McNemar p
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference
arXiv:2606.08098v1 Announce Type: new Abstract: Majority voting over sampled answers is the dominant unsupervised aggregator for multi-sample LLM inference. We show that piping the signals every sample carries into a delegation-based aggregator (Propagational Proxy Voting, PPV) yields an unsupervised consensus rule that beats majority on MMLU-Pro by +1.5 pp overall and +2.24 pp on the non-trivial subset (paired McNemar p ~ 1.0e-14, n = 8,099).
Capacity, Not Format: Rethinking Structured Reasoning Failures
Announce Type: new Abstract: Prior work treats structured output as a reasoning tax, but this framing is incomplete: the cost of formatting depends strongly on a model's spare capacity. Using information-matched prose controls and a four-level schema complexity gradient, we separate format-specific effects from prompt-length confounds across 4 models and 5 benchmarks with 0% parse failures on successfully generated responses.
Hierarchical Online Prompt Mutation with Dual-Loop Feedback for Guardrailed Evidence Document Generation: A Production-Evaluation Case Study
arXiv:2606.01472v1 Announce Type: new Abstract: High-stakes production document-generation systems require language models to be adaptive, evidence-grounded, and auditable. We present HOPM, a hierarchical online prompt mutation framework evaluated on a real marketplace dispute-evidence workflow. HOPM treats prompts as online policies: a family/version router selects a prompt, deterministic guardrails attribute failures to mutable prompt-token categories, and dual feedback from human review...
How we index images for RAG
How we index images for RAG Reading the screenshots, diagrams and tables in technical documentation for LLMs by Matteo Bortoletto Kapa builds AI assistants that answer questions from technical documentation. The knowledge bases we process hold millions of images: screenshots, architecture diagrams, circuit schematics, annotated UI walkthroughs. We spent several months working out how to make them useful in our RAG pipeline.
AutoTail-BSFGM: Class-Balance-Aware Fine-Tuning for Chinese Scholarly Text Classification
arXiv:2606.03576v1 Announce Type: new Abstract: Scholarly text classification supports literature organization, subject indexing, and research intelligence, but Chinese scholarly corpora often contain imbalanced and semantically adjacent disciplinary labels. We propose AutoTail-BSFGM, a class-balance-aware fine-tuning method that combines an automatically gated tail-prior adjustment, a weak Balanced Softmax auxiliary loss, and Fast Gradient Method adversarial regularization. The method...
AutoTail-BSFGM: Class-Balance-Aware Fine-Tuning for Chinese Scholarly Text Classification
arXiv:2606.03576v2 Announce Type: replace Abstract: Scholarly text classification supports literature organization, subject indexing, and research intelligence, but Chinese scholarly corpora often contain imbalanced and semantically adjacent disciplinary labels. We propose AutoTail-BSFGM, a class-balance-aware fine-tuning method that combines an automatically gated tail-prior adjustment, a weak Balanced Softmax auxiliary loss, and Fast Gradient Method adversarial regularization. The method...
AEGIS: A Backup Reflex for Physical AI
Announce Type: new Abstract: Long-horizon robot manipulation tends to fail gradually: one bad step degrades the state, and the policy spirals into a basin from which it cannot recover. The failure is often visible before it happens. We introduce AEGIS (Activation-probe Early-warning, Gated Inference Switching), a selective escalation method that uses a lightweight probe on a weak policy's frozen activations to detect high-risk steps while there is still time to act.