Confidence Estimation in Automatic Short Answer Grading with LLMs

• URL: http://arxiv.org/abs/2605.00200v1
• Date: Thu, 30 Apr 2026 20:26:10 GMT
• Title: Confidence Estimation in Automatic Short Answer Grading with LLMs
• Abstract summary: Automatic Short Answer Grading (ASAG) with generative large language models (LLMs) has recently demonstrated strong performance without task-specific fine-tuning.<n>LLMs-based grading remains imperfect, making reliable confidence estimates essential for safe and effective human-AI collaboration.<n>We propose a hybrid confidence framework that integrates model-based confidence signals with an explicit estimate of dataset-derived aleatoric uncertainty.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automatic Short Answer Grading (ASAG) with generative large language models (LLMs) has recently demonstrated strong performance without task-specific fine-tuning, while also enabling the generation of synthetic feedback for educational assessment. Despite these advances, LLM-based grading remains imperfect, making reliable confidence estimates essential for safe and effective human-AI collaboration in educational decision-making. In this work, we investigate confidence estimation for ASAG with LLMs by jointly considering model-based confidence signals and dataset-derived uncertainty. We systematically compare three model-based confidence estimation strategies, namely verbalizing, latent, and consistency-based confidence estimation, and show that model-based confidence alone is insufficient to reliably capture uncertainty in ASAG. To address this limitation, we propose a hybrid confidence framework that integrates model-based confidence signals with an explicit estimate of dataset-derived aleatoric uncertainty. Aleatoric uncertainty is operationalized by clustering semantically embedded student responses and quantifying within-cluster heterogeneity. Our results demonstrate that the proposed hybrid confidence measure yields more reliable confidence estimates and improves selective grading performance compared to single-source approaches. Overall, this work advances confidence-aware LLM-based grading for human-in-the-loop assessment, supporting more trustworthy AI-assisted educational assessment systems.

Related papers

• A Calibrated Reflection Approach for Enhancing Confidence Estimation in LLMs [3.9353006440879525]
  Calibrated Reflection is a framework that combines structured reasoning with distance-aware calibration technique.<n>We evaluate our framework on diverse datasets, including HelpSteer2, Llama T-REx, and a proprietary conversational dataset.
  arXiv  Detail & Related papers  (2026-09-03T22:52:01Z)
• Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence? [50.17126900886782]
  It remains unclear whether models can apply their own linguistic confidence framework to associate markers with specific confidence levels in a stable and generalizable way.<n>We formalize _marker internal confidence_ (MIC) as the estimated intrinsic confidence a model associates with a specific epistemic marker in a given task domain.<n>Applying our analysis framework to diverse models and tasks, we find that LLMs remain faithfully miscalibrated even under model-centric interpretation of marker meanings.
  arXiv  Detail & Related papers  (2026-05-27T17:38:00Z)
• Margin-Adaptive Confidence Ranking for Reliable LLM Judgement [19.892445164810987]
  Jung et al. (2025) introduce a hypothesis testing framework for guaranteeing agreement between large language models and human judgments.<n>We learn a dedicated confidence estimator instead of relying on confidence signals.<n>When integrated into fixed-sequence testing, the learned confidence estimator yields improved ranking accuracy and empirically strengthens the monotonic relationship between confidence and disagreement risk.
  arXiv  Detail & Related papers  (2026-05-14T21:01:05Z)
• Less Approximates More: Harmonizing Performance and Confidence Faithfulness via Hybrid Post-Training for High-Stakes Tasks [52.81286869496811]
  Large language models are increasingly deployed in high-stakes tasks, where confident yet incorrect inferences may cause real-world harm.<n>We propose to jointly optimize unsupervised Reinforcement Learning from Internal Feedback with reasoning-trace-guided Reasoning Distillation.<n>We introduce HyTuning, a hybrid post-training framework that adaptively reweights RD and RLIF via a PRG-style metric.
  arXiv  Detail & Related papers  (2026-04-09T16:50:11Z)
• BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents [58.05949210993854]
  We investigate whether search agents have the ability to communicate their own confidence through verbalized confidence scores after long sequences of actions.<n>We propose Test-Time Scaling (TTS) methods that use confidence scores to determine answer quality, encourage the model to try again until reaching a satisfactory confidence level.
  arXiv  Detail & Related papers  (2025-10-27T15:58:51Z)
• Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief [6.1929548590367505]
  Large Language Models (LLMs) have achieved remarkable success across a wide range of natural language tasks, but often exhibit overconfidence and generate plausible yet incorrect answers.<n>This overconfidence poses significant challenges for reliable uncertainty estimation and safe deployment.<n>We propose a novel self-evaluation-based calibration method that leverages the internal hidden states of LLMs to derive more accurate confidence scores.
  arXiv  Detail & Related papers  (2025-09-01T15:50:10Z)
• Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation [63.49409574310576]
  Large language models (LLMs) exhibit overconfidence, assigning high confidence scores to incorrect predictions.<n>We introduce FineCE, a novel confidence estimation method that delivers accurate, fine-grained confidence scores during text generation.<n>Our code and all baselines used in the paper are available on GitHub.
  arXiv  Detail & Related papers  (2025-08-16T13:29:35Z)
• Confidence Estimation for LLM-Based Dialogue State Tracking [9.305763502526833]
  Estimation of a model's confidence on its outputs is critical for Conversational AI systems based on large language models (LLMs) We provide an exhaustive exploration of methods, including approaches proposed for open- and closed-weight LLMs. Our findings suggest that fine-tuning open-weight LLMs can result in enhanced AUC performance, indicating better confidence score calibration.
  arXiv  Detail & Related papers  (2024-09-15T06:44:26Z)
• Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models [14.5291643644017]
  We introduce the concept of Confidence-Probability Alignment. We probe the alignment between models' internal and expressed confidence. Among the models analyzed, OpenAI's GPT-4 showed the strongest confidence-probability alignment.
  arXiv  Detail & Related papers  (2024-05-25T15:42:04Z)
• When to Trust LLMs: Aligning Confidence with Response Quality [49.371218210305656]
  We propose CONfidence-Quality-ORDer-preserving alignment approach (CONQORD) It integrates quality reward and order-preserving alignment reward functions. Experiments demonstrate that CONQORD significantly improves the alignment performance between confidence and response accuracy.
  arXiv  Detail & Related papers  (2024-04-26T09:42:46Z)
• Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection [90.71323430635593]
  We propose a novel self-detection paradigm that considers the comprehensive answer space beyond LLM-generated answers. Building upon this paradigm, we introduce a two-step framework, which firstly instructs LLM to reflect and provide justifications for each candidate answer. This framework can be seamlessly integrated with existing approaches for superior self-detection.
  arXiv  Detail & Related papers  (2024-03-15T02:38:26Z)
• An evaluation of word-level confidence estimation for end-to-end automatic speech recognition [70.61280174637913]
  We investigate confidence estimation for end-to-end automatic speech recognition (ASR) We provide an extensive benchmark of popular confidence methods on four well-known speech datasets. Our results suggest a strong baseline can be obtained by scaling the logits by a learnt temperature.
  arXiv  Detail & Related papers  (2021-01-14T09:51:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.