Related papers: Handling the Alignment for Wake Word Detection: A …

Real-world machine learning applications often struggle with two major challenges: distribution shift and label noise. Models tend to overfit by focusing on redundant and uninformative features in the training data, which makes it hard for…

We propose a practical approach based on federated learning to solve out-of-domain issues with continuously running embedded speech-based models such as wake word detectors. We conduct an extensive empirical study of the federated averaging…

Large language model (LLM) alignment algorithms typically consist of post-training over preference pairs. While such algorithms are widely used to enable safety guardrails and align LLMs with general human preferences, we show that…

The field of artificial intelligence (AI) alignment aims to investigate whether AI technologies align with human interests and values and function in a safe and ethical manner. AI alignment is particularly relevant for large language models…

Wakeup is the primary function in voice interaction which is the mainstream scheme in man-machine interaction (HMI) applications for smart home. All devices will response if the same wake-up word is used for all devices. This will bring…

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and…

Cross-lingual word embeddings aim to bridge the gap between high-resource and low-resource languages by allowing to learn multilingual word representations even without using any direct bilingual signal. The lion's share of the methods are…

Large language models (LLMs) undergo safety alignment to ensure safe conversations with humans. However, this paper introduces a training-free attack method capable of reversing safety alignment, converting the outcomes of stronger…

Multimodal Large Language Models (MLLMs) have shown strong performance in multi-image cross-modal retrieval, yet suffer from severe position bias, where predictions are dominated by input order rather than semantic relevance. Through…

In recent years, the accuracy of automatic lyrics alignment methods has increased considerably. Yet, many current approaches employ frameworks designed for automatic speech recognition (ASR) and do not exploit properties specific to music.…

Image-text retrieval is a widely studied topic in the field of computer vision due to the exponential growth of multimedia data, whose core concept is to measure the similarity between images and text. However, most existing retrieval…

In this paper we describe an algorithm for aligning sentences with their translations in a bilingual corpus using lexical information of the languages. Existing efficient algorithms ignore word identities and consider only the sentence…

We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF). Our main idea is to exploit knowledge…

Models of acoustic word embeddings (AWEs) learn to map variable-length spoken word segments onto fixed-dimensionality vector representations such that different acoustic exemplars of the same word are projected nearby in the embedding…

Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…

Prompt Tuning has emerged as a prominent research paradigm for adapting vision-language models to various downstream tasks. However, recent research indicates that prompt tuning methods often lead to overfitting due to limited training…

We demonstrate that explicitly aligning the pretraining objectives to the finetuning objectives in language model training significantly improves the finetuning task performance and reduces the minimum amount of finetuning examples…

Reinforcement learning has seen wide success in finetuning large language models to better align with instructions via human feedback. The so-called algorithm, Reinforcement Learning with Human Feedback (RLHF) demonstrates impressive…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

Uncertainty estimation remains a key challenge when adapting pre-trained language models to downstream classification tasks, with overconfidence often observed for difficult inputs. While predictive entropy provides a strong baseline for…