AI Briefing#classification
The latest AI and developer news about #classification, with the original source and a short summary.
The latest AI and developer news about #classification, with the original source and a short summary.
Decider v1.3 achieves 91.6% average accuracy on 63 classification tasks, outperforming previous production classifiers by 6.54 percentage points.
Kakao's Kanana-2-v-decide-3b-2611 is a decision model that accepts text, JSON, or chat history with optional images to output probabilities for choice, yes/no, or scale-based answers.
The multimodal model returns structured probabilities for classification and routing tasks rather than generating text.
Achieves 0.743 accuracy by performing decisions with a single forward pass of a 27B model
The model requires only an AI Gateway API key, with no separate Azure account or deployment needed.
A Jev-compatible API-based model offering low latency and calibrated probabilities with 0 output tokens
The 2B parameter Jeff model achieves an 83.1% score on a five-benchmark panel, slightly exceeding the published 83.0% score of the larger Jev model.
Jevper, an open-source library that performs Jev classification on OpenAI-compatible APIs, has been released, offering automatic logprobs detection and reasoning model support.
Convai Innovations has open-sourced Laya, a non-autoregressive multilingual decision model that classifies states without text generation.
Combining LLMs as feature extractors rather than final classifiers with logistic regression improves irony detection performance and calibration.
This article introduces an efficient technique that induces hallucinations instead of using structured outputs from LLMs, then performs actual classification via vector similarity.
It presents a methodology for optimizing hardware-specific costs and latency for large-scale classification and embedding workloads.
OpenAI has unveiled a methodology for building an integrated classification system to effectively detect harmful content in real-world environments.