LLM Digest

Story

arxiv_cs_cl · Nov 10, 2026 · paper

Source brief

Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation

arxiv.orgNov 10, 2026
original source linked

In brief

In this paper, we present 1020 Group's submission to the WMT26 shared task on automated quality evaluation. Our system, Pterodactyl, was engineered specifically for subtasks 2 and 3, that is, segment-level quality sco...

Feed lens

evaluation

Read the original at arxiv.org →Open in live feed Read that day’s brief

Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation

Earlier in this thread 4 items

Studying quantization trade-offs for efficient inference deployment in machine translation

C$^2$-Routing: Complementary Cropping and Compression for Efficient Vision-Language Inference

AMSchem: Automated Schematic Visualization of AMS Circuits via Verifiable Agentic Generation

Intent-Aware Caching for Efficient LLM Serving