Papers Topic coverage
“Topic coverage” 태그가 달린 논문 30편 · 필터 해제
X+Slides: Benchmarking Audience-Conditioned Slide Generation
Automatically generating slide decks from source documents is an important application of large language models (LLMs). Existing benchmarks primarily assess slide completeness and technical depth, while overlooking the t…
Topic coverageGIScholarBench: Benchmarking LLM Overconfidence in GIS Research
Large language models (LLMs) are increasingly used in academic research workflows, but scholarly tasks require high factual precision and therefore expose a key weakness: overconfidence. Here, overconfidence is defined b…
Topic coverageAgent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding their responses in external knowledge, but conventional pipelines rely on static, single-step retrieval that limits performance on c…
Topic coverageKletterMix: Climbing Toward High-Quality German Pretraining Data - The Full Report
High-quality pretraining data is a central ingredient in modern language models, but German-language resources remain far less developed than their English counterparts: they are often smaller, less carefully curated, we…
Topic coverageASTRA-QA: A Benchmark for Abstract Question Answering over Documents
Document-based question answering (QA) increasingly includes abstract questions that require synthesizing scattered information from long documents or across multiple documents into coherent answers. However, this settin…
Question AnsweringTopic coverageFrom Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors
Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context compression an important component of many systems. Existing compression…
Topic coverageOptimizing Coverage and Difficulty in Reinforcement Learning for Quiz Composition
Quiz design is a tedious process that teachers undertake to evaluate the acquisition of knowledge by students. Our goal in this paper is to automate quiz composition from a set of multiple choice questions (MCQs). We for…
Reinforcement LearningTransfer LearningTopic coverageDiversifying Toxicity Search in Large Language Models Through Speciation
Evolutionary prompt search is a practical black-box approach for red teaming large language models, however existing methods often collapse onto a small family of high-performing prompts, limiting coverage of distinct fa…
Topic coverageRed TeamingFrom Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning
Large Language Models (LLMs) excel at general tasks but underperform in specialized domains like economics and psychology, which require deep, principled understanding. To address this, we introduce ACER (Automated Curri…
Continual PretrainingTopic coverageTowards AI Agents for Course Instruction in Higher Education: Early Experiences from the Field
This article presents early findings from designing, deploying and evaluating an AI-based educational agent deployed as the primary instructor in a graduate-level Cloud Computing course at IISc. We detail the design of a…
Topic coverageTopic Coverage-based Demonstration Retrieval for In-Context Learning
The effectiveness of in-context learning relies heavily on selecting demonstrations that provide all the necessary information for a given test input. To achieve this, it is crucial to identify and cover fine-grained kno…
Topic coverageConfigurable multi-agent framework for scalable and realistic testing of llm-based agents
Large-language-model (LLM) agents exhibit complex, context-sensitive behaviour that quickly renders static benchmarks and ad-hoc manual testing obsolete. We present Neo, a configurable, multi-agent framework that automat…
Question GenerationTopic coverageDeFine: A Decomposed and Fine-Grained Annotated Dataset for Long-form Article Generation
Long-form article generation (LFAG) presents challenges such as maintaining logical consistency, comprehensive topic coverage, and narrative coherence across extended articles. Existing datasets often lack both the hiera…
ArticlesFormRetrievalTopic coverageQG-SMS: Enhancing Test Item Analysis via Student Modeling and Simulation
While the Question Generation (QG) task has been increasingly adopted in educational assessments, its evaluation remains limited by approaches that lack a clear connection to the educational values of test items. In this…
Language ModelingLanguage ModellingLarge Language ModelQuestion Generation+2ExpertGenQA: Open-ended QA generation in Specialized Domains
Generating high-quality question-answer pairs for specialized technical domains remains challenging, with existing approaches facing a tradeoff between leveraging expert examples and achieving topical diversity. We prese…
DiversityFew-Shot LearningTopic coveragePinLanding: Content-First Keyword Landing Page Generation via Multi-Modal AI for Web-Scale Discovery
Online platforms like Pinterest hosting vast content collections traditionally rely on manual curation or user-generated search logs to create keyword landing pages (KLPs) -- topic-centered collection pages that serve as…
AttributeAttribute ExtractionLanguage ModelingLanguage Modelling+2Neural Topic Modeling with Large Language Models in the Loop
Topic modeling is a fundamental task in natural language processing, allowing the discovery of latent thematic structures in text corpora. While Large Language Models (LLMs) have demonstrated promising capabilities in to…
Topic coverageTopic ModelsReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval
With the development of large language models (LLMs), zero-shot learning has attracted much attention for various NLP tasks. Different from prior works that generate training data with billion-scale natural language gene…
DescriptiveRetrievaltext-classificationText Classification+4MUG: A General Meeting Understanding and Generation Benchmark
Listening to long video/audio recordings from video conferencing and online courses for acquiring information is extremely inefficient. Even after ASR systems transcribe recordings into long-form spoken language document…
Extractive SummarizationKeyphrase ExtractionTopic coverageTopic Ontologies for Arguments
Many computational argumentation tasks, like stance classification, are topic-dependent: the effectiveness of approaches to these tasks significantly depends on whether the approaches were trained on arguments from the s…
Stance ClassificationTopic coverage