Related papers: Do Localization Methods Actually Localize Memorize…
Over-parameterized deep neural networks are able to achieve excellent training accuracy while maintaining a small generalization error. It has also been found that they are able to fit arbitrary labels, and this behaviour is referred to as…
Rapid integration of large language models (LLMs) into societal applications has intensified concerns about their alignment with universal ethical principles, as their internal value representations remain opaque despite behavioral…
Large language model (LLM) evaluation is increasingly costly, prompting interest in methods that speed up evaluation by shrinking benchmark datasets. Benchmark prediction (also called efficient LLM evaluation) aims to select a small subset…
Localization is the problem of estimating the location of an autonomous agent from an observation and a map of the environment. Traditional methods of localization, which filter the belief based on the observations, are sub-optimal in the…
Large language models (LLMs) have been widely adopted in various downstream task domains. However, their abilities to directly recall and apply factual medical knowledge remains under-explored. Most existing medical QA benchmarks assess…
Model editing has recently emerged as a popular paradigm for efficiently updating knowledge in LLMs. A central desideratum of updating knowledge is to balance editing efficacy, i.e., the successful injection of target knowledge, and…
We address the problem of visual place recognition with perceptual changes. The fundamental problem of visual place recognition is generating robust image representations which are not only insensitive to environmental changes but also…
Many applications of large language models (LLMs) require long-context understanding, but models continue to struggle with such tasks. We hypothesize that conventional next-token prediction training could contribute to this, because each…
Pre-trained Language Models (PLMs) are trained on vast unlabeled data, rich in world knowledge. This fact has sparked the interest of the community in quantifying the amount of factual knowledge present in PLMs, as this explains their…
Large language models (LLMs) have enabled a range of applications in zero-shot and few-shot learning settings, including the generation of synthetic datasets for training and testing. However, to reliably use these synthetic datasets, it is…
Robotic path planning problems are often NP-hard, and practical solutions typically rely on approximation algorithms with provable performance guarantees for general cases. While designing such algorithms is challenging, formally proving…
Generative models have recently been explored for synthesizing neural network weights. These approaches take neural network checkpoints as training data and aim to generate high-performing weights during inference. In this work, we examine…
Large Language Models (LLMs) demonstrate remarkable capabilities in question answering (QA), but metrics for assessing their reliance on memorization versus retrieval remain underdeveloped. Moreover, while finetuned models are…
Recent advances in Large Language Models (LLMs) have enhanced text-based recommendation by enriching traditional ID-based methods with semantic generalization capabilities. Text-based methods typically encode item textual information via…
Representing continuous time is a critical and under-explored challenge in modeling temporal event sequences with large language models (LLMs). Various strategies like byte-level representations or calendar tokens have been proposed.…
Recent breakthroughs in computer vision make use of large deep neural networks, utilizing the substantial speedup offered by GPUs. For applications running on limited hardware, however, high precision real-time processing can still be a…
Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. Prior research on decoding methods, primarily focusing on task-specific models, may not extend to the current…
Large language models (LLMs) regularly demonstrate new and impressive performance on a wide range of language, knowledge, and reasoning benchmarks. Such rapid progress has led many commentators to argue that LLM general cognitive…
The use of LLMs for natural language processing has become a popular trend in the past two years, driven by their formidable capacity for context comprehension and learning, which has inspired a wave of research from academics and industry…
The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks responsible for specific task behaviors. In this work, we…