semantic search
30 articles about semantic search in AI news
Replace Claude Code's Context-Stuffing with git-semantic for Team-Wide Semantic Search
A new tool, git-semantic, lets teams build and share a semantic search index of their codebase via Git, eliminating redundant API calls and enabling faster, more accurate Claude Code queries.
From BM25 to Corrective RAG: A Benchmark Study Challenges the Dominance of Semantic Search for Tabular Data
A systematic benchmark of 10 RAG retrieval strategies on a financial QA dataset reveals that a two-stage hybrid + reranking pipeline performs best. Crucially, the classic BM25 algorithm outperformed modern dense retrieval models, challenging a core assumption in semantic search. The findings provide actionable, cost-aware guidance for building retrieval systems over heterogeneous documents.
Add Semantic Search to Claude Code with pmem: A Local RAG That Cuts Token Costs 75%
Install pmem, a local RAG MCP server, to give Claude Code instant semantic search over your entire project's history, slashing token usage for file retrieval.
Mediagenix Enhances Content Personalization with AI Semantic Search for Better Discovery
Media technology company Mediagenix has integrated AI-powered semantic search into its content management platform to improve content discovery and personalization for broadcasters and media companies. This represents a practical application of embedding technology in the media sector.
DoorDash Builds DashCLIP for Semantic Search Using 32 Million Labels
DoorDash has developed DashCLIP, a custom multimodal embedding model trained on 32 million proprietary labels to align images, text, and user queries for semantic search. This represents a significant move away from generic models for a critical e-commerce function.
Uber Eats Details Production System for Multilingual Semantic Search Across Stores, Dishes, and Items
Uber Eats engineers published a paper detailing their production semantic retrieval system that unifies search across stores, dishes, and grocery items using a fine-tuned Qwen2 model. The system leverages Matryoshka Representation Learning to serve multiple embedding sizes and shows substantial recall gains across six markets.
GameMatch AI Proposes LLM-Powered Identity Layer for Semantic Search in Recommendations
A new Medium article introduces GameMatch AI, a system that uses an LLM to create a user identity layer from descriptive paragraphs, aiming to move beyond click-based recommendations. The concept suggests a shift towards understanding user intent and identity for more personalized discovery.
Andrej Karpathy's Personal Knowledge Management System Uses LLM Embeddings Without RAG for 400K-Word Research Base
AI researcher Andrej Karpathy has developed a personal knowledge management system that processes 400,000 words of research notes using LLM embeddings rather than traditional RAG architecture. The system enables semantic search, summarization, and content generation directly from his Obsidian vault.
Beyond Cosine Similarity: How Embedding Magnitude Optimization Can Transform Luxury Search & Recommendation
New research reveals that controlling embedding magnitude—not just direction—significantly boosts retrieval and RAG performance. For luxury retail, this means more accurate product discovery, personalized recommendations, and enhanced clienteling through superior semantic search.
How Weaviate Agent Skills Let Claude Code Build Vector Apps in Minutes
Weaviate's official Agent Skills give Claude Code structured access to vector databases, eliminating guesswork when building semantic search and RAG applications.
New Research: ADC-SID Framework Improves Semantic ID Generation by Denoising Collaborative Signals
A new arXiv paper proposes ADC-SID, a framework that adaptively denoises collaborative information to create more robust Semantic IDs for recommender systems. It specifically addresses the corruption of long-tail item representations, a critical problem for large retail catalogs.
GateSID: A New Framework for Adaptive Cold-Start Recommendation Using Semantic IDs
Researchers propose GateSID, an adaptive gating framework that dynamically balances semantic and collaborative signals for cold-start items. It uses hierarchical Semantic IDs and adaptive attention to improve recommendations, showing +2.6% GMV in online tests.
KARMA: Alibaba's Framework for Bridging the Knowledge-Action Gap in LLM-Powered Personalized Search
Alibaba researchers propose KARMA, a framework that regularizes LLM fine-tuning for personalized search by preventing 'semantic collapse.' Deployed on Taobao, it improved key metrics and increased item clicks by +0.5%.
Brittlebench Framework Quantifies LLM Robustness, Finds Semantics-Preserving Perturbations Degrade Performance Up to 12%
Researchers introduce Brittlebench, a framework to measure LLM sensitivity to prompt variations. Applying semantics-preserving perturbations to standard benchmarks degrades model performance by up to 12% and alters model rankings in 63% of cases.
VLM4Rec: A New Approach to Multimodal Recommendation Using Vision-Language Models for Semantic Alignment
A new research paper proposes VLM4Rec, a framework that uses large vision-language models to convert product images into rich, semantic descriptions, then encodes them for recommendation. It argues semantic alignment matters more than complex feature fusion, showing consistent performance gains.
98× Faster LLM Routing Without a Dedicated GPU: Technical Breakthrough for vLLM Semantic Router
New research presents a three-stage optimization pipeline for the vLLM Semantic Router, achieving 98× speedup and enabling long-context classification on shared GPUs. This solves critical memory and latency bottlenecks for system-level LLM routing.
Building Semantic Product Recommendation Systems with Two-Tower Embeddings
A technical guide explains how to implement a two-tower neural network architecture for product recommendations, creating separate embeddings for users and items to power similarity search and personalized ads. This approach moves beyond simple collaborative filtering to semantic understanding.
StyleGallery: A Training-Free, Semantic-Aware Framework for Personalized Image Style Transfer
Researchers propose StyleGallery, a novel diffusion-based framework for image style transfer that addresses key limitations: semantic gaps, reliance on extra constraints, and rigid feature alignment. It enables personalized customization from arbitrary reference images without requiring model training.
Multi-TAP: A New Framework for Cross-Domain Recommendation Using Semantic Persona Modeling
Researchers propose Multi-TAP, a cross-domain recommendation framework that models intra-domain user preference heterogeneity through semantic personas. It selectively transfers knowledge between domains, outperforming existing methods on real-world datasets.
How Semantic AI Bridges Threat Intelligence to Automated Firewall Defense
Researchers propose a neuro-symbolic AI system that automatically converts cyber threat intelligence into firewall rules using semantic relationships. The approach leverages hypernym-hyponym relations to extract actionable security information, outperforming traditional methods.
Semantic Caching: The Key to Affordable, Real-Time AI for Luxury Clienteling
Semantic caching for LLMs reuses responses to similar customer queries, cutting API costs by 20-40% and slashing response times. This makes deploying AI-powered personal assistants and search at scale financially viable for luxury brands.
The Hidden Contamination Crisis: How Semantic Duplicates Are Skewing AI Benchmark Results
New research reveals that LLM training data contains widespread 'soft contamination' through semantic duplicates of benchmark test data, artificially inflating performance metrics and raising questions about genuine AI capability improvements.
New Research Proposes DITaR Method to Defend Sequential Recommenders
Researchers propose DITaR, a dual-view method to detect and rectify harmful fake orders embedded in user sequences. It aims to protect recommendation integrity while preserving useful data, showing superior performance in experiments. This addresses a critical vulnerability in e-commerce and retail AI systems.
Walmart Research Proposes Unified Training for Sponsored Search Retrieval
A new arXiv preprint details Walmart's novel bi-encoder training framework for sponsored search retrieval. It addresses the limitations of using user engagement as a sole training signal by combining graded relevance labels, retrieval priors, and engagement data. The method outperformed the production system in offline and online tests.
New Research: How Online Marketplaces Can Use Demand Allocation to Control Seller Inventory
Researchers propose a model where a marketplace platform, by controlling the timing and predictability of order allocation to sellers, can influence their safety-stock inventory and their choice to use platform fulfillment services. This identifies demand allocation as a key operational lever for digital marketplaces.
How Claude Code's Tool Search Saves 90% of Your Context Window
Tool search automatically defers MCP tool definitions, replacing them with a single search tool that loads tools on-demand, preserving your context window for actual work.
Dell's Agentic AI Strategy Prioritizes Enterprise Search Over Commerce
A report suggests Dell is prioritizing agentic AI for enterprise search applications over direct commerce. This reflects a pragmatic approach to deploying autonomous AI agents where they can deliver immediate operational value before tackling complex consumer transactions.
Snapchat Details Production Use of Semantic IDs for Recommender Systems
A technical paper from Snapchat details their application of Semantic IDs (SIDs) in production recommender systems. SIDs are ordered lists of codes derived from item semantics, offering smaller cardinality and semantic clustering than atomic IDs. The team reports overcoming practical challenges to achieve positive online metrics impact in multiple models.
BM25: The 30-Year-Old Algorithm Still Powering Production Search
A viral technical thread details why BM25, a 30-year-old statistical ranking algorithm, is still foundational for search. It argues for its continued use, especially in hybrid systems with vector search, for precise keyword matching.
Stanford and Harvard Researchers Publish Significant AI Safety Paper on Mechanistic Interpretability
Researchers from Stanford and Harvard have published a notable AI paper focusing on mechanistic interpretability and AI safety, with implications for understanding and securing advanced AI systems.