Showing cs.CYShow all
2 papers · 1 filter
cs.CY2025
Only a Little to the Left: A Theory-grounded Measure of Political Bias in Large Language Models
Mats Faulborn, Indira Sen, Max Pellert +2
Prompt-based language models like GPT4 and LLaMa have been used for a wide variety of use cases such as simulating agents, searching for information, or for content analysis. For a…
cs.CY2025
Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models
Georg Ahnert, Max Pellert, David Garcia +1
This paper proposes temporally aligned Large Language Models (LLMs) as a tool for longitudinal analysis of social media data. We fine-tune Temporal Adapters for Llama 3 8B on full…