FITRep: Transparent AI to De-duplicate Lookalike Items

Kari Jaaskelainen

27 Nov 2025 — 1 min read

Duplicate and lookalike items clutter online feeds and ads, hurting user experience.

FITRep is an attention-guided, white-box way to represent items for fine-grained deduplication. Inspired by Feature Integration Theory, it teaches Multimodal LLMs to separate what’s primary from what’s auxiliary—so structures don’t collapse into one vague embedding.

CHIE: extracts a hierarchy of semantic concepts from text + visuals.
SPDR: an adaptive, UMAP-based reduction that preserves structure while compressing.
FBC: FAISS-powered clustering that assigns each item a stable, unique cluster ID.

Deployed in Meituan’s ad system, FITRep lifted CTR by +3.60% and CPM by +4.25% in online A/B tests—cleaner feeds, better matching, real revenue impact.

Bottom line: fewer near-duplicates, clearer item meaning, and faster, scalable clustering—without the black-box guesswork.

Paper: https://arxiv.org/abs/2511.21389v1

Register: https://www.AiFeta.com

#MLLM #RecommenderSystems #InformationRetrieval #Deduplication #AdTech #UMAP #FAISS #CTR #CPM #AI #Meituan

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A