activity
20222025
most citedSciNLI: A Corpus for Natural Language Inference on Scientific Text

2 citations · 3 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2025

A MISMATCHED Benchmark for Scientific Natural Language Inference

Firoz Shaik, Mobashir Sadat, Nikita Gautam +2

Scientific Natural Language Inference (NLI) is the task of predicting the semantic relation between a pair of sentences extracted from research articles. Existing datasets for this…

cs.CL2024

Co-training for Low Resource Scientific Natural Language Inference

Mobashir Sadat, Cornelia Caragea

Scientific Natural Language Inference (NLI) is the task of predicting the semantic relation between a pair of sentences extracted from research articles. The automatic annotation m…

cs.CL2024

MSciNLI: A Diverse Benchmark for Scientific Natural Language Inference

Mobashir Sadat, Cornelia Caragea

The task of scientific Natural Language Inference (NLI) involves predicting the semantic relation between two sentences extracted from research articles. This task was recently pro…

cs.CL2023

DelucionQA: Detecting Hallucinations in Domain-specific Question Answering

Mobashir Sadat, Zhengyu Zhou, Lukas Lange +6

Hallucination is a well-known phenomenon in text generated by large language models (LLMs). The existence of hallucinatory responses is found in almost all application scenarios e.…

cs.CL2022

Learning to Infer from Unlabeled Data: A Semi-supervised Learning Approach for Robust Natural Language Inference

Mobashir Sadat, Cornelia Caragea

Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) aims at predicting the relation between a pair of sentences (premise and hypothesis) as entailment, contrad…

cs.CL20221 cited

Hierarchical Multi-Label Classification of Scientific Documents

Mobashir Sadat, Cornelia Caragea

Automatic topic classification has been studied extensively to assist managing and indexing scientific documents in a digital collection. With the large number of topics being avai…