PinnedNeeraj VarshneyThe Hallucination Problem of Large Language ModelsHallucination in the context of language models refers to the generation of text or responses that seem syntactically sound, fluent, and…Aug 20, 2023Aug 20, 2023
PinnedNeeraj VarshneyinAnalytics VidhyaA Primer on Open-Domain Question Answering (ODQA) — Part 1Jul 23, 2022Jul 23, 2022
PinnedNeeraj VarshneyinAnalytics VidhyaOut-of-Distribution Detection in Deep Neural NetworksMaking AI systems Robust and ReliableDec 25, 2020Dec 25, 2020
Neeraj VarshneyinBecoming Human: Artificial Intelligence MagazineLLM Defense StrategiesTowards Improving the Safety of LLMsJan 3Jan 3
Neeraj VarshneySelective Prediction in Natural Language ProcessingImproving Reliability of NLP SystemsSep 11, 2022Sep 11, 2022
Neeraj VarshneyLet the Model Decide its Curriculum for Multitask LearningTo appear in the third edition of the workshop Deep Learning for Low Resource NLP @ NAACL 2022.May 30, 2022May 30, 2022
Neeraj VarshneyILDAE: Instance-Level Difficulty Analysis of Evaluation DataTo appear in ACL 2022.May 6, 2022May 6, 2022
Neeraj VarshneyUnsupervised Natural Language Inference Using PHL Triplet GenerationTo appear in the Findings of ACL 2022.May 1, 2022May 1, 2022
Neeraj VarshneyinAnalytics VidhyaA Primer on Knowledge Distillation in NLP — Part 1Teacher Student NetworksDec 22, 20211Dec 22, 20211
Neeraj VarshneyCan We Predict Performance of an NLP Model without Actually Training or Testing it?An Alternative to Exhaustive TestingFeb 25, 2021Feb 25, 2021