The field of natural language processing is witnessing significant advancements with the integration of Large Language Models (LLMs) in various applications, including information retrieval and education. Recent studies have explored the potential of LLMs in automated grading, privacy policy analysis, and critical thinking development. The use of LLMs in education has shown promising results, with studies demonstrating their ability to enhance student learning outcomes and improve the efficiency of grading processes. Furthermore, LLMs have been found to be effective in analyzing argumentative moves and predicting writing quality, highlighting their potential in supporting personalized learning environments. In the context of information retrieval, LLMs have been used to improve search results, detect biases, and enhance fairness. Novel approaches, such as the use of bias detectors and agentic frameworks, have been proposed to address issues of bias and fairness in AI-driven knowledge retrieval. Noteworthy papers in this area include 'Using LLMs for Automated Privacy Policy Analysis' and 'Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes', which demonstrate the potential of LLMs in advancing the field of natural language processing.
Advancements in Large Language Models for Information Retrieval and Education
Sources
Users Favor LLM-Generated Content -- Until They Know It's AI
Using LLMs for Automated Privacy Policy Analysis: Prompt Engineering, Fine-Tuning and Explainability
Developing Critical Thinking in Second Language Learners: Exploring Generative AI like ChatGPT as a Tool for Argumentative Essay Writing
Summarization Metrics for Spanish and Basque: Do Automatic Scores and LLM-Judges Correlate with Humans?
Can AI expose tax loopholes? Towards a new generation of legal policy assistants
Enhancing Arabic Automated Essay Scoring with Synthetic Data and Error Injection
Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying Probes
On the effectiveness of LLMs for automatic grading of open-ended questions in Spanish
A Multi-Model Adaptation of Speculative Decoding for Classification
Robust-IR @ SIGIR 2025: The First Workshop on Robust Information Retrieval
EconEvals: Benchmarks and Litmus Tests for LLM Agents in Unknown Environments
LLMs in the Classroom: Outcomes and Perceptions of Questions Written with the Aid of AI
Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation
Machine-assisted writing evaluation: Exploring pre-trained language models in analyzing argumentative moves
Enhanced Bloom's Educational Taxonomy for Fostering Information Literacy in the Era of Large Language Models
Raising Awareness of Location Information Vulnerabilities in Social Media Photos using LLMs
FAIR-QR: Enhancing Fairness-aware Information Retrieval through Query Refinement
Bias-Aware Agent: Enhancing Fairness in AI-Driven Knowledge Retrieval
Evaluating book summaries from internal knowledge in Large Language Models: a cross-model and semantic consistency approach