arXiv AI
Proxy reliance in large language model decisions is uncalibrated to predictive evidence
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
2d ago
Proxy reliance in large language model decisions is uncalibrated to predictive evidence
Large language models (LLMs) are entering decisions in triage and lending, where task-relevant inference must be distinguished from impermissible proxy use. Current audits ask whether decisions change...
arXiv AI
Jun 30
The strength of clinical evidence is recoverable from language model representations but not from their stated grades
arXiv:2606. 29034v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly summarize clinical evidence, where a claim's weight depends on how strongly it is supported.
arXiv Machine Learning
Jul 7
Faithfulness to Refusal: A Causal Audit of Neuron Selectors
arXiv:2607. 05355v1 Announce Type: cross Abstract: Attribution scores increasingly identify which neuron rows of a language model matter for applications such as pruning, interpretability, and editing for safety, yet whether they identify causally important rows is rarely tested directly.
arXiv AI
Jun 17
Statistical Foundations of LLM-based A/B Testing: A Surrogacy Framework for Human Causal Inference
arXiv:2606. 17165v1 Announce Type: cross Abstract: Organizations and researchers show increasing interest in using large language models (LLMs) in place of human participants in A/B tests, in the hope of experimenting faster and at lower cost.
arXiv AI
2d ago
Who Do Language Models Think Is Competent? A Mechanistic Analysis of Occupational Bias
The paper investigates whether language models still encode occupational biases even when they appear unbiased in behavioral tests. Using a causal framework, the authors separate bias into internal representations of user competence and observable outputs, deriving steering vectors that show these representations influence model behavior in question‑answering and hiring tasks. Across several open‑weight models, demographic factors such as gender, race, and socioeconomic status affect the models’ internal competence representations, revealing hidden bias that behavioral metrics alone may miss.
arXiv AI
Aug 17
AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs
arXiv:2608. 14320v1 Announce Type: new Abstract: The anchoring effect is a cognitive bias in which an initial reference value shifts a later judgment toward itself.