Divij Handa
Divij Handa has 2 papers in our library, in 2024–2025, most of them on Language models & pretraining, Question answering, Reasoning; often with Amir Saeidi, Chitta Baral, Md Nayem Uddin.
OpenAlex · h-index 2 · 15 works · 18 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 25 times in our library · ⭐ Paper Stars ranking: #8517
Affiliations
Fields, topics and concepts
📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work
🧭 Topics 4Research subjects and languages the work is about.Language models & pretraining · 2 worksQuestion answering · 1 workBias, fairness & safety · 1 workReasoning · 1 work
Works by year
2020s
Papers
- When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers (2024 · 15 citations)
Safety training for LLMs usually covers harmful requests in natural language or in well-known encodings such as Base64. This work argues that this leaves a gap: stronger reasoning lets models decode ciphers invented on the spot, and defenders cannot anticipate such ciphers in alignment data. - UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization (2025 · 14 citations)
Benchmarks for time-sensitive question answering (TSQA), such as TimeQA, TempReason and MenatQA, are built from real-world Wikidata/Wikipedia facts.
Co-authors here
Venues
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/divij-handa/