Tulika Tewari, Nalin Asanka Gamagedara Arachchilage, Jagat Sesh Challa, Dhruv Kumar. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Taxonomy completion is the task of integrating new concepts into an existing taxonomy by determining the appropriate hypernym--hyponym relations. Existing approaches often struggle with the inherent imbalance between leaf and non-leaf edges, which induces bias in representation learning. In this paper, we propose BLEND: B alanced and L eaf- En hanced D ual Fine-Tuning for Taxonomy Completion, a novel framework designed to mitigate this inductive bias. Our method employs independent fine-tuning of two lightweight large language models (LLMs): one optimized with a leaf-focused objective and the other trained with a balanced focused strategy. To further enhance structural understanding, we apply contrastive learning over structure-encoded paths and introduce a combined loss function, enabling more robust representation of hierarchical relations. Extensive experiments on three real-world benchmark datasets demonstrate that BLEND achieves up to 9.32% improvement in recall or hit metrics compared to state-of-the-art approaches. Moreover, BLEND delivers efficient inference while outperforming the latest baseline COMI, highlighting its effectiveness for taxonomy completion tasks.

Effective teaching necessitates adapting pedagogical strategies to the inherent diversity of students, encompassing variations in aptitude, learning styles, and personality, a critical challenge in education and teacher training. Large Language Models (LLMs) offer a powerful tool to simulate complex classroom dynamics, providing a controlled environment for exploring optimal teaching patterns. However, existing simulation frameworks often fall short by neglecting comprehensive student modeling beyond basic knowledge states and, more importantly, by lacking mechanisms for teachers to dynamically adapt their approach based on student feedback and collective performance. Addressing these limitations, we propose a simulation framework that integrates LLM-based diverse student agents with a self-evolving teacher agent. We use genetic algorithms to automatically tune and optimize the teacher’s pedagogical parameters based on simulated student performance, enabling the teacher agent to discover and refine teaching patterns tailored to specific class characteristics. Complementing this, we introduce Persona-RAG, a novel Retrieval-Augmented Generation method specifically designed for personalized knowledge retrieval in pedagogical contexts, allowing students to retrieve information as per their learning styles. We show how Persona-RAG remains competitive with standard RAG baselines in accurately retrieving relevant information while adding a touch of personalization for students. Crucially, we perform extensive experiments and highlight the different patterns learnt by the teacher agent while optimizing over classes with students of various learning styles. Our work presents a significant step towards creating adaptive educational technologies and improving teacher training through realistic, data-driven simulation.

Since the emergence of Large Language Models (LLMs) popularized by the release of GPT-3 and ChatGPT, LLMs have shown remarkable promise in programming-related tasks. While code generation using LLMs has become a popular field of research, code evaluation using LLMs remains under-explored. In this paper, we focus on LLM-based code evaluation and attempt to fill in the existing gaps. We propose multi-agentic novel approaches using question-specific rubrics tailored to the problem statement, arguing that these perform better for logical assessment than the existing approaches that use question-agnostic rubrics . To address the lack of suitable evaluation datasets, we introduce two datasets: a Data Structures and Algorithms dataset containing 150 student submissions from a popular Data Structures and Algorithms practice website, and an Object Oriented Programming dataset comprising 80 student submissions from undergraduate computer science courses. In addition to using standard metrics (Spearman Correlation, Cohen’s Kappa), we additionally propose a new metric called as Leniency, which quantifies evaluation strictness relative to expert assessment. Our comprehensive analysis demonstrates that question-specific rubrics significantly enhance logical assessment of code in educational settings, providing better feedback aligned with instructional goals beyond mere syntactic correctness.

In this paper, we investigate the potential of Large Language Models (LLMs) to improve English speaking skills. This is particularly relevant in countries like India, where English is crucial for academic, professional, and personal communication but remains a non-native language for many. Traditional methods for enhancing speaking skills often rely on human experts, which can be limited in terms of scalability, accessibility, and affordability. Recent advancements in Artificial Intelligence (AI) offer promising solutions to overcome these limitations.

This research paper aims to analyze the strengths and weaknesses associated with the utilization of ChatGPT as an educational tool in the context of undergraduate computer science education. ChatGPT's usage in tasks such as solving assignments and exams has the potential to undermine students' learning outcomes and compromise academic integrity. This study adopts a quantitative approach to demonstrate the notable unreliability of ChatGPT in providing accurate answers to a wide range of questions within the field of undergraduate computer science. While the majority of existing research has concentrated on assessing the performance of Large Language Models in handling programming assignments, our study adopts a more comprehensive approach. Specifically, we evaluate various types of questions such as true/false, multi-choice, multi-select, short answer, long answer, design-based, and coding-related questions. Our evaluation highlights the potential consequences of students excessively relying on ChatGPT for the completion of assignments and exams, including self-sabotage. We conclude with a discussion on how can students and instructors constructively use ChatGPT and related tools to enhance the quality of instruction and the overall student experience.

Geo-distributed analytics (GDA) involves processing of data stored across geographically distributed sites. Such analytics involves data transfer over the wide area network (WAN) links. WAN links are highly constrained and heterogeneous in nature, making the data transfer over the WAN slow and costly. To tackle this issue, recent approaches have proposed WAN-aware scheduling and placement of geo-distributed analytics tasks. However, computing joins in a geo-distributed setting remains a challenging problem. In this work, we propose AggFirstJoin, an approach to minimize the cost of geo-distributed joins using a theoretically sound query transformation technique. Our optimization approach takes a combined view of the join and aggregation operations which are often part of the same query and pushes (a transformed) aggregation before join in a manner to produce the same results as the original query. We augment our query transformation technique with a WAN-aware task placement and a Bloom filtering approach to further reduce query execution time and WAN usage respectively. We implement our proposed technique on top of Apache Spark, a popular engine for big data analytics. We extensively evaluate our proposed technique using synthetic, TPC-H and Amplab Big Data benchmark datasets on a real geo-distributed testbed on AWS as well as an emulated testbed. Our evaluations show our proposed technique achieves up to 300x reduction in query execution time and 200x reduction in WAN usage as compared to state-of-the-art GDA techniques.

Federated Learning is a machine learning paradigm where a global model is trained in-situ across a large number of distributed edge devices. While this technique avoids the cost of transferring data to a central location and achieves a strong degree of privacy, it presents additional challenges due to the heterogeneous hardware resources available for training. Furthermore, data is not independent and identically distributed (IID) across all edge devices, resulting in statistical heterogeneity across devices. Due to these constraints, client selection strategies play an important role for timely convergence during model training. Existing strategies ensure that each individual device is included, at least periodically, in the training process. In this work, we propose HACCS, a Heterogeneity-Aware Clustered Client Selection system that identifies and exploits the statistical heterogeneity by representing all distinguishable data distributions instead of individual devices in the training process. HACCS is robust to individual device dropout, provided other devices in the system have similar data distributions. We propose privacy-preserving methods for estimating these client distributions and clustering them. We also propose strategies for leveraging these clusters to make scheduling decisions in a federated learning system. Our evaluation on real-world datasets suggests that our framework can provide 18% −38% reduction in time to convergence compared to the state of the art without any compromise in accuracy.

Federated Learning [1] enables distributed devices to learn a shared machine learning model together, without uploading their private training data. It has received significant attention recently and has been used in mobile applications such as search suggestion [2] and object detection [3]. Federated Learning is different from distributed machine learning due to the following reasons: 1) System heterogeneity: federated learning is usually performed on devices having highly dynamic and heterogeneous network, compute, and power availability. 2) Data heterogeneity (or statistical heterogeneity): data is produced by different users on different devices, and therefore may have different statistical distribution (non-IID).