cs.CLNov 9, 2026

Improving Confidence Estimation in Language Models with Linear Representations of Ambiguity

Authors: Themistoklis Nikas, Nishant Subramani, Aaron Mueller

Organizations: Boston University · Carnegie Mellon University, Language Technologies Institute

Abstract

As language models (LMs) are increasingly deployed in downstream applications, accurately estimating their likelihood of success on a given example is critical. However, confidence estimates from LMs are poor predictors of their likelihood of success. Accurate confidence estimation is linked in part to the detection of aleatoric uncertainty; we hypothesize that LMs possess representations of at least some aspects of this uncertainty in the form of representations of the inherent ambiguity of the input. Using difference-in-means on minimal pairs of ambiguous and unambiguous sentences, we derive ambiguity representations in LM activations, and find that steering with them selectively (albeit weakly) modulates LMs' judgments of the input's ambiguity. We then propose DART, a fine-tuning method that encourages updates to lie within the span of the ambiguity directions, and penalizes changes to the LM activations outside of this subspace. DART greatly improves calibration, encodes these improvements into the model parameters, and maintains model accuracy on multiple-choice and generative QA tasks.

Figures & tables

Explore similar work

CardsList
  1. From Answers to Interpretations: Rethinking Ambiguity-Induced Aleatoric Uncertainty Estimation in LLMs

    Sep 3, 2026Omer Nahum, Niv Nayman, Jonathan Fhima +4LLM Uncertainty EstimationAleatoric Uncertainty

  2. Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs

    Sep 29, 2026Feiyang Li, Shengjing Liu, Qi Zhan +7Uncertainty QuantificationConfidence Estimation in Language Models

  3. Closing the Confidence-Faithfulness Gap in Large Language Models

    Mar 26, 2026Miranda Muqing Miao, Lyle UngarConfidence Estimation in Language ModelsVerbalized Confidence Estimation