SOTAVerified

answerability prediction

Papers

Showing 19 of 9 papers

TitleStatusHype
Mistral 7BCode6
GPT-4 Technical ReportCode6
The Llama 3 Herd of ModelsCode4
Language Models are Few-Shot LearnersCode3
PeerQA: A Scientific Question Answering Dataset from Peer ReviewsCode1
Towards Reliable and Factual Response Generation: Detecting Unanswerable Questions in Information-Seeking ConversationsCode0
Towards Confident Machine Reading Comprehension0
Challenges in Information-Seeking QA: Unanswerable Questions and Paragraph Retrieval0
NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading Comprehension0
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Mistral-IT-v02-7B-32kMacro F10.47Unverified
2Command-R-v01-34B-128kMacro F10.42Unverified
3GPT-3.5-Turbo-0613-16kMacro F10.33Unverified
4Llama-3-IT-8B-8kMacro F10.31Unverified
5GPT-4o-2024-08-06Macro F10.31Unverified
6Llama-3-IT-8B-32kMacro F10.29Unverified