ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models

• URL: http://arxiv.org/abs/2608.09548v2
• Date: Tue, 11 Aug 2026 06:58:23 GMT
• Title: ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models
• Abstract summary: Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators.<n>Existing benchmarks evaluate these requirements largely in isolation, so none assesses education-facing suitability as an integrated profile.<n>We introduce ELBench, the first benchmark to evaluate all four requirements (General Capability, Safety and Trustworthiness, Basic Education, and High-Level Cultivation) on the same models under a common protocol.
• Score: 71.84650682660373
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators. These roles place demands that ordinary question answering does not: a usable education-facing model is supposed to be accurate, safe under sensitive prompts, instructionally useful, and aligned with pedagogical goals at the same time. Existing benchmarks evaluate these requirements largely in isolation, so none assesses education-facing suitability as an integrated profile. We introduce ELBench, the first benchmark to evaluate all four requirements (General Capability, Safety and Trustworthiness, Basic Education, and High-Level Cultivation) on the same models under a common protocol, combining curated public sources with newly synthesized safety and cultivation data. We evaluate nine models, seven frontier general-purpose systems and two education-specialized variants, and report three findings. First, module-level profiles are more informative than a single aggregate: the top six models are statistically indistinguishable on overall score, yet their module leaders differ substantially, and safety is anti-correlated with practical teaching (r = -0.83). Second, the Chinese-developed models lead the safety module, the most discriminative in the suite; this advantage is largest on region-specific normative content and narrows, but does not vanish, on universal-harm content. Third, the two education-specialized models lead neither education module, and on High-Level Cultivation all models share a systematic blind spot: on the structured judgment task they converge on the same non-reference option, favoring pedagogical style over fit to the stated goal, so the module scores uniformly low and does not separate models. This raises, but does not resolve, whether domain post-training keeps pace with frontier systems on education tasks.

Related papers

• Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model [50.29667251847595]
  We show that despite being larger in model size and stronger in safety capability, there exists an alignment gap between teacher and student language models.<n>We propose a BoN sampling method that attributes the unsafe behavior back to the base LLMs in the latent space.<n>In particular, across 7 teacher models and 6 student models of different classes and sizes, we show an average attack success rate (ASR) reduction of 28.2% in DAN, 31.3% in WildJailbreak and 35.4 % in StrongREJECT benchmarks.
  arXiv  Detail & Related papers  (2026-04-01T02:42:41Z)
• From Images to Words: Efficient Cross-Modal Knowledge Distillation to Language Models from Black-box Teachers [33.522307330599496]
  ARMADA is a cross-modal knowledge distillation framework designed to transfer knowledge from large vision-language models to language-only models.<n>We empirically validate ARMADA on twelve natural language understanding, eight complex generative reasoning and five instruction-tuning tasks.<n>Our findings challenge conventional knowledge distillation paradigms by demonstrating that even vision-language models can significantly enhance language models when distilled appropriately.
  arXiv  Detail & Related papers  (2026-03-11T15:24:34Z)
• UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? [50.92401586025528]
  Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear.<n>We introduce UniG2U-Bench, a comprehensive benchmark categorizing generation-to-understanding (G2U) evaluation into 7 regimes and 30 subtasks.
  arXiv  Detail & Related papers  (2026-03-03T18:36:16Z)
• UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models [62.76435672183968]
  We introduce a novel framework, namely UNIFORM, for knowledge transfer from a diverse set of off-the-shelf models into one student model.<n>We propose a dedicated voting mechanism to capture the consensus of knowledge both at the logit level and at the feature level.<n>Experiments demonstrate that UNIFORM effectively enhances unsupervised object recognition performance compared to strong knowledge transfer baselines.
  arXiv  Detail & Related papers  (2025-08-27T00:56:11Z)
• PL-Guard: Benchmarking Language Model Safety for Polish [43.39208658482427]
  We introduce a manually annotated benchmark dataset for language model safety classification in Polish.<n>We also create adversarially perturbed variants of these samples designed to challenge model robustness.<n>We train these models using different combinations of annotated data and evaluate their performance, comparing it against publicly available guard models.
  arXiv  Detail & Related papers  (2025-06-19T13:56:41Z)
• An Open-Source Dual-Loss Embedding Model for Semantic Retrieval in Higher Education [0.30723404270319693]
  This study presents two open-source embedding models fine-tuned for educational question answering.<n>A synthetic dataset of 3,197 sentence pairs was constructed through a combination of manual curation and large language model (LLM)-assisted generation.<n>Two training strategies were evaluated: (1) a baseline model fine-tuned using MultipleNegativesRankingLoss (MNRL), and (2) a dual-loss model that combines MNRL with CosineSimilarityLoss to improve both semantic ranking and similarity calibration.
  arXiv  Detail & Related papers  (2025-05-08T03:14:14Z)
• MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset [0.0]
  Language models (LMs) have excelled in various broad domains.<n>They must demonstrate proficiency in specific, granular areas of knowledge.<n> MALAMUTE is the first education-based cloze-style dataset.
  arXiv  Detail & Related papers  (2024-12-13T12:46:33Z)
• Universal Semi-supervised Model Adaptation via Collaborative Consistency Training [92.52892510093037]
  We introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA) We propose a collaborative consistency training framework that regularizes the prediction consistency between two models. Experimental results demonstrate the effectiveness of our method on several benchmark datasets.
  arXiv  Detail & Related papers  (2023-07-07T08:19:40Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)

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.