20 results for “topic models”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper proposes a new method, EGIM, to improve high-granularity topic modeling by separating semantically similar but distinct topics.
This paper relates linear recommenders and topic models, and proposes a method to extract topics from linear autoencoders.
The paper proposes a zero-shot multi-label topic classification framework and finds that while knowledge graph augmentation improves performance for smaller language models, it offers diminishing retu…
This paper introduces SVD-RAG, a cost-efficient and content-adaptive summarization method for hierarchical Retrieval-Augmented Generation systems using Singular Value Decomposition on dense sentence e…
This paper introduces model merging as a training-free strategy for designing a single retrieval model that operates across both ad-hoc and conversational settings, improving ad-hoc search capabilitie…
This paper surveys 34 peer-reviewed studies applying generative large language models to literature retrieval and eligibility screening.
The paper tests language models on an information retrieval task using the Wikipedia Game and compares their performance across languages and domains.
This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.
This paper introduces a new framework for understanding how autoregressive and masked diffusion language models access factual knowledge.
This paper proposes a joint model for learning textual representations that are both semantically meaningful and aligned with an external response.
The paper introduces an agentic framework for text clustering that dynamically adapts the taxonomy generation process using specialized LLM agents, achieving state-of-the-art performance on multiple b…
An extension of Triangolazioni webapp is presented, which enriches curated content with context-dependent information from Large Language Models in a loosely-coupled architecture.
Mathieu Delcluze, Léa Briand, Benjamin Chapus, Deniz Mekik +1 more
The paper presents an automatic playlist captioning system deployed on Deezer to address the challenge of describing personalized playlists in natural language.
Ziyu Chen, Yilun Zhao, Jiashuo Sun, Yiling Ma +2 more
The paper introduces IdeaAnchor, a paradigm for training LLMs to perform research ideation using structured specifications.
The paper introduces TikStance, a multimodal and context-aware dataset for stance detection in political discussions on TikTok.
This paper proposes an approach for fine-grained sentiment analysis using regression and extraction tasks, involving a weighted ensemble of transformer-based encoder models and a large language model…
The paper introduces a novel, scalable framework to monitor and classify dataset usage within research literature, addressing the current lack of infrastructure for tracking data citations.
This paper proposes a unified multi-task framework for handling six different entity pair relationship types in e-commerce with a shared relevance model.
The paper presents a graph-based clustering approach for unsupervised term discovery that outperforms centre-based methods in producing Zipf-like distributions.
The authors introduce Structured PubMed, a comprehensive corpus of section-labeled biomedical abstracts compiled from the complete PubMed database.