2 papers
cs.AI2026
AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs
Yiderigun Borjigin, Alexander Hermann, Christian Cyron +1
The anchoring effect is a cognitive bias in which an initial reference value shifts a later judgment toward itself. This effect is well established in human judgment and decision-m…
cs.LG2026
Synthetic Persona Pretraining: Alignment from Token Zero
Julian Minder, Viktor Moskvoretskii, Raghav Singhal +12
As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and the assistant…