Related papers: Evaluating Sentence-Level Relevance Feedback for H…
A common way to extend the memory of large language models (LLMs) is by retrieval augmented generation (RAG), which inserts text retrieved from a larger memory into an LLM's context window. However, the context window is typically limited…
Evaluation of QA systems is very challenging and expensive, with the most reliable approach being human annotations of correctness of answers for questions. Recent works (AVA, BEM) have shown that transformer LM encoder based similarity…
If we cannot inspect the training data of a large language model (LLM), how can we ever know what it has seen? We believe the most compelling evidence arises when the model itself freely reproduces the target content. As such, we propose…
Large-scale generative language and vision-language models (LLMs and VLMs) excel in few-shot learning but require high-quality demonstrations. We propose In-Context Abstraction Learning (ICAL), enabling VLM agents to transform suboptimal…
Continual learning aims to learn a sequence of tasks by leveraging the knowledge acquired in the past in an online-learning manner while being able to perform well on all previous tasks, this ability is crucial to the artificial…
Supporting longer context for Large Language Models (LLM) is a promising direction to advance LLMs. As training a model for a longer context window is computationally expensive, many alternative solutions, such as Retrieval Augmented…
Acquiring new knowledge without forgetting what has been learned in a sequence of tasks is the central focus of continual learning (CL). While tasks arrive sequentially, the training data are often prepared and annotated independently,…
Augmenting Large Language Models (LLMs) with information retrieval capabilities (i.e., Retrieval-Augmented Generation (RAG)) has proven beneficial for knowledge-intensive tasks. However, understanding users' contextual search intent when…
Due to the privacy protection or the difficulty of data collection, we cannot observe individual outputs for each instance, but we can observe aggregated outputs that are summed over multiple instances in a set in some real-world…
Recent advances in reinforcement learning for large language models have converged on increasing complexity: multi-stage training pipelines, dynamic hyperparameter schedules, and curriculum learning strategies. This raises a fundamental…
Recent advancements in Large Language Models (LLMs) have significantly improved reasoning capabilities, with in-context learning (ICL) emerging as a key technique for adaptation without retraining. While previous works have focused on…
As large language models (LLMs) become increasingly versatile, numerous large scale benchmarks have been developed to thoroughly assess their capabilities. These benchmarks typically consist of diverse datasets and prompts to evaluate…
Active Learning (AL) is a human-in-the-loop framework to interactively and adaptively label data instances, thereby enabling significant gains in model performance compared to random sampling. AL approaches function by selecting the hardest…
Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a novel active learning approach that utilizes self-supervised…
Modern speech processing systems rely on self-attention. Unfortunately, token mixing with self-attention takes quadratic time in the length of the speech utterance, slowing down inference and training and increasing memory consumption.…
Retrieval-augmented generation (RAG) is a key technique for leveraging external knowledge and reducing hallucinations in large language models (LLMs). However, RAG still struggles to fully prevent hallucinated responses. To address this, it…
Deep learning has profoundly impacted domains such as computer vision and natural language processing by uncovering complex patterns in vast datasets. However, the reliance on extensive labeled data poses significant challenges, including…
A systematic review identifies and collates various clinical studies and compares data elements and results in order to provide an evidence based answer for a particular clinical question. The process is manual and involves lot of time. A…
System-oriented IR evaluations are limited to rather abstract understandings of real user behavior. As a solution, simulating user interactions provides a cost-efficient way to support system-oriented experiments with more realistic…
"High Quality Related Search Query Suggestions" task aims at recommending search queries which are real, accurate, diverse, relevant and engaging. Obtaining large amounts of query-quality human annotations is expensive. Prior work on…