Claims Browser

LLM outputs are treated as authoritative even when they are ungrounded or incorrect

"fluent, confident outputs are treated as authoritative even when ungrounded or incorrect"

A systematic review of 122 primary studies plus 12 regulatory documents reveals four persistent gaps in LLM accountability frameworks

"of 4,512 records identified, 122 primary studies were included, together with 12 regulatory and standards documents analysed as primary sources"

Current LLM accountability frameworks suffer from under-specification of human oversight

"Four persistent gaps emerge: under-specification of human oversight, absence of shared accountability metrics, disciplinary disconnection, and limited empirical evaluation"

There is an absence of shared accountability metrics for LLMs across the field

"absence of shared accountability metrics"

GASHE (Gradient-Aware Selective Homomorphic Encryption) dynamically encrypts only gradient components exceeding a DP-calibrated sensitivity threshold, improving efficiency over uniform encryption schemes

"GASHE (Gradient-Aware Selective Homomorphic Encryption), a novel selective encryption strategy that dynamically identifies and encrypts only the gradient components exceeding a DP-calibrated sensitivity threshold, rather than encrypting all parameters uniformly as in static layer-based or full-parameter CKKS schemes"

SecureDrive-FL creates the first closed-loop DP+HE privacy pipeline by coupling DP-SGD with GASHE, unifying training-time privacy and communication-time confidentiality

"SecureDrive-FL, a federated driver monitoring framework that couples DP-SGD with GASHE to create the first closed-loop DP+HE privacy pipeline: DP-SGD calibration parameters directly derive the GASHE encryption mask, unifying training-time privacy and communication-time confidentiality"

SecureDrive-FL matches DP-SGD's poisoning resistance while additionally protecting against MitM attacks with only 8-10% runtime overhead

"SecureDrive-FL matches DP-SGD alone's poisoning resistance (73.6% vs. 74.0% accuracy, 3.9% Attack Success Rate for both) while additionally withstanding MitM interception, where DP-SGD alone collapses to near-random accuracy (78.2% vs. 10.4%), all under only approx. 8--10% additional runtime overhead relative to DP-SGD alone"

Gradient updates in federated learning remain vulnerable to Man-in-the-Middle interception and model poisoning attacks

"gradient updates remain exploitable: Man-in-the-Middle (MitM) interception exposes updates in transit, while model poisoning corrupts global convergence"

Reliable medical conversational AI requires authentic expert-patient interaction data, but such datasets are scarce for low-resource languages like Bengali

"Reliable medical conversational AI requires authentic expert--patient interaction data, yet such datasets remain scarce, especially for low-resource languages such as Bengali."

DocTalkBN preserves spontaneity, contextual richness, and spoken characteristics of authentic medical interactions unlike prior resources from forums, written content, or synthetic data

"Unlike prior resources derived from medical forums, written health content, or synthetic data, our dataset preserves the spontaneity, contextual richness, and spoken characteristics of authentic medical interactions in a low-resource setting."

DocTalkBN is a practically useful resource, particularly for clinically grounded reasoning tasks

"Our results show that DocTalkBN is a practically useful resource, particularly for clinically grounded reasoning tasks."

The DocTalkBN dataset will facilitate future research on reliable medical NLP and safer, more culturally grounded healthcare systems for low-resource languages

"We release this resource to facilitate future research on reliable medical NLP and safer, more culturally grounded healthcare systems for low-resource languages."

Post-composing a fixed number of pairwise distinct nonconstant polynomials with a generic polynomial of sufficiently large degree yields linearly independent polynomials

"post-composing a fixed number of pairwise distinct nonconstant polynomials with a generic polynomial of sufficiently large degree yields linearly independent polynomials"

The conjecture on polynomial composition generalizes Newman-Slater's theorem on powers of polynomials

"This generalizes Newman--Slater's theorem on powers of polynomials"

The polynomial composition conjecture has been proven for two polynomials and for an arbitrary number of polynomials when their degrees are bounded

"We prove the result for two polynomials, and for an arbitrary number of polynomials when their degrees are bounded"

The polynomial composition conjecture implies a complete understanding of the identifiability of deep fully connected neural network architectures with generic polynomial activation functions

"the conjecture implies a complete understanding of the identifiability (i.e., parameter symmetries) of deep fully connected neural network architectures with generic polynomial activation functions"

For neural network architectures with layer-specific activations of increasing degree, the established versions of the conjecture fully characterize the set of parameters yielding the same end-to-end network function

"for network architectures with layer-specific activations of increasing degree, our established versions of the conjecture fully characterize the set of parameters yielding the same end-to-end network function"

The identifiability of shallow polynomial networks has been fully resolved

"we fully resolve the identifiability of shallow polynomial networks"