From Answers to Interpretations: Rethinking Ambiguity-Induced Aleatoric Uncertainty Estimation in LLMs
On the map: LLM reasoning → Test-time compute and efficient thinking
Abstract (arXiv)
A key challenge in reliable LLM deployment is recognizing when uncertainty reflects irreducible variability in the task rather than limitations in the model's knowledge. In language tasks, a central source of such aleatoric uncertainty is input ambiguity or underspecification, where multiple interpretations remain plausible. Existing decomposition methods estimate aleatoric uncertainty by generating multiple clarifications of the input, querying the model for an answer under each clarification, and comparing the resulting answers. We argue that answers are not necessary for identifying ambiguity: they are often redundant, add avoidable cost, and can mislead through epistemic leakage. We support this claim theoretically, and propose a clarification-only approach that estimates this ambiguity-induced component directly from the space of plausible interpretations, without answers to the clarified inputs. Using ambiguity detection as an operational evaluation across three benchmarks, this direct approach improves AUROC (63.34 vs. 60.85), reduces computational cost by 4-26x in output tokens and 2.2-3.5x in API calls, and yields estimates with substantially lower correlation with epistemic uncertainty. Overall, our results suggest that ambiguity-induced aleatoric uncertainty is better estimated from the interpretation space than from the response space.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 13 of its 46 references that are in the map. First posted on arXiv 3 Sep 2026.
Builds on
13 of 46 references.
Closest ancestors · 1
Same direction, newest first
Other references · 12
- 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
- 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
- 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
- 2024To Believe or Not to Believe Your LLMcited by 120
- 2023Decomposing Uncertainty for Large Language Models through Input Clarification Ensemblingcited by 113
- 2020ConvAI3: Generating Clarifying Questions for Open-Domain Dialogue Systems (ClariQ)cited by 55
- 2024Distinguishing the Knowable from the Unknowable with Language Modelscited by 45
- 2024AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queriescited by 32
- 2020Uncertainty Estimation in Autoregressive Structured Predictioncited by 21
- 2023Decision-Making Under Uncertainty: Beyond Probabilitiescited by 8
- 2025Fine-Grained Uncertainty Decomposition in Large Language Models: A Spectral Approachcited by 8
- 2026Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilitiescited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models
- 2026Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
- 2023Quantifying Uncertainty in Natural Language Explanations of Large Language Models
- 2025Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents
- 2026Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification
- 2026Uncertainty Decomposition for Clarification Seeking in LLM Agents
- 2026Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs
- 2026Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study