Copertina

When Helpful Context Leaks: Privacy Risks in Domain-Adapted ASR

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Züfle, Maike, Niehues, Jan
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Contrastive Learning for Task-Independent SpeechLLM-Pretraining
di: Züfle, Maike, et al.
Pubblicazione: (2024)

Talk2Ref: A Dataset for Reference Prediction from Scientific Talks
di: Broy, Frederik, et al.
Pubblicazione: (2025)

MuSaG: A Multimodal German Sarcasm Dataset with Full-Modal Annotations
di: Scott, Aaron, et al.
Pubblicazione: (2025)

Beyond Transcripts: A Renewed Perspective on Audio Chaptering
di: Retkowski, Fabian, et al.
Pubblicazione: (2026)

NUTSHELL: A Dataset for Abstract Generation from Scientific Talks
di: Züfle, Maike, et al.
Pubblicazione: (2025)

Early-Exit and Instant Confidence Translation Quality Estimation
di: Zouhar, Vilém, et al.
Pubblicazione: (2025)

Do Slides Help? Multi-modal Context for Automatic Transcription of Conference Talks
di: Sinhamahapatra, Supriti, et al.
Pubblicazione: (2025)

F-Actor: Controllable Conversational Behaviour in Full-Duplex Models
di: Züfle, Maike, et al.
Pubblicazione: (2026)

Multimodal In-context Learning for ASR of Low-resource Languages
di: Li, Zhaolin, et al.
Pubblicazione: (2026)

KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025
di: Koneru, Sai, et al.
Pubblicazione: (2025)

COMET-poly: Machine Translation Metric Grounded in Other Candidates
di: Züfle, Maike, et al.
Pubblicazione: (2025)

Do What I Say: A Spoken Prompt Dataset for Instruction-Following
di: Züfle, Maike, et al.
Pubblicazione: (2026)

Summarizing Speech: A Comprehensive Survey
di: Retkowski, Fabian, et al.
Pubblicazione: (2025)

MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
di: Papi, Sara, et al.
Pubblicazione: (2025)

A Bayesian Optimization Approach to Machine Translation Reranking
di: Cheng, Julius, et al.
Pubblicazione: (2024)

MosaicLeaks:Privacy Risks in Querying-in-the-Open for Deep Research Agents
di: Gurung, Alexander, et al.
Pubblicazione: (2026)

Conditions for Catastrophic Forgetting in Multilingual Translation
di: Liu, Danni, et al.
Pubblicazione: (2025)

Text-to-OverpassQL: A Natural Language Interface for Complex Geodata Querying of OpenStreetMap
di: Staniek, Michael, et al.
Pubblicazione: (2023)

When Do "More Contexts" Help with Sarcasm Recognition?
di: Nimase, Ojas, et al.
Pubblicazione: (2024)

Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs
di: Liu, Danni, et al.
Pubblicazione: (2025)

In-context Language Learning for Endangered Languages in Speech Recognition
di: Li, Zhaolin, et al.
Pubblicazione: (2025)

How Transferable are Attribute Controllers on Pretrained Multilingual Translation Models?
di: Liu, Danni, et al.
Pubblicazione: (2023)

Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach
di: Li, Siqi, et al.
Pubblicazione: (2024)

When Benchmarks Leak: Inference-Time Decontamination for LLMs
di: Chai, Jianzhe, et al.
Pubblicazione: (2026)

ContextLeak: Auditing Leakage in Private In-Context Learning Methods
di: Choi, Jacob, et al.
Pubblicazione: (2025)

When Does Context Help? Error Dynamics of Contextual Information in Large Language Models
di: Wang, Dingzirui, et al.
Pubblicazione: (2026)

When Does Monolingual Data Help Multilingual Translation: The Role of Domain and Model Scale
di: Baziotis, Christos, et al.
Pubblicazione: (2023)

Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
di: Lee, Jinsook, et al.
Pubblicazione: (2026)

TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent
di: Meier, Dominik, et al.
Pubblicazione: (2025)

Sigmoid Head for Quality Estimation under Language Ambiguity
di: Dinh, Tu Anh, et al.
Pubblicazione: (2026)

Are Generative Models Underconfident? Better Quality Estimation with Boosted Model Probability
di: Dinh, Tu Anh, et al.
Pubblicazione: (2025)

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
di: Patil, Vaidehi, et al.
Pubblicazione: (2025)

OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion
di: Koneru, Sai, et al.
Pubblicazione: (2025)

Language-Independent Representations Improve Zero-Shot Summarization
di: Solovyev, Vladimir, et al.
Pubblicazione: (2024)

Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts
di: Parihar, Shweta, et al.
Pubblicazione: (2026)

When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing
di: Dhaini, Mahdi, et al.
Pubblicazione: (2025)

Quality-Aware Decoding: Unifying Quality Estimation and Decoding
di: Koneru, Sai, et al.
Pubblicazione: (2025)

How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations
di: Lee, Hyunji, et al.
Pubblicazione: (2024)

From Slides to Chatbots: Enhancing Large Language Models with University Course Materials
di: Dinh, Tu Anh, et al.
Pubblicazione: (2025)

Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learning
di: Zhang, Yuchen, et al.
Pubblicazione: (2026)