JB
Jan Batzner
cs.CLcs.AIcs.CY
On Valency
published · living versionsW_dm5xu66x·v1 · currentpublished
Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use
with Yijiang River Dong, Zexue He, Cheng Yu, Tiancheng Hu +7
1 version
Preprints & journals
11 papers in the corpus · 2024–2026Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use2610.31272v1 · Yijiang River Dong, Zexue He, Cheng Yu et al.2026 · 0 citationsarXivon Valency
Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results2606.14516v1 · Jan Batzner, Sree Harsha Nelaturu, Damian Stachura et al.2026 · 0 citationsarXiv
Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting2606.09809v2 · Avijit Ghosh, Anka Reuel, Jenny Chim et al.2026 · 0 citationsarXiv
Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure2604.25580v2 · David Hartmann, Manuel Tonneau, Angelie Kraft et al.2026 · 0 citationsarXiv
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation2602.16763v4 · Mubashara Akhtar, Anka Reuel, Prajna Soni et al.2026 · 2 citationsarXiv
Agent Benchmarks Fail Public Sector Requirements2601.20617v1 · Jonathan Rystr\om, Chris Schmitz, Karolina Korgul et al.2026 · 0 citationsarXiv
One Persona, Many Cues, Different Results: How Sociodemographic Cues Impact LLM Personalization2601.18572v3 · Franziska Weeber, Vera Neplenbroek, Jan Batzner et al.2026 · 0 citationsarXiv
Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency2512.00461v1 · Jan Batzner, Volker Stocker, Bingjun Tang et al.2025 · 3 citationsProceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 8(1), 2025, 343-354
Sycophancy Claims about Language Models: The Missing Human-in-the-Loop2512.00656v1 · Jan Batzner, Volker Stocker, Stefan Schmid et al.2025 · 0 citationsarXiv
Measuring what Matters: Construct Validity in Large Language Model Benchmarks2511.04703v1 · Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou et al.2025 · 7 citationsarXiv
GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy2407.18008v2 · Jan Batzner, Volker Stocker, Stefan Schmid et al.2024 · 4 citationsProceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 8(1), 2025, pp. 330-342
Career total: 17 works. 11 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.