Related papers: APE: Selective Fine-tuning with Acceptance Criteri…
Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models (LLMs) by employing a fast draft model to propose candidate token sequences and a large target model to verify them in…
The capabilities of Large Language Models (LLMs) are limited to some extent by pre-training, so some researchers optimize LLMs through post-training. Existing post-training strategies, such as memory-based retrieval or preference…
Large Language Models (LLMs) have so far impressed the world, with unprecedented capabilities that emerge in models at large scales. On the vision side, transformer models (i.e., ViT) are following the same trend, achieving the best…
Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and…
While Reinforcement Learning (RL) agents can successfully learn to handle complex tasks, effectively generalizing acquired skills to unfamiliar settings remains a challenge. One of the reasons behind this is the visual encoders used are…
As MT quality increases, interest in enhanced post-editing features such as QE-derived error highlights is growing, yet evidence for their usefulness remains limited. In this work, we explore the usefulness of LLM-derived error highlights…
Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…
Recent works have revealed the great potential of speculative decoding in accelerating the autoregressive generation process of large language models. The success of these methods relies on the alignment between draft candidates and the…
Covering all languages with a multilingual speech recognition model (MASR) is very difficult. Performing language extension on top of an existing MASR is a desirable choice. In this study, the MASR continual learning problem is…
The growing sophistication of Business Email Compromise (BEC) and spear phishing attacks poses significant challenges to organizations worldwide. The techniques featured in traditional spam and phishing detection are insufficient due to the…
Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…
Large pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive generalization but remain highly vulnerable to adversarial examples (AEs). Previous work has explored robust text prompts through adversarial training,…
Large-scale pretrained models have proven immensely valuable in handling data-intensive modalities like text and image. However, fine-tuning these models for certain specialized modalities, such as protein sequence and cosmic ray, poses…
We propose Partially Interpretable Estimators (PIE) which attribute a prediction to individual features via an interpretable model, while a (possibly) small part of the PIE prediction is attributed to the interaction of features via a…
Machine learning techniques lend themselves as promising decision-making and analytic tools in a wide range of applications. Different ML algorithms have various hyper-parameters. In order to tailor an ML model towards a specific…
The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity…
Automatic Term Extraction (ATE) identifies domain-specific expressions that are crucial for downstream tasks such as machine translation and information retrieval. Although large language models (LLMs) have significantly advanced various…
We propose a new, more general approach to the design of stochastic gradient-based optimization methods for machine learning. In this new framework, optimizers assume access to a batch of gradient estimates per iteration, rather than a…
Aspect Sentiment Triplet Extraction (ASTE) aims to extract the triplet of an aspect term, an opinion term, and their corresponding sentiment polarity from the review texts. Due to the complexity of language and the existence of multiple…
Vision-Language Models (VLMs), such as CLIP, have achieved significant zero-shot performance on downstream tasks with various fine-tuning adaptation methods. However, recent studies have proven that adversarial attacks can significantly…