MultiHint-9K: Orchestrating Human and AI Agency for Scalable Pedagogical Hint Generation

Toward scalable generative AI: efficient language model distillation via zero-shot rationales

Results indicate that near-optimal performance can be achieved even when rationales are provided for only a subset of the training data, and that shorter explanations are often sufficient.

Team DArgk at the 2026 ELOQUENT lab for evaluating generative language model quality: Residuals of Humanity: AI Detection Evasion via GRPO Fine-Tuning

Large language models (LLMs) can generate fluent and coherent text that is increasingly difficult to distinguish from human writing, motivating the development of automatic AI-generated text detectors. However, the robustness of such detectors under adversarial generation remains uncertain. This paper presents SHADE (S...

Self-Play Search Distillation for Large Language Model Reasoning

Self-Play Search Distillation (SPSD), a framework for generating superhuman synthetic data via self-play of MuZero-like networks trained on board games, offers an annotation-efficient way to create high-quality synthetic data for improving LLM performance in reasoning tasks.

Overview and Joint Report of the Voight-Kampff Task of the ELOQUENT 2026 Lab for Evaluating Generative Language Model Quality

Reactance-Aware Recursive Alignment for Human–AI Translation: Modeling Translator Agency and Task-Specific Critical Automation Capability

Professional translators may resist highly directive AI assistance when it threatens perceived autonomy, authorship, and control. This study introduces the Recursive Control and Alignment Protocol (ReCAP), a reactance-aware framework for interactive machine translation. ReCAP combines a reactance-potential model with a...

EduBehaviors: Assertion-based Schemas for Auditable Coding of Educational Dialogues

Large language models have enabled rapid deployment of language classification and analysis, allowing users to describe complex constructs in natural language, such as pedagogical moves or expressions of learning and engagement, and label them in conversational datasets such as classroom or tutoring transcripts. Howeve...