SOTAVerified

Reading Comprehension

Most current question answering datasets frame the task as reading comprehension where the question is about a paragraph or document and the answer often is a span in the document.

Some specific tasks of reading comprehension include multi-modal machine reading comprehension and textual machine reading comprehension, among others. In the literature, machine reading comprehension can be divide into four categories: cloze style, multiple choice, span prediction, and free-form answer. Read more about each category here.

Benchmark datasets used for testing a model's reading comprehension abilities include MovieQA, ReCoRD, and RACE, among others.

The Machine Reading group at UCL also provides an overview of reading comprehension tasks.

Figure source: A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 1760 papers

TitleStatusHype
DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback SynergyCode1
Chaining Event Spans for Temporal Relation GroundingCode0
S2ST-Omni: An Efficient and Scalable Multilingual Speech-to-Speech Translation Framework via Seamless Speech-Text Alignment and Streaming Speech Generation—0
CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversationsCode0
Automatic Generation of Inference Making Questions for Reading Comprehension AssessmentsCode0
SCOP: Evaluating the Comprehension Process of Large Language Models from a Cognitive View—0
Prosodic Structure Beyond Lexical Content: A Study of Self-Supervised Learning—0
Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language ModelsCode0
What Has Been Lost with Synthetic Evaluation?—0
ReadBench: Measuring the Dense Text Visual Reading Ability of Vision-Language ModelsCode1
Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning—0
SELF: Self-Extend the Context Length With Logistic Growth FunctionCode0
A Participatory Strategy for AI Ethics in Education and Rehabilitation grounded in the Capability Approach—0
Social Bias in Popular Question-Answering Benchmarks—0
Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation—0
Learning Graph Representation of Agent DiffusersCode0
Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models—0
Using LLMs in Generating Design Rationale for Software Architecture DecisionsCode0
LLM-as-a-Judge: Reassessing the Performance of LLMs in Extractive QACode0
GOAT-TTS: Expressive and Realistic Speech Generation via A Dual-Branch LLM—0
Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes FromCode0
Efficient Tuning of Large Language Models for Knowledge-Grounded Dialogue GenerationCode0
Do LLMs Understand Your Translations? Evaluating Paragraph-level MT with Question AnsweringCode0
FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM ExtractionCode0
Locations of Characters in Narratives: Andersen and Persuasion DatasetsCode0
Comment Staytime Prediction with LLM-enhanced Comment UnderstandingCode0
Do Chinese models speak Chinese languages?—0
Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users—0
Investigating Recent Large Language Models for Vietnamese Machine Reading Comprehension—0
HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language ModelsCode0
MRCEval: A Comprehensive, Challenging and Accessible Machine Reading Comprehension BenchmarkCode0
Zero-Shot Complex Question-Answering on Long Scientific DocumentsCode0
HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs—0
Causal Tree Extraction from Medical Case Reports: A Novel Task for Experts-like Text Comprehension—0
Exploring the Potential of Large Language Models for Estimating the Reading Comprehension Question Difficulty—0
Pay Attention to Real World Perturbations! Natural Robustness Evaluation in Machine Reading Comprehension—0
Unveiling Cultural Blind Spots: Analyzing the Limitations of mLLMs in Procedural Text Comprehension—0
RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-FollowingCode0
Eye Tracking Based Cognitive Evaluation of Automatic Readability Assessment Measures—0
Unknown Word Detection for English as a Second Language (ESL) Learners Using Gaze and Pre-trained Language Models—0
Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models—0
The Use of Artificial Intelligence Tools in Assessing Content Validity: A Comparative Study with Human Experts—0
General Embedding vs. Task-Specific Embedding: A Comparative Approach to Enhancing NLP Performance—0
A linguistically-motivated evaluation methodology for unraveling model's abilities in reading comprehension tasks—0
Automatic Feedback Generation for Short Answer Questions using Answer Diagnostic Graphs—0
LongReason: A Synthetic Long-Context Reasoning Benchmark via Context Expansion—0
Few-shot Policy (de)composition in Conversational Question Answering—0
SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language ModelsCode0
A Coordination-based Approach for Focused Learning in Knowledge-Based Systems—0
Unlocking the Potential of Multiple BERT Models for Bangla Question Answering in NCTB Textbooks—0
Show:102550
← PrevPage 1 of 36Next →
All datasetsReClorRACEMuSeRCAdversarialQACrowdSource QARadQA

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Rational Reasoner / IDOLTest80.6—Unverified
2AMR-LE-EnsembleTest80—Unverified
3MERIt(MERIt-deberta-v2-xxlarge )Test79.3—Unverified
4MERIt-deberta-v2-xxlarge deberta.v2.xxlarge.path.override_True.norm_1.1.0.w2.A100.cp200.s42Test79.3—Unverified
5Knowledge modelTest79.2—Unverified
6DeBERTa-v2-xxlarge-AMR-LE-ContrapositionTest77.2—Unverified
7LReasoner ensembleTest76.1—Unverified
8ELECTRA and ALBERTTest71—Unverified
9WWZTest69.7—Unverified
10xlnet-large-uncased [extended data]Test69.3—Unverified
#ModelMetricClaimedVerifiedStatus
1ALBERT (Ensemble)Accuracy91.4—Unverified
2Megatron-BERT (ensemble)Accuracy90.9—Unverified
3ALBERTxxlarge+DUMA(ensemble)Accuracy89.8—Unverified
4Megatron-BERTAccuracy89.5—Unverified
5XLNetAccuracy (Middle)88.6—Unverified
6DeBERTalargeAccuracy86.8—Unverified
7B10-10-10Accuracy85.7—Unverified
8RoBERTaAccuracy83.2—Unverified
9Orca 2-13BAccuracy82.87—Unverified
10Orca 2-7BAccuracy80.79—Unverified
#ModelMetricClaimedVerifiedStatus
1Golden TransformerAverage F10.94—Unverified
2MT5 LargeAverage F10.84—Unverified
3ruRoberta-large finetuneAverage F10.83—Unverified
4ruT5-large-finetuneAverage F10.82—Unverified
5Human BenchmarkAverage F10.81—Unverified
6ruT5-base-finetuneAverage F10.77—Unverified
7ruBert-large finetuneAverage F10.76—Unverified
8ruBert-base finetuneAverage F10.74—Unverified
9RuGPT3XL few-shotAverage F10.74—Unverified
10RuGPT3LargeAverage F10.73—Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa-LargeOverall: F164.4—Unverified
2BERT-LargeOverall: F162.7—Unverified
3BiDAFOverall: F128.5—Unverified
#ModelMetricClaimedVerifiedStatus
1BERTMSE0.05—Unverified
#ModelMetricClaimedVerifiedStatus
1BERT pretrained on MIMIC-IIIAnswer F163.55—Unverified