering over clinical text is a crucial need to help deal with the deluge of clinical text generated in hospitals. While encoder models (e.g., BERT) have been popular for this reading comprehension …
DecoderExtractive Question-AnsweringQuestion AnsweringReading ComprehensionMLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models
Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved i…
Extractive Question-AnsweringKnowledge DistillationLanguage ModelingLanguage Modelling+2QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering
Extractive Question Answering (EQA) in Machine Reading Comprehension (MRC) often faces the challenge of dealing with semantically identical but format-variant inputs. Our work introduces a novel approach, called the ``Qu…
Extractive Question-AnsweringMachine Reading ComprehensionQuestion AnsweringReading ComprehensionFrom Multiple-Choice to Extractive QA: A Case Study for English and Arabic
The rapid evolution of Natural Language Processing (NLP) has favoured major languages such as English, leaving a significant gap for many others due to limited resources. This is especially evident in the context of data…
BelebeleExtractive Question-AnsweringMachine Reading ComprehensionMultiple-choice+3GeMQuAD : Generating Multilingual Question Answering Datasets from Large Language Models using Few Shot Learning
The emergence of Large Language Models (LLMs) with capabilities like In-Context Learning (ICL) has ushered in new possibilities for data generation across various domains while minimizing the need for extensive data coll…
Extractive Question-AnsweringFew-Shot LearningIn-Context LearningMachine Translation+2Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding
Recent advances in natural language processing (NLP) can be largely attributed to the advent of pre-trained language models such as BERT and RoBERTa. While these models demonstrate remarkable performance on general datas…
Domain AdaptationExtractive Question-AnsweringMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION+5Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought
We introduce a novel framework, LM-Guided CoT, that leverages a lightweight (i.e., <1B) language model (LM) for guiding a black-box large (i.e., >10B) LM in reasoning tasks. Specifically, the lightweight LM first generat…
Extractive Question-AnsweringKnowledge DistillationLanguage ModelingLanguage Modelling+3Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation
We introduce Bonito, an open-source model for conditional task generation that converts unannotated text into task-specific training datasets for instruction tuning. We aim to enable zero-shot task adaptation of large la…
AttributeExtractive Question-AnsweringLanguage ModellingLarge Language Model+2