Themis
PulseAugur coverage of Themis — every cluster mentioning Themis across labs, papers, and developer communities, ranked by signal.
- 2026-06-23 research_milestone Researchers published a paper introducing Themis, an explainable AI-enabled framework for Reinforcement Learning with Human Feedback. source
2 day(s) with sentiment data
-
Estonia blames Russia for arson attack on Ukraine-supplying defense firm
Estonia has officially blamed Russia for an arson attack on Milrem Robotics, a defense company that supplies military vehicles to Ukraine. The attack, which occurred in mid-August, is considered an act of sabotage commi…
-
New research details auditable LLM-based software repair workflow
A new research paper introduces THEMIS, a workflow designed to make the process of repairing software bugs using large language models more transparent and auditable. This system externalizes requirement-to-repair artif…
-
LLM-as-a-Judge evaluation methods face scrutiny over reliability and bias · 4 sources tracked
Recent research is raising concerns about the reliability of Large Language Models (LLMs) when used as judges for evaluating AI-generated text. Studies indicate that LLM judges may rely too heavily on the rubric itself,…
-
Themis framework combines AI explainability with human feedback for safer RL
Researchers have introduced Themis, a novel framework designed to enhance the safety and transparency of Reinforcement Learning (RL) systems by integrating explainability with human feedback. This framework aims to addr…