Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors

In this paper, we investigate whether current state-of-the-art large language models (LLMs) are effective as AI tutors and whether they demonstrate pedagogical abilities necessary for good AI tutoring in educational dialogues. Previous efforts towards evaluation have been limited to subjective protocols and benchmarks. To bridge this gap, we propose a unified evaluation taxonomy with eight pedagogical dimensions based on key learning sciences principles, which is designed to assess the pedagogical value of LLM-powered AI tutor responses grounded in student mistakes or confusion in the mathematical domain. We release MRBench -- a new evaluation benchmark containing 192 conversations and 1,596 responses from seven state-of-the-art LLM-based and human tutors, providing gold annotations for eight pedagogical dimensions. We assess reliability of the popular Prometheus2 LLM as an evaluator and analyze each tutor's pedagogical abilities, highlighting which LLMs are good tutors and which ones are more suitable as question-answering systems. We believe that the presented taxonomy, benchmark, and human-annotated labels will streamline the evaluation process and help track the progress in AI tutors' development.

LLMs in Education: Novel Perspectives, Challenges, and Opportunities

The role of large language models (LLMs) in education is an increasing area of interest today, considering the new opportunities they offer for teaching, learning, and assessment. This cutting-edge tutorial provides an overview of the educational applications of NLP and the impact that the recent advances in LLMs have had on this field. We will discuss the key challenges and opportunities presented by LLMs, grounding them in the context of four major educational applications: reading, writing, and speaking skills, and intelligent tutoring systems (ITS). This COLING 2025 tutorial is designed for researchers and practitioners interested in the educational applications of NLP and the role LLMs have to play in this area. It is the first of its kind to address this timely topic.

SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models

Large language models (LLMs) have gained increased popularity due to their remarkable success across various tasks, which has led to the active development of a large set of diverse LLMs. However, individual LLMs have limitations when applied to complex tasks because of such factors as training biases, model sizes, and the datasets used. A promising approach is to efficiently harness the diverse capabilities of LLMs to overcome these individual limitations. Towards this goal, we introduce a novel LLM selection algorithm called SelectLLM. This algorithm directs input queries to the most suitable subset of LLMs from a large pool, ensuring they collectively provide the correct response efficiently. SelectLLM uses a multi-label classifier, utilizing the classifier's predictions and confidence scores to design optimal policies for selecting an optimal, query-aware, and lightweight subset of LLMs. Our findings show that the proposed model outperforms individual LLMs and achieves competitive performance compared to similarly sized, computationally expensive top-performing LLM subsets. Specifically, with a similarly sized top-performing LLM subset, we achieve a significant reduction in latency on two standard reasoning benchmarks: 13% lower latency for GSM8K and 70% lower latency for MMLU. Additionally, we conduct comprehensive analyses and ablation studies, which validate the robustness of the proposed model.

Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing

With the rapid development of LLMs, it is natural to ask how to harness their capabilities efficiently. In this paper, we explore whether it is feasible to direct each input query to a single most suitable LLM. To this end, we propose LLM routing for challenging reasoning tasks. Our extensive experiments suggest that such routing shows promise but is not feasible in all scenarios, so more robust approaches should be investigated to fill this gap.

Trie-NLG: Trie Context Augmentation to Improve Personalized Query Auto-Completion for Short and Unseen Prefixes

Query auto-completion (QAC) aims at suggesting plausible completions for a given query prefix. Traditionally, QAC systems have leveraged tries curated from historical query logs to suggest most popular completions. In this context, there are two specific scenarios that are difficult to handle for any QAC system: short prefixes (which are inherently ambiguous) and unseen prefixes. Recently, personalized Natural Language Generation (NLG) models have been proposed to leverage previous session queries as context for addressing these two challenges. However, such NLG models suffer from two drawbacks: (1) some of the previous session queries could be noisy and irrelevant to the user intent for the current prefix, and (2) NLG models cannot directly incorporate historical query popularity. This motivates us to propose a novel NLG model for QAC, Trie-NLG, which jointly leverages popularity signals from trie and personalization signals from previous session queries. We train the Trie-NLG model by augmenting the prefix with rich context comprising of recent session queries and top trie completions. This simple modeling approach overcomes the limitations of trie-based and NLG-based approaches and leads to state-of-the-art performance. We evaluate the Trie-NLG model using two large QAC datasets. On average, our model achieves huge ~57% and ~14% boost in MRR over the popular trie-based lookup and the strong BART-based baseline methods, respectively. We make our code publicly available.

Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages

We address the task of machine translation from an extremely low-resource language (LRL) to English using cross-lingual transfer from a closely related high-resource language (HRL). For many of these languages, no parallel corpora are available, even monolingual corpora are limited and representations in pre-trained sequence-to-sequence models are absent. These factors limit the benefits of cross-lingual transfer from shared embedding spaces in multilingual models. However, many extremely LRLs have a high level of lexical similarity with related HRLs. We utilize this property by injecting character and character-span noise into the training data of the HRL prior to learning the vocabulary. This serves as a regularizer which makes the model more robust to lexical divergences between the HRL and LRL and better facilitates cross-lingual transfer. On closely related HRL and LRL pairs from multiple language families, we observe that our method significantly outperforms the baseline MT as well as approaches proposed previously to address cross-lingual transfer between closely related languages. We also show that the proposed character-span noise injection performs better than the unigram-character noise injection.

Meta-X$_{NLG}$: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation

Recently, the NLP community has witnessed a rapid advancement in multilingual and cross-lingual transfer research where the supervision is transferred from high-resource languages (HRLs) to low-resource languages (LRLs). However, the cross-lingual transfer is not uniform across languages, particularly in the zero-shot setting. Towards this goal, one promising research direction is to learn shareable structures across multiple tasks with limited annotated data. The downstream multilingual applications may benefit from such a learning setup as most of the languages across the globe are low-resource and share some structures with other languages. In this paper, we propose a novel meta-learning framework (called Meta-X$_{NLG}$) to learn shareable structures from typologically diverse languages based on meta-learning and language clustering. This is a step towards uniform cross-lingual transfer for unseen languages. We first cluster the languages based on language representations and identify the centroid language of each cluster. Then, a meta-learning algorithm is trained with all centroid languages and evaluated on the other languages in the zero-shot setting. We demonstrate the effectiveness of this modeling on two NLG tasks (Abstractive Text Summarization and Question Generation), 5 popular datasets and 30 typologically diverse languages. Consistent improvements over strong baselines demonstrate the efficacy of the proposed framework. The careful design of the model makes this end-to-end NLG setup less vulnerable to the accidental translation problem, which is a prominent concern in zero-shot cross-lingual NLG tasks.

ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation

Despite the recent advancement in NLP research, cross-lingual transfer for natural language generation is relatively understudied. In this work, we transfer supervision from high resource language (HRL) to multiple low-resource languages (LRLs) for natural language generation (NLG). We consider four NLG tasks (text summarization, question generation, news headline generation, and distractor generation) and three syntactically diverse languages, i.e., English, Hindi, and Japanese. We propose an unsupervised cross-lingual language generation framework (called ZmBART) that does not use any parallel or pseudo-parallel/back-translated data. In this framework, we further pre-train mBART sequence-to-sequence denoising auto-encoder model with an auxiliary task using monolingual data of three languages. The objective function of the auxiliary task is close to the target tasks which enriches the multi-lingual latent representation of mBART and provides good initialization for target tasks. Then, this model is fine-tuned with task-specific supervised English data and directly evaluated with low-resource languages in the Zero-shot setting. To overcome catastrophic forgetting and spurious correlation issues, we applied freezing model component and data argumentation approaches respectively. This simple modeling approach gave us promising results.We experimented with few-shot training (with 1000 supervised data points) which boosted the model performance further. We performed several ablations and cross-lingual transferability analyses to demonstrate the robustness of ZmBART.

Walk in Wild: An Ensemble Approach for Hostility Detection in Hindi Posts

As the reach of the internet increases, pejorative terms started flooding over social media platforms. This leads to the necessity of identifying hostile content on social media platforms. Identification of hostile contents on low-resource languages like Hindi poses different challenges due to its diverse syntactic structure compared to English. In this paper, we develop a simple ensemble based model on pre-trained mBERT and popular classification algorithms like Artificial Neural Network (ANN) and XGBoost for hostility detection in Hindi posts. We formulated this problem as binary classification (hostile and non-hostile class) and multi-label multi-class classification problem (for more fine-grained hostile classes). We received third overall rank in the competition and weighted F1-scores of ~0.969 and ~0.61 on the binary and multi-label multi-class classification tasks respectively.

Coarse and Fine-Grained Hostility Detection in Hindi Posts using Fine Tuned Multilingual Embeddings

Due to the wide adoption of social media platforms like Facebook, Twitter, etc., there is an emerging need of detecting online posts that can go against the community acceptance standards. The hostility detection task has been well explored for resource-rich languages like English, but is unexplored for resource-constrained languages like Hindidue to the unavailability of large suitable data. We view this hostility detection as a multi-label multi-class classification problem. We propose an effective neural network-based technique for hostility detection in Hindi posts. We leverage pre-trained multilingual Bidirectional Encoder Representations of Transformer (mBERT) to obtain the contextual representations of Hindi posts. We have performed extensive experiments including different pre-processing techniques, pre-trained models, neural architectures, hybrid strategies, etc. Our best performing neural classifier model includes One-vs-the-Rest approach where we obtained 92.60%, 81.14%,69.59%, 75.29% and 73.01% F1 scores for hostile, fake, hate, offensive, and defamation labels respectively. The proposed model outperformed the existing baseline models and emerged as the state-of-the-art model for detecting hostility in the Hindi posts.