Tootfinder

FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition
Jongsuk Kim, Jaemyung Yu, Minchan Kwon, Junmo Kim
https://arxiv.org/abs/2506.10747

FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition
Large-scale ASR models have achieved remarkable gains in accuracy and robustness. However, fairness issues remain largely unaddressed despite their critical importance in real-world applications. In this work, we introduce FairASR, a system that mitigates demographic bias by learning representations that are uninformative about group membership, enabling fair generalization across demographic groups. Leveraging a multi-demographic dataset, our approach employs a gradient reversal layer to suppr…

Trump signed an executive order decrying so-called anti-Christian bias in February,
and a hotline was created in April to encourage State Department workers to call in and snitch on their colleagues who might be acting with any kind of “anti-Christian bias.”
The Religious Liberty Commission was established via another executive order on May 1 during a flashy White House event.
Trump has even established his own Christian “faith” office in the White House, seemingly further…

Trump’s ‘anti-Christian bias’ taskforce reveals its propagandistic agenda in first meeting
Even though Christians are the dominant religious group in the country, Trump and his allies are desperate to portray persecution where there is none

This https://arxiv.org/abs/2506.01832 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCC_…

Pseudorandom bits for non-commutative programs
We obtain new explicit pseudorandom generators for several computational models involving groups. Our main results are as follows: 1. We consider read-once group-products over a finite group $G$, i.e., tests of the form $\prod_{i=1}^n g_i^{x_i}$ where $g_i\in G$, a special case of read-once permutation branching programs. We give generators with optimal seed length $c_G \log(n/\varepsilon)$ over any $p$-group. The proof uses the small-bias plus noise paradigm, but derandomizes the noise to av…

Social Group Bias in AI Finance
Thomas R. Cook, Sophia Kazinnik
https://arxiv.org/abs/2506.17490 https://arxiv.org/pdf/2506.17490

Social Group Bias in AI Finance
Financial institutions increasingly rely on large language models (LLMs) for high-stakes decision-making. However, these models risk perpetuating harmful biases if deployed without careful oversight. This paper investigates racial bias in LLMs specifically through the lens of credit decision-making tasks, operating on the premise that biases identified here are indicative of broader concerns across financial applications. We introduce a reproducible, counterfactual testing framework that evalua…

Pseudorandom bits for non-commutative programs
Chin Ho Lee, Emanuele Viola
https://arxiv.org/abs/2506.01832 https://arxiv.org/pdf/250…

Pseudorandom bits for non-commutative programs
We obtain new explicit pseudorandom generators for several computational models involving groups. Our main results are as follows: 1. We consider read-once group-products over a finite group $G$, i.e., tests of the form $\prod_{i=1}^n g_i^{x_i}$ where $g_i\in G$, a special case of read-once permutation branching programs. We give generators with optimal seed length $c_G \log(n/\varepsilon)$ over any $p$-group. The proof uses the small-bias plus noise paradigm, but derandomizes the noise to av…

This https://arxiv.org/abs/2410.08948 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMA_…

Emergent social conventions and collective bias in LLM populations
Social conventions are the backbone of social coordination, shaping how individuals form a group. As growing populations of artificial intelligence (AI) agents communicate through natural language, a fundamental question is whether they can bootstrap the foundations of a society. Here, we present experimental results that demonstrate the spontaneous emergence of universally adopted social conventions in decentralized populations of large language model (LLM) agents. We then show how strong coll…