keyword
linguistic confidence
Linguistic confidence refers to the degree of certainty or probability that a language model expresses directly through natural language text rather than through internal numerical probabilities or output logits. Instead of relying on hidden mathematical scores, a model conveys linguistic confidence within its generated statements using verbalized probabilities, explicit assertions of certainty, or epistemic hedging markers. In natural language processing and uncertainty calibration, this concept is used to assess how well a system's spoken or written certainty reflects the actual factual correctness of its outputs, helping human users and downstream applications gauge reliability and make calibrated decisions.
2 items
Linguistic Calibration of Long-Form Generations
Neil Band, Xuechen Li, Tengyu Ma, Tatsunori Hashimoto
Why you should read this
Proposes a decision-theoretic training framework that combines supervised fine-tuning and reinforcement learning to teach language models to express calibrated verbal confidence statements across long-form text, significantly improving downstream user decision-making without sacrificing generation accuracy.
Language models (LMs) may lead their users to make suboptimal downstream decisions when they confidently hallucinate. This issue can be mitigated by having the LM verbally convey the probability that its claims are correct, but existing models cannot produce long-form text with calibrated confidence statements. Through the lens of decision-making, we define linguistic calibration for long-form generations: an LM is linguistically calibrated if its generations enable its users to make calibrated probabilistic predictions. This definition enables a training framework where a supervised finetuning step bootstraps an LM to emit long-form generations with confidence statements such as “I estimate a 30% chance of...” or “I am certain that...”, followed by a reinforcement learning step which rewards generations that enable a user to provide calibrated answers to related questions. We linguistically calibrate Llama 2 7B and find in automated and human evaluations of long-form generations that it is significantly more calibrated than strong finetuned factuality baselines with comparable accuracy. These findings generalize under significant domain shifts to scientific and biomedical questions and to an entirely held-out person biography generation task. Our results demonstrate that long-form generations may be calibrated end-to-end by constructing an objective in the space of the predictions that users make in downstream decision-making.
Added
2026-10-03
A Survey of Confidence Estimation and Calibration in Large Language Models
Jiahui Geng, Fengyu Cai, Yuxia Wang, Heinz Koeppl, Preslav Nakov, Iryna Gurevych
Why you should read this
Presents a structured taxonomy of methods, metrics, and applications for estimating and calibrating large language model confidence to mitigate factual errors and improve generation reliability.
Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks in various domains. Despite their impressive performance, they can be unreliable due to factual errors in their generations. Assessing their confidence and calibrating them across different tasks can help mitigate risks and enable LLMs to produce better generations. There has been a lot of recent research aiming to address this, but there has been no comprehensive overview to organize it and to outline the main lessons learned. The present survey aims to bridge this gap. In particular, we outline the challenges and we summarize recent technical advancements for LLM confidence estimation and calibration. We further discuss their applications and suggest promising directions for future work.
Added
2026-09-26