An experimental search reranking technique that replaces single relevance queries with LLM-generated question rubrics, scoring documents by summing probability scores across multiple yes/no questions tailored to each query.

p(yes) is a great mental model for decision models.

An AI-powered scheduling app that helps attendees plan their AWS re:Invent week by converting natural language queries into session filters and automatically suggesting talks based on location, interests, and available time gaps.

A comprehensive guide tracing the history of text classification techniques from traditional bag-of-words and logistic regression through RNNs, CNNs, and Transformers, examining how modern models like Jev balance generality, speed, and cost for classification tasks.

A framework that enhances LLM-based recommendation systems with explicit reasoning capabilities through item-textual alignment, reasoning scaffolding, and recommendation-specific reward functions, validated on public benchmarks and deployed at scale on Kuaishou.

This paper describes GLIDE, a production-scale generative recommender system that uses Semantic IDs and large language models to balance user preferences with exploration in podcast discovery. The system addresses challenges in catalog grounding, personalization, and serving latency while achieving significant improvements in non-habitual listening through large-scale A/B testing.

PLUM is a framework that adapts pre-trained large language models for recommendation systems at scale, using semantic IDs for item tokenization, continued pre-training on domain-specific data, and generative retrieval fine-tuning. The approach demonstrates significant improvements over production models on video recommendation tasks and has been deployed to billions of YouTube users.

Netflix's GenRec system leverages large language models to power native recommendations, representing a shift toward LLM-based approaches in content discovery and personalization.

Marc Brooker describes building Hobson, a 2-billion parameter classifier optimized for accuracy and calibration at low latency, by fine-tuning a pre-trained LLM with a pointer head instead of a language modeling head to score multiple choice answers.

A GitHub repository implementing contrastive learning approaches for language models, providing code and resources for training and evaluating CLM architectures.

LLMs used as classifiers have significant limitations like poor calibration and difficulty incorporating structured data, but treating LLM outputs as features for traditional ML models like logistic regression can overcome these constraints.

A technique for fine-tuning the Qwen 4B language model to optimize SQL query plans using reinforcement learning, achieving 81% faster execution than Postgres's default planner.

Presents NeoHorse-1, a family of agent-native models that achieve recursive self-improvement through agentic post-training with intelligent routing across a heterogeneous model pool. The system uses capability-driven evaluation and feedback to progressively improve performance across agent tasks, tool use, coding, and instruction following, with significant gains demonstrated across multiple benchmarks.

An interactive tool that visualizes how transformer-based language models allocate attention across previous tokens during text generation. Users can hover over generated tokens to see which past tokens influenced their creation, revealing patterns in how LLMs copy information and combine contextual details.