LLM self-reports predict behavior selectively: TPB reaches human-level coherence within shared conversations but collapses across sessions for primed behaviors, unlike Big 5, with persona prompting stabilizing reports but not actions.
Leiva, and Ioannis Arapakis
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
PaperFlow proposes a Profiling-Recommending-Adapting framework for longitudinal scientific paper recommendation and evaluates it on a new user-day benchmark with 24 simulated users, outperforming five baselines in ranking, behavioral alignment, and blind human evaluation.
An experiment finds that overreliance on chatbots persists in hybrid AI-plus-web-search setups and is driven primarily by user characteristics rather than answer properties, with warmth increasing agreement on incorrect answers.
AllSERP enriches the AdSERP corpus with per-element bounding boxes, thirteen semantic types, typed gap-filling, and 91.7% click attribution while shipping the full pipeline and viewer for reproducibility.
citing papers explorer
-
AllSERP: Exhaustive Per-Element Enrichment of the Versatile AdSERP Dataset
AllSERP enriches the AdSERP corpus with per-element bounding boxes, thirteen semantic types, typed gap-filling, and 91.7% click attribution while shipping the full pipeline and viewer for reproducibility.