Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study
Large language models are increasingly evaluated through the values they endorse, but such evaluations presuppose that models can identify the value expressed in a concrete situation. We study this prerequisite as controlled top-1 recognition over Schwartz's ten basic values. Our evaluation set contains 1,000 Russian situational texts, balanced across the ten values and independently labeled by two human annotators per item. We evaluate 21 instruction-tuned LLM runs under a fixed ranked-response protocol; 20 runs with reliable outputs form the semantic panel. Pooled Acc@1 is 0.683 and Acc@3 is
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 53%Identifying Interactions at Scale for LLMs →
- LinkedLinked via arxiv author · 85%Andrei Chetvergov →
“Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study”
- LinkedLinked via arxiv author · 85%Stepan Ukolov →
“Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study”
- LinkedLinked via arxiv author · 85%Timofei Sivoraksha →
“Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study”
- LinkedLinked via arxiv author · 85%Alexander Evseev →
“Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study”
- LinkedLinked via arxiv author · 85%Mikhail Solovev →
“Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study”
- LinkedLinked via arxiv author · 85%Valeriia Kuschenko →
“Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study”
- LinkedLinked via arxiv author · 85%Maria Chistyakova →
“Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study”