tf–idf
PulseAugur coverage of tf–idf — every cluster mentioning tf–idf across labs, papers, and developer communities, ranked by signal.
9 day(s) with sentiment data
-
New benchmark improves SNOMED CT concept recommendation from clinical text
Researchers have developed a new benchmark for recommending SNOMED CT concepts from masked clinical contexts, aiming to improve the standardization and interoperability of clinical language. The study utilized the SNOME…
-
New Bangla Sentence Function Classification Corpus Developed
Researchers have developed a new corpus of 10,000 Bangla sentences, manually categorized into declarative, interrogative, imperative, and exclamatory functions, to address the limited resources for Bangla sentence funct…
-
New framework detects adversarial intent injection in AI-native 6G networks
Researchers have developed a new framework to detect adversarial intent injection in AI-native 6G networks. This method addresses the challenge of malicious policies being disguised within legitimate network configurati…
-
TF-IDF and BM25 identified as exact KL divergences in new arXiv paper
A new paper published on arXiv proposes that TF-IDF and BM25, two foundational methods for scoring query-document relevance in information retrieval, can be precisely interpreted as Kullback-Leibler divergences. This re…
-
New study benchmarks privacy risks in NLP text classifiers
A new study on arXiv evaluates the privacy risks associated with training natural language processing (NLP) text classifiers. Researchers benchmarked membership inference attacks (MIAs) on the GLUE SST-2 sentiment datas…
-
New method enables cross-domain solution import for computational problems
Researchers have developed a novel method for identifying and importing computational solutions across different scientific fields. By creating domain-stripped computational fingerprints for research papers, they can ef…
-
New method learns representations for Classical Tamil verse-commentary pairs
Researchers have developed a new method for learning representations of Classical Tamil verse-commentary pairs, aiming to understand what information can be recovered through machine learning. They trained various model…
-
Study compares six retrieval methods for academic advisor discovery
A new study published on arXiv evaluates six different information retrieval methods for discovering academic advisors. The research, which analyzed 768 faculty profiles from nine US universities, found that a re-rankin…
-
New SHELF benchmark tests LLMs on library bibliographic tasks
A new benchmark system called SHELF has been developed to evaluate the performance of language models on bibliographic tasks relevant to libraries and archives. The system generates synthetic data based on Library of Co…
-
New SHELF benchmark tests LLMs on library bibliographic tasks · 2 sources tracked
Researchers have developed SHELF, a Synthetic Harness for Evaluating LLM Fitness, designed to benchmark bibliographic tasks for libraries and archives. This Python system generates controlled benchmark data from labeled…
-
PageIndex offers vectorless RAG for dev.to content
PageIndex is a new, vectorless retrieval-augmented generation (RAG) solution designed specifically for the dev.to platform. It bypasses the need for computationally intensive vector embeddings by building an inverted in…
-
Sparse autoencoders show reward filtering captures solution completeness, not reasoning quality
Researchers have developed a reward-informed sparse autoencoder (RI-SAE) to interpret language model activations, specifically focusing on reasoning capabilities. While the RI-SAE successfully separated high-reward and …
-
AI model predicts research paper quality using text analysis
Researchers have developed a method to classify scientific papers as high-quality or flawed using only textual features from their titles and abstracts. The study evaluated various embedding techniques and classifiers, …
-
LLMs vs. Fine-Tuned NLU: New Framework Guides Intent Detection Choices
A new research paper explores when large language models (LLMs) are a suitable replacement for fine-tuned Natural Language Understanding (NLU) models in conversational systems. The study found that while fine-tuned mode…
-
LLM agents show lexical convergence on social platforms, study finds
A new study introduces PV-SST, a peer-voted social-platform testbed for evaluating large language model (LLM) agents. The research found that exposure to a feed of previous peer posts, ranked by likes, led to increased …
-
New dataset Strategic 16K benchmarks AI models for document sensitivity
Researchers have developed Strategic 16K, a new dataset of 16,000 diplomatic cables from WikiLeaks, designed to prevent label leakage in document sensitivity classification. This corpus was used to benchmark classical a…
-
Financial NLP benchmarks suffer from temporal leakage, inflating performance metrics
A new audit of financial news NLP benchmarks reveals significant temporal leakage, where random train-test splits inflate performance metrics by up to 6.5x compared to chronological splits. This leakage is particularly …
-
AccretionLink system audits on-device attribute inference attacks
Researchers have developed AccretionLink, a novel on-device auditing system designed to detect attribute inference attacks. This system defines confidentiality and integrity games to model the attack, utilizing partial …
-
New AI Tool Lets Users Chat With Webpage Content
A developer created TooLong.AI, a web application that allows users to chat with the content of any webpage. The tool scrapes and cleans webpage content, then uses TF-IDF and keyword similarity to extract the most relev…
-
IMDb sentiment analysis tutorial combines classic ML with DistilBERT LoRA
A new tutorial details a comprehensive sentiment analysis workflow using the Stanford NLP IMDb dataset. It compares traditional TF-IDF and Logistic Regression baselines with fine-tuned DistilBERT models utilizing LoRA a…