Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models (2025 · 22 citations)
The paper examines whether large language models can recognise when they should decline to answer, which the authors call Abstention Ability (AA).
Augmenting LLM Reasoning with Dynamic Notes Writing for Complex MultiHop QA (2026)
Iterative retrieval-augmented generation helps with multi-hop questions, but each retrieval round adds more documents to the prompt.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language ModelsInternational Conference on Computational Linguistics (COLING)Nishanth Madhusudhan, Sathwik Tejaswi Madhusudhan, Vikas Yadav, et al.2025 · 22 citations
BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning ↗arXiv (Cornell University) · no summary yetAhmed Masry et al.2025 · 3 citations
Augmenting LLM Reasoning with Dynamic Notes Writing for Complex MultiHop QALanguage Resources and Evaluation Conference (LREC)Rishabh Maheshwary, Masoud Hashemi, Khyati Mahajan, et al.2026

Co-authors here

6 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 25 times (of the 149,439 papers whose bibliographies we read); 5 citing papers with a page here →.

Updated 1 November 2026