Related papers: Addressing Topic Leakage in Cross-Topic Evaluation…
Numerical voice impression (VI) control (e.g., scaling brightness) enables fine-grained control in text-to-speech (TTS). However, it faces two challenges: no public corpus and impression leakage, where reference audio biases synthesized…
From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a…
The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific data. This undermines the validity of benchmark evaluations,…
Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended…
We study a distributed binary hypothesis testing (HT) problem with communication and security constraints, involving three parties: a remote sensor called Alice, a legitimate decision centre called Bob, and an eavesdropper called Eve, all…
Determining semantic similarity between academic documents is crucial to many tasks such as plagiarism detection, automatic technical survey and semantic search. Current studies mostly focus on semantic similarity between concepts,…
Detecting false information on social media is critical in mitigating its negative societal impacts. To reduce the propagation of false information, automated detection provide scalable, unbiased, and cost-effective methods. However, there…
Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…
Authorship attribution aims to identify the author of a text based on the stylometric analysis. Authorship obfuscation, on the other hand, aims to protect against authorship attribution by modifying a text's style. In this paper, we…
Speaker de-identification aims to conceal a speaker's identity while preserving intelligibility of the underlying speech. We introduce a benchmark that quantifies residual identity leakage with three complementary error rates: equal error…
Content moderation faces a challenging task as social media's ability to spread hate speech contrasts with its role in promoting global connectivity. With rapidly evolving slang and hate speech, the adaptability of conventional deep…
This paper is mainly concerned with the question of how to decompose multiclass classification problems into binary subproblems. We extend known Jensen-Shannon bounds on the Bayes risk of binary problems to hierarchical multiclass problems…
Chatbots have the risk of generating offensive utterances, which must be avoided. Post-deployment, one way for a chatbot to continuously improve is to source utterance/label pairs from feedback by live users. However, among users are…
The proliferation of news media outlets has increased the demand for intelligent systems capable of detecting redundant information in news articles in order to enhance user experience. However, the heterogeneous nature of news can lead to…
As a cross-modal task, visual storytelling aims to generate a story for an ordered image sequence automatically. Different from the image captioning task, visual storytelling requires not only modeling the relationships between objects in…
Recent research has highlighted a key issue in speech deepfake detection: models trained on one set of deepfakes perform poorly on others. The question arises: is this due to the continuously improving quality of Text-to-Speech (TTS)…
Systematic literature reviews (SLRs) are fundamental to evidence-based research, but manual screening is an increasing bottleneck as scientific output grows. Screening features low prevalence of relevant studies and scarce, costly expert…
This paper tackles the problem of detecting abrupt changes in the mean of a heteroscedastic signal by model selection, without knowledge on the variations of the noise. A new family of change-point detection procedures is proposed, showing…
The responses generated by Large Language Models (LLMs) can include sensitive information from individuals and organizations, leading to potential privacy leakage. This work implements Influence Functions (IFs) to trace privacy leakage back…
Knowledge-to-text generators often struggle to faithfully generate descriptions for the input facts: they may produce hallucinations that contradict the input, or describe facts not present in the input. To reduce hallucinations, we propose…