Authority Bias in Conversational Search Engines for Academic Paper Recommendation

Name: Authority Bias in Conversational Search Engines for Academic Paper Recommendation
Uploaded: 2026-09-08T06:56:27.979658+00:00
Duration: 625 s
Description: The episode analyzes 'Authority Bias in Conversational Search Engines for Academic Paper Recommendation,' finding that LLMs significantly favor high-prestige academic papers regardless of content. Hosts conclude this bias is systemic, driven primarily by venue prestige, and cannot be fixed simply by prompting the AI to 'be fair.'

The episode analyzes 'Authority Bias in Conversational Search Engines for Academic Paper Recommendation,' finding that LLMs significantly favor high-prestige academic papers regardless of content. Hosts conclude this bias is systemic, driven primarily by venue prestige, and cannot be fixed simply by prompting the AI to 'be fair.'

Open the full episode