information retrieval
PulseAugur coverage of information retrieval — every cluster mentioning information retrieval across labs, papers, and developer communities, ranked by signal.
12 day(s) with sentiment data
-
New TRUST framework improves temporal session-based recommendations
Researchers have developed a new framework called TRUST for temporal session-based recommendation systems. Unlike previous methods that used absolute time intervals, TRUST calibrates each interval relative to the specif…
-
Research paper highlights scoring function limitations in AI fairness
A new research paper titled "Scoring Is Not Enough: Addressing Gaps in Utility-fairness Trade-offs for Ranking" argues that current scoring functions in information retrieval and recommendation systems are insufficient …
-
New visual analytics tool enhances personalized item ranking creation
Researchers have developed "Ranking Companion," a novel visual analytics system designed to improve the creation of personalized item rankings. This approach addresses the challenge of users lacking domain knowledge or …
-
New academic concept index boosts scientific document retrieval
Researchers have developed a new method to improve scientific document retrieval by creating an academic concept index. This index extracts and organizes key concepts from papers, which then enhances both synthetic quer…
-
New SAERec system uses LLMs and sparse autoencoders for interpretable recommendations
Researchers have developed SAERec, a novel recommendation system that leverages sparse autoencoders to construct fine-grained, interpretable intent priors from large language models. This approach aims to improve recomm…
-
New NNN decoding method enhances information retrieval beyond dense retrieval
Researchers have introduced Non-Negative Elastic Net (NNN) decoding as a novel approach to information retrieval, moving beyond the standard inner-product scoring of dense retrieval methods. This new technique treats re…
-
New method boosts user modeling by using negative behavior signals
Researchers have developed a new method for sequential user modeling in click-through rate prediction that incorporates implicit negative behaviors, such as skips and scroll-pasts, alongside positive interactions. This …
-
New framework aims for verifiable, bias-aware LLM user simulators
A new tutorial proposes a framework for creating verifiable user simulators based on large language models (LLMs). This framework aims to address the opacity of current LLM-based simulators, making it easier to understa…
-
Quantization Limits Dense Retrieval Dimension, Study Finds
A new theoretical study published on arXiv explores the limitations imposed by quantization on dense top-k retrieval systems. The research demonstrates that achieving perfect retrieval with B bits per coordinate require…
-
Reader sub-groups form within documents, but cross-document stability is unclear
Researchers have found that when multiple individuals highlight the same document, distinct sub-groups of readers emerge within that document. These factions agree on specific sections far more than random chance would …
-
Research: Personalization in highlighting is driven by selection, not salience
New research published on arXiv explores the nature of personalization in social web highlighting, distinguishing between "selection" (which documents a user chooses) and "salience" (which passages within a document are…
-
New method retrieves similar segmentation problems for evolutionary learning
Researchers have developed a novel approach to evolutionary learning by focusing on retrieving similar segmentation problems rather than solely on algorithm design. This method involves collecting knowledge into an abst…
-
New metric 1/Ratio@k proposed for ANN search evaluation
Researchers have proposed a new metric, 1/Ratio@k, to evaluate Approximate Nearest Neighbor (ANN) search algorithms, arguing it better reflects retrieval quality than the traditional Recall@k. The proposed metric, which…
-
New Bayesian Model Explains Search Engine User Behavior
A new research paper introduces a Bayesian rational model for search engine users, detailing how individuals sequentially decide whether to inspect more items or stop with their best find. The model proposes an optimal …
-
LLMs transform information retrieval, focusing on denoising and content grounding
Two new research papers explore the evolving landscape of information retrieval (IR) as it shifts from human consumption to large language model (LLM) utilization. The first paper, "LLM-Oriented Information Retrieval: A…
-
Survey details methods for characterizing semantic change in language
This survey paper examines methods for characterizing semantic change in language, a phenomenon that impacts computational linguistics tasks like translation and information retrieval. It formally defines three categori…
-
A Reproducibility Study of LLM-Based Query Reformulation
Two new research papers explore the application and efficiency of Large Language Models (LLMs) in information retrieval. The first paper, a reproducibility study, evaluates ten LLM-based query reformulation methods acro…