25 citations · 53 across the 7 of their papers we have counts for
3 papers · 1 filter
Information Discernment in Large Language Models
Joshua Ashkinaze, Laura Kurek, Alina Faisal +4
LLMs are increasingly used with external knowledge sources like the internet. Do they weigh information appropriately -- updating more for reliable sources (source discernment) and…
Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences
Joshua Ashkinaze, Hua Shen, Saipranav Avula +2
We introduce the Deep Value Benchmark (DVB), an evaluation framework that directly tests whether large language models (LLMs) learn fundamental human values or merely surface-level…
Prompt Design Matters for Computational Social Science Tasks but in Unpredictable Ways
Shubham Atreja, Joshua Ashkinaze, Lingyao Li +2
Manually annotating data for computational social science tasks can be costly, time-consuming, and emotionally draining. While recent work suggests that LLMs can perform such annot…