-
2025The use of human speech to train LLMs poses privacy concerns due to these models’ ability to generate samples that closely resemble artifacts in the training data. We propose a speaker privacy-preserving representation learning method through the Universal Speech Codec (USC), a computationally efficient codec that disentangles speech into: (i) privacy-preserving semantically rich representations, capturing
-
2025Language localization is the adaptation of written content to different linguistic and cultural contexts. Ability to localize written content is crucial for global businesses to provide consistent and reliable customer experience across diverse markets. Traditional methods have approached localization as an application of machine translation (MT), but localization requires more than linguistic conversion
-
AAAI 2025 Workshop on Preventing and Detecting LLM Misinformation2025Unlearning aims to remove copyrighted, sensitive, or private content from large language models (LLMs) without a full retraining. In this work, we develop a multi-task unlearning benchmark (LUME) which features three tasks: (1) unlearn synthetically generated creative short novels, (2) unlearn synthetic biographies with sensitive information, and (3) unlearn a collection of public biographies. We further
-
NAACL 2025 Workshop on TrustNLP2025Large Language Models (LLMs) have demonstrated excellent capabilities in Question Answering (QA) tasks, yet their ability to identify and address ambiguous questions remains underdeveloped. Ambiguities in user queries often lead to inaccurate or misleading answers, undermining user trust in these systems. Despite prior attempts using prompt-based methods, performance has largely been equivalent to random
-
2025We present MegaBeam-Mistral-7B1, a language model that supports 512K-token context length. Our work addresses practical limitations in long-context training, supporting real-world tasks such as compliance monitoring and verification. Evaluated on three long-context benchmarks, our 7B-parameter model demonstrates superior in-context learning performance on HELMET and robust retrieval and tracing capability
Related content
-
July 2, 2021Giving a neural generation model “control knobs” enables modulation of the content of generated language.
-
July 1, 2021Methods share a two-stage training process in which a model learns a representation from audio data, then learns to predict that representation from text.
-
June 24, 2021The organization focuses on furthering the state of the art on discourse- and dialogue-related technologies.
-
June 17, 2021Combining classic signal processing with deep learning makes method efficient enough to run on a phone.
-
June 16, 2021Watch the replay of the June 15 discussion featuring five Amazon scientists.
-
June 16, 2021Relative to human evaluation of question-answering models, the new method has an error rate of only 7%.