I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering

[2604.03904] I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2604.03904 (cs) [Submitted on 5 Apr 2026 ( v1 ), last revised 14 Aug 2026 (this version, v2)] Title: I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering Authors: Haotian Zong , Binze Li , Yufei Long , Sinyin Chang , Jialong Wu , Gillian K. Hadfield View a PDF of the paper titled I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering, by Haotian Zong and 5 other authors View PDF HTML (experimental) Abstract: Large language models (LLMs) often produce confident but incorrect answers, in part because standard evaluation incentives reward guessing over expressing uncertainty. We study epistemic abstention for factual questions with verifiable answers, where the goal is to improve selective answering, making LLMs abstain when they are likely to be wrong while preserving correct answers. Inspired by human behavioral decisions in question answering, we introduce I-CALM, a prompt-level framework for black-box LLMs. I-CALM combines elicited verbal confidence, announced answer/abstain payoffs, and normative guidance emphasizing truthfulness, humility, evidential support, and responsibility. To distinguish targeted abstention from indiscriminate refusal, we use a two-stage evaluation protocol, in which LLMs first choose whether to answer or abstain, and are then forced to provide a best guess for the abstained ones. Across models and factual QA datasets, I-CALM improves selective answering by reducing false-answer rate among surfaced responses and improving abstention quality, shifting error-prone cases into abstention while retaining answers the model would have answered correctly. Overall, I-CALM offers a lightweight way to improve inference-time selective answering without retraining or access to model's internal states. Code is available at this https URL . Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2604.03904 [cs.CL] (or arXiv:2604.03904v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2604.03904 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Binze Li [ view email ] [v1] Sun, 5 Apr 2026 00:15:41 UTC (5,127 KB) [v2] Fri, 14 Aug 2026 20:05:50 UTC (4,698 KB) Full-text links: Access Paper: View a PDF of the paper titled I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering, by Haotian Zong and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2026-04 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty#974211
• Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation#984165
• ABSOL: Aggregated Bayesian Subsampling Orchestrated with LLMs#1084906
• Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs#1142368
• Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs#1122327