How do chatbots handle election-related questions? We've analyzed over 600,000 responses from four major language models (GPT-3.5, GPT-4o, Gemini, and Copilot). While there were some positive developments, our research revealed several issues. Read the full report:
algorithmwatch.org/en/llms_stat...
algorithmwatch.org/en/llms_stat...
@algorithmwatch.bsky.social ending 2024 with a new LLMs & elections report. Also a test of DSA 40.4 Data Access - we even got data!
Key points in thread 👇 (while travelling so maybe installments). Was quite a process, so lots to say!
@clarahelming.bsky.social
algorithmwatch.org/en/llms_stat...
Key points in thread 👇 (while travelling so maybe installments). Was quite a process, so lots to say!
@clarahelming.bsky.social
algorithmwatch.org/en/llms_stat...
December 21, 2024 at 4:52 AM