arXiv Machine Learning July 7, 2026 By Zhichao Fan, Yanhang Li, Zexin Zhuang, Xian Sun, Yingshuo Wang

The Moving Target: A Longitudinal Audit of Trustworthiness Drift Across Twelve Checkpoints of Open-Source Chat LLMs

Read the original on arXiv Machine Learning →

arXiv:2607. 02587v1 Announce Type: cross Abstract: Model cards quote trust-benchmark scores without recording when they were measured, and the same number is routinely carried across successive checkpoints of one release line as if the model behind it had not shifted.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 11

The Moving Target: A Longitudinal Audit of Trust-Benchmark Score Drift Across Open-Source Chat LLM Release Lines

arXiv:2607. 02587v2 Announce Type: replace-cross Abstract: Trust-benchmark scores reported on a chat-LLM release line are often carried across several checkpoints of the same line, as if the underlying model had not shifted between releases.

By Zhichao Fan, Yanhang Li, Zexin Zhuang, Xian Sun, Yingshuo Wang

llms benchmarks

arXiv Machine Learning

Jul 22

HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks

arXiv:2607. 18867v1 Announce Type: new Abstract: Large language models leak parametric knowledge of realized outcomes into historical financial decision tasks.

By Haozhe Jia

llms robotics efficiency

arXiv AI

22h ago

Beyond Suspicious Steps: Ontological Trust in Long-Horizon Agents

arXiv:2608. 17718v1 Announce Type: new Abstract: Long-horizon agents increasingly operate across many steps, tools, and observa- tions.

By An He, Yao Wang, Haibin Zhang

llms agents benchmarks

arXiv AI

Aug 5

BulkPR-Bench: Benchmarking Queue-Level Governance of Interacting Pull Requests

arXiv:2608. 02685v1 Announce Type: cross Abstract: Coding-agent benchmarks increasingly cover long-horizon, end-to-end, and interactive development, but typically retain one requested outcome or a fixed change sequence.

By Zetong Xiong, Qiao Zhao, Jun Zhang, Xueying Lyu, Zhi Li, Yixiang Tu, Xiaowen Yang, Yunjie Zhang, Yufeng Wang, Zhe Zhang, Kaize Yu, Hanwen Du, Zhongkai Sun, Zhuoxin Liu, Zekun Lin, Jianwen Yang, Ruining Chen, Ying Zhang, Tingxuan Pan, Ke Chen, Shubin Han, Chuanhao Sun, Yehua Yang

agents benchmarks safety

arXiv AI

Jun 16

Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines

arXiv:2606. 15474v1 Announce Type: new Abstract: Continuous evaluation of LLM products relies on a strong LLM judge treated as ground truth: a cheap monitor scores every interaction and a team is paged when the score drifts down.

By Yitao Li

llms nlp

arXiv AI

22h ago

The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence

arXiv:2608. 17176v1 Announce Type: cross Abstract: An AI audit record is useful only if its durability and trust boundary are explicit.

By Neeraj Kumar Singh Beshane

efficiency safety

Related stories

The Moving Target: A Longitudinal Audit of Trust-Benchmark Score Drift Across Open-Source Chat LLM Release Lines

HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks

Beyond Suspicious Steps: Ontological Trust in Long-Horizon Agents

BulkPR-Bench: Benchmarking Queue-Level Governance of Interacting Pull Requests

Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines

The Acknowledgment Point Is the System: Durable Policy-Decision Receipts for AI Audit Evidence