Towards Transparent AI Grading: Semantic Entropy as a Signal for Human-AI Disagreement

• URL: http://arxiv.org/abs/2508.04105v1
• Date: Wed, 06 Aug 2025 06:02:14 GMT
• Title: Towards Transparent AI Grading: Semantic Entropy as a Signal for Human-AI Disagreement
• Abstract summary: We introduce semantic entropy, a measure of variability across multiple GPT-4-generated explanations for the same student response, as a proxy for human grader disagreement.<n>Our findings position semantic entropy as an interpretable uncertainty signal that supports more transparent and trustworthy AI-assisted grading.
• Score: 2.6293270655263385
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated grading systems can efficiently score short-answer responses, yet they often fail to indicate when a grading decision is uncertain or potentially contentious. We introduce semantic entropy, a measure of variability across multiple GPT-4-generated explanations for the same student response, as a proxy for human grader disagreement. By clustering rationales via entailment-based similarity and computing entropy over these clusters, we quantify the diversity of justifications without relying on final output scores. We address three research questions: (1) Does semantic entropy align with human grader disagreement? (2) Does it generalize across academic subjects? (3) Is it sensitive to structural task features such as source dependency? Experiments on the ASAP-SAS dataset show that semantic entropy correlates with rater disagreement, varies meaningfully across subjects, and increases in tasks requiring interpretive reasoning. Our findings position semantic entropy as an interpretable uncertainty signal that supports more transparent and trustworthy AI-assisted grading workflows.

Related papers

• The Measurement Revolution? Credible Measurement and Inference in the Age of AI [8.204799574862864]
  AI models convert unstructured data, such as text and images, into structured variables at low cost.<n>This shifts the bottleneck from finding any scalable measure of a phenomenon to choosing among many plausible ones.<n>We argue that credible inference with AI-generated variables requires appropriately designed validation.
  arXiv  Detail & Related papers  (2026-08-24T17:28:34Z)
• Beyond Semantic Equivalence: Logical Graphs for LLM Uncertainty Quantification [30.900501335481184]
  We propose Logical Graph Uncertainty (LGU), a framework that explicitly models implication and incompatibility among answers.<n>Across multiple question-answering benchmarks, LGU consistently improves uncertainty estimation over existing methods.
  arXiv  Detail & Related papers  (2026-07-18T16:14:08Z)
• Pause or Fabricate? Training Language Models for Grounded Reasoning [50.104657152302956]
  We propose Grounded Reasoning via Interactive Reinforcement Learning (GRIL) for grounded reasoning under incomplete information.<n>GRIL decomposes the reasoning process into two stages: clarify and pause, which identifies whether the available information is sufficient, and grounded reasoning, which performs task solving once the necessary premises are established.<n>Experiments on GSM8K-Insufficient and MetaMATH-Insufficient show that GRIL significantly improves premise detection (up to 45%), leading to a 30% increase in task success while reducing average response length by over 20%.
  arXiv  Detail & Related papers  (2026-04-21T16:45:29Z)
• RAGEN-2: Reasoning Collapse in Agentic RL [123.40730283427136]
  In RAGEN-2, we find that even with stable entropy, models can rely on fixed templates that look diverse but are input-agnostic.<n>We decompose reasoning quality into within-input diversity (Entropy) and cross-input distinguishability (Mutual Information, MI)<n>Across diverse tasks, mutual information correlates with final performance much more strongly than entropy, making it a more reliable proxy for reasoning quality.
  arXiv  Detail & Related papers  (2026-04-07T04:29:41Z)
• The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs? [14.977096886054142]
  We show that reasoning prefixes accumulate answer-relevant information in expectation as generation progresses.<n>We derive observable signatures of SIA linking conditional answer entropy dynamics to correctness.
  arXiv  Detail & Related papers  (2026-03-11T18:00:18Z)
• Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure [58.89643769707751]
  We study latent chain-of-thought as a manipulable causal process in representation space.<n>We find that latent-step budgets behave less like homogeneous extra depth and more like staged functionality with non-local routing.<n>These results motivate mode-conditional and stability-aware analyses as more reliable tools for interpreting and improving latent reasoning systems.
  arXiv  Detail & Related papers  (2026-02-09T15:25:12Z)
• Exploring Syntropic Frameworks in AI Alignment: A Philosophical Investigation [0.0]
  I argue that AI alignment should be reconceived as architecting syntropic, reasons-responsive agents through process-based, multi-agent, developmental mechanisms.<n>I articulate the specification trap'' argument demonstrating why content-based value specification appears structurally unstable.<n>I propose syntropy as an information-theoretic framework for understanding multi-agent alignment dynamics.
  arXiv  Detail & Related papers  (2025-11-19T23:31:29Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• How does Transformer Learn Implicit Reasoning? [41.315116538534106]
  We study how implicit multi-hop reasoning emerges by training transformers from scratch in a controlled symbolic environment.<n>We find that training with atomic triples is not necessary but accelerates learning, and that second-hop generalization relies on query-level exposure to specific compositional structures.
  arXiv  Detail & Related papers  (2025-05-29T17:02:49Z)
• Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales [54.78115855552886]
  We show how to construct over-complete invariants with a Convolutional Neural Networks (CNN)-like hierarchical architecture. With the over-completeness, discriminative features w.r.t. the task can be adaptively formed in a Neural Architecture Search (NAS)-like manner. For robust and interpretable vision tasks at larger scales, hierarchical invariant representation can be considered as an effective alternative to traditional CNN and invariants.
  arXiv  Detail & Related papers  (2024-02-23T16:50:07Z)
• Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs [58.620269228776294]
  We propose a task-agnostic framework for resolving ambiguity by asking users clarifying questions. We evaluate systems across three NLP applications: question answering, machine translation and natural language inference. We find that intent-sim is robust, demonstrating improvements across a wide range of NLP tasks and LMs.
  arXiv  Detail & Related papers  (2023-11-16T00:18:50Z)
• A Semantic Approach to Decidability in Epistemic Planning (Extended Version) [72.77805489645604]
  We use a novel semantic approach to achieve decidability. Specifically, we augment the logic of knowledge S5$_n$ and with an interaction axiom called (knowledge) commutativity. We prove that our framework admits a finitary non-fixpoint characterization of common knowledge, which is of independent interest.
  arXiv  Detail & Related papers  (2023-07-28T11:26:26Z)
• Learnability with PAC Semantics for Multi-agent Beliefs [38.88111785113001]
  The tension between deduction and induction is perhaps the most fundamental issue in areas such as philosophy, cognition and artificial intelligence. Valiant recognised that the challenge of learning should be integrated with deduction. Although weaker than classical entailment, it allows for a powerful model-theoretic framework for answering queries.
  arXiv  Detail & Related papers  (2023-06-08T18:22:46Z)
• RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank [54.854714257687334]
  We propose a novel approach, RankCSE, for unsupervised sentence representation learning. It incorporates ranking consistency and ranking distillation with contrastive learning into a unified framework. An extensive set of experiments are conducted on both semantic textual similarity (STS) and transfer (TR) tasks.
  arXiv  Detail & Related papers  (2023-05-26T08:27:07Z)
• How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding [56.222097640468306]
  We provide mechanistic understanding of how transformers learn "semantic structure" We show, through a combination of mathematical analysis and experiments on Wikipedia data, that the embedding layer and the self-attention layer encode the topical structure.
  arXiv  Detail & Related papers  (2023-03-07T21:42:17Z)
• Domain-level Pairwise Semantic Interaction for Aspect-Based Sentiment Classification [3.1977819149534987]
  We propose a plug-and-play Pairwise Semantic Interaction (PSI) module, which takes pairwise sentences as input. Different gates are generated to effectively highlight the key semantic features of each sentence. Finally, the adversarial interaction between the vectors is used to make the semantic representation of two sentences more distinguishable.
  arXiv  Detail & Related papers  (2022-02-21T07:59:17Z)
• Nested Counterfactual Identification from Arbitrary Surrogate Experiments [95.48089725859298]
  We study the identification of nested counterfactuals from an arbitrary combination of observations and experiments. Specifically, we prove the counterfactual unnesting theorem (CUT), which allows one to map arbitrary nested counterfactuals to unnested ones.
  arXiv  Detail & Related papers  (2021-07-07T12:51:04Z)
• Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity [0.0]
  I've exploited a recently released dataset for span-selection Question Answering, namely SubjQA. SubjQA is the first dataset that contains questions that ask for subjective opinions corresponding to review paragraphs from six different domains. I've investigated the inner workings of a Transformer-based architecture to contribute to a better understanding of these not yet well understood "black-box" models.
  arXiv  Detail & Related papers  (2020-06-02T13:48:14Z)

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.