Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2501.14976

A review of annotation classification tools in the educational domain

Joaquín Gayoso-Cabada·Antonio Sarasa-Cabezuelo·José-Luis Sierra
View original source ↗Read source document ↗Export metadata ↓

Abstract

An annotation consists of a portion of information that is associated with a piece of content in order to explain something about the content or to add more information. The use of annotations as a tool in the educational field has positive effects on the learning process. The usual way to use this instrument is to provide students with contents, usually textual, with which they must associate annotations. In most cases this task is performed in groups of students who work collaboratively. This process encourages analysis and understanding of the contents since they have to understand them in order to annotate them, and also encourages teamwork. To facilitate its use, computer applications have been devel-oped in recent decades that implement the annotation process and offer a set of additional functionalities. One of these functionalities is the classification of the annotations made. This functionality can be exploited in various ways in the learning process, such as guiding the students in the annotation process, providing information to the student about how the annotation process is done and to the teacher about how the students write and how they understand the content, as well as implementing other innovative educational processes. In this sense, the classification of annotations plays a critical role in the application of the annotation in the educational field. There are many studies of annotations, but most of them consider the classification aspect marginally only. This paper presents an initial study of the classification mech-anisms used in the annotation tools, identifying four types of cases: absence of classification mechanisms, classification based on pre-established vocabularies, classification based on extensible vocabularies, and classification based on struc-tured vocabularies.

Explore related subjects

cs.CLcs.DL

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Joaquín Gayoso-Cabada, Antonio Sarasa-Cabezuelo, José-Luis Sierra. 2025-01-24. A review of annotation classification tools in the educational domain. https://doi.org/10.1515/comp-2019-0021

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Hierarchical attention interpretation: an interpretable speech-level transformer for bi-modal depression detection

Depression is a common mental disorder. Automatic depression detection tools using speech, enabled by machine learning, help early screening of depression. This paper addresses two limitations that may hinder the clinical implementations of such tools: noise resulting from segment-level labelling and a lack of model interpretability. We propose a bi-modal speech-level transformer to avoid segment-level labelling and introduce a hierarchical interpretation approach to provide both speech-level and sentence-level interpretations, based on gradient-weighted attention maps derived from all attention layers to track interactions between input features. We show that the proposed model outperforms a model that learns at a segment level ($p$=0.854, $r$=0.947, $F1$=0.897 compared to $p$=0.732, $r$=0.808, $F1$=0.768). For model interpretation, using one true positive sample, we show which sentences within a given speech are most relevant to depression detection; and which text tokens and Mel-spectrogram regions within these sentences are most relevant to depression detection. These interpretations allow clinicians to verify the validity of predictions made by depression detection tools, promoting their clinical implementations.

cs.CL↗
arXiv2026

Cultural Alignment in Large Language Models Using Soft Prompt Tuning

Large Language Model (LLM) alignment is commonly achieved through supervised fine-tuning or reinforcement learning, both of which require labeled or preference data and update model weights. Without targeted cultural adaptation, however, deployed LLMs often exhibit culturally homogeneous behavior that fails to reflect diverse local values. Aligning models to cultural value frameworks such as Hofstede's Value Survey Module (VSM13) presents a distinct challenge: alignment signals are available only as aggregated survey-level scores computed after generating responses to an entire survey, providing no per-token gradient and requiring no preference data by construction. This makes standard gradient-based alignment methods ill-suited to the task. We propose a deployment-friendly approach that encodes cultural behavior in short, tunable soft prompts optimized with Differential Evolution (DE), while keeping model weights frozen and requiring no preference data. At inference, the system inserts the appropriate cultural-specific prompt to adapt model responses for different cultures. Experiments across four countries and four instruction-tuned models show that DE-optimized prompts generally reduce discrepancy with VSM13 reference profiles, improve rank agreement with the World Values Survey (WVS), an independent framework not seen during optimization, and are preferred in blinded pairwise evaluations using majority voting across three LLM judges.

cs.CL↗
arXiv2026

VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits

Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their extensive output vocabularies. The final linear projection layer, mapping hidden states to vocabulary-sized logits, often constitutes a substantial portion of the model's parameters and computational cost during inference. Existing methods like adaptive softmax or hierarchical softmax introduce structural complexities. In this paper, we propose VQ-Logits, a novel approach that leverages Vector Quantization (VQ) to drastically reduce the parameter count and computational load of the LLM output layer. VQ-Logits replaces the large V * dmodel output embedding matrix with a small, shared codebook of K embedding vectors (K << V ). Each token in the vocabulary is mapped to one of these K codebook vectors. The LLM predicts logits over this compact codebook, which are then efficiently "scattered" to the full vocabulary space using the learned or preassigned mapping. We demonstrate through extensive experiments on standard language modeling benchmarks (e.g., WikiText-103, C4) that VQ-Logits can achieve up to 99% parameter reduction in the output layer and 6x speedup in logit computation, with only a marginal 4% increase in perplexity compared to full softmax baselines. We further provide detailed ablation studies on codebook size, initialization, and learning strategies, showcasing the robustness and effectiveness of our approach.

cs.CL↗