GitHub

uqlm: Uncertainty Quantification for Language Models

UQLM provides a suite of response-level scorers for quantifying the uncertainty of Large Language Model (LLM) outputs. Each scorer returns a confidence score between 0 and 1, where higher scores ...
Unite.AI

Easy Rewording Breaks AI Safety, Even for Gemini and Claude

AI safety tests found to rely on 'obvious' trigger words; with easy rephrasing, models labeled 'reasonably safe' suddenly fail, with attacks succeeding up to 98% of the time. New corporate research ...
GitHub

Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

If you prefer a managed hosted solution check out tadata.com. FastAPI-MCP is designed as a native extension of FastAPI, not just a converter that generates MCP tools from your API. This approach ...

SUDF Introduces Digital Recovery Standards (DRS) to Guide Government and Insurers to Verified Digital Recovery Platforms

A new third-party certification program establishes requirements for HIPAA, 42 CFR Part 2, clinical quality, patient ...
IEEE

On the Dependability of Bidirectional Encoder Representations from Transformers (BERT) to Soft Errors

Abstract: Transformers are widely used in natural language processing and computer vision, and Bidirectional Encoder Representations from Transformers (BERT) is one of the most popular pre-trained ...
IEEE

Fully Quantized Matrix Arithmetic-Only BERT Model and Its FPGA-Based Accelerator

Abstract: In this paper, we propose a fully quantized matrix arithmetic-only BERT (FQ MA-BERT) model to enable efficient natural language processing. Conventionally, the BERT model relies on floating ...