Optimizing LLM Annotation of Classroom Discourse through Multi-Agent Orchestration

• URL: http://arxiv.org/abs/2603.13353v1
• Date: Sun, 08 Mar 2026 16:51:03 GMT
• Title: Optimizing LLM Annotation of Classroom Discourse through Multi-Agent Orchestration
• Abstract summary: Large language models (LLMs) are increasingly positioned as scalable tools for annotating educational data.<n>However, growing evidence suggests that single-pass LLM outputs remain unreliable for high-stakes educational constructs.<n>This tension between scale and validity sits at the core of contemporary education data science.
• Score: 0.21410799064827235
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly positioned as scalable tools for annotating educational data, including classroom discourse, interaction logs, and qualitative learning artifacts. Their ability to rapidly summarize instructional interactions and assign rubric-aligned labels has fueled optimism about reducing the cost and time associated with expert human annotation. However, growing evidence suggests that single-pass LLM outputs remain unreliable for high-stakes educational constructs that require contextual, pedagogical, or normative judgment, such as instructional intent or discourse moves. This tension between scale and validity sits at the core of contemporary education data science. In this work, we present and empirically evaluate a hierarchical, cost-aware orchestration framework for LLM-based annotation that improves reliability while explicitly modeling computational tradeoffs. Rather than treating annotation as a one-shot prediction problem, we conceptualize it as a multi-stage epistemic process comprising (1) an unverified single-pass annotation stage, in which models independently assign labels based on the rubric; (2) a self-verification stage, in which each model audits its own output against rubric definitions and revises its label if inconsistencies are detected; and (3) a disagreement-centric adjudication stage, in which an independent adjudicator model examines the verified labels and justifications and determines a final label in accordance with the rubric. This structure mirrors established human annotation workflows in educational research, where initial coding is followed by self-checking and expert resolution of disagreements.

Related papers

• From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment [12.134587575174633]
  We propose a general framework for sentence-level interpretability of rubric-based scoring.<n>We show that SHAP provides more faithful and transferable explanations for rubric-based scoring.
  arXiv  Detail & Related papers  (2026-04-18T14:27:51Z)
• Beyond Holistic Scores: Automatic Trait-Based Quality Scoring of Argumentative Essays [15.895792302323883]
  In educational contexts, teachers and learners require interpretable, trait-level feedback.<n>We study trait-based Automatic Argumentative Essay Scoring using two complementary modeling paradigms.<n>We show that explicitly modeling score ordinality substantially improves agreement with human raters.
  arXiv  Detail & Related papers  (2026-02-04T14:30:52Z)
• Enhancing LLM-Based Data Annotation with Error Decomposition [6.6544828402388445]
  Large language models offer a scalable alternative to human coding for data annotation tasks.<n>Their performance on subjective annotation tasks is less consistent and more prone to errors.<n>We propose a diagnostic evaluation paradigm that incorporates a human-in-the-loop step to separate task-inherent ambiguity from model-driven inaccuracies.
  arXiv  Detail & Related papers  (2026-01-17T05:43:17Z)
• FORESTLLM: Large Language Models Make Random Forest Great on Few-shot Tabular Learning [20.27406245916013]
  We propose a novel framework that unifies the structural inductive biases of decision forests with the semantic reasoning capabilities of large language models (LLMs)<n>Our method is two-fold. First, we introduce a semantic splitting criterion in which the LLM evaluates candidate partitions based on their coherence over both labeled and unlabeled data, enabling the induction of more robust and generalizable tree structures under few-shot supervision.<n>Second, we propose a one-time in-context inference mechanism for leaf node stabilization, where the LLM distills the decision path and its supporting examples into a concise, deterministic prediction, replacing noisy empirical estimates with semantically informed outputs
  arXiv  Detail & Related papers  (2026-01-16T14:08:51Z)
• Context-Adaptive Requirements Defect Prediction through Human-LLM Collaboration [1.4499356176178066]
  We propose a Human-LLM Collaboration (HLC) approach that treats defect prediction as an adaptive process rather than a static classification task.<n>We evaluate this approach using the weak word smell on the QuRE benchmark of 1,266 annotated Mercedes-Benz requirements.
  arXiv  Detail & Related papers  (2026-01-05T10:00:14Z)
• Consistency-Aware Editing for Entity-level Unlearning in Language Models [53.522931419965424]
  We introduce a novel consistency-aware editing (CAE) framework for entity-level unlearning.<n>CAE aggregates a diverse set of prompts related to a target entity, including its attributes, relations, and adversarial paraphrases.<n>It then jointly learns a low-rank update guided by a consistency regularizer that aligns the editing directions across prompts.
  arXiv  Detail & Related papers  (2025-12-19T15:18:07Z)
• Measuring Teaching with LLMs [4.061135251278187]
  This paper uses custom Large Language Models built on sentence-level embeddings.<n>We show that these specialized models can achieve human-level and even super-human performance with expert human ratings above 0.65.<n>We also find that aggregate model scores align with teacher value-added measures, indicating they are capturing features relevant to student learning.
  arXiv  Detail & Related papers  (2025-10-27T03:42:04Z)
• Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
  We study how well large language models (LLMs) explain their generations through rationales. We show that prompting-based methods are less "faithful" than attribution-based explanations.
  arXiv  Detail & Related papers  (2024-06-28T20:06:30Z)
• Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
  We propose a new evaluation method, SQC-Score. Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score. Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
  arXiv  Detail & Related papers  (2024-04-04T15:36:53Z)
• Robust Representation Learning for Unreliable Partial Label Learning [86.909511808373]
  Partial Label Learning (PLL) is a type of weakly supervised learning where each training instance is assigned a set of candidate labels, but only one label is the ground-truth. This is known as Unreliable Partial Label Learning (UPLL) that introduces an additional complexity due to the inherent unreliability and ambiguity of partial labels. We propose the Unreliability-Robust Representation Learning framework (URRL) that leverages unreliability-robust contrastive learning to help the model fortify against unreliable partial labels effectively.
  arXiv  Detail & Related papers  (2023-08-31T13:37:28Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
  We evaluate language understanding capacities on simple inference tasks that most humans find trivial. We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. The models exhibit moderate to low performance on these evaluation sets.
  arXiv  Detail & Related papers  (2023-05-24T06:41:09Z)

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.