Related papers: Context is Key: A Benchmark for Forecasting with E…

Long-context modeling capabilities have garnered widespread attention, leading to the emergence of Large Language Models (LLMs) with ultra-context windows. Meanwhile, benchmarks for evaluating long-context LLMs are gradually catching up.…

Temporal reasoning and planning are essential capabilities for large language models (LLMs), yet most existing benchmarks evaluate them in isolation and under limited forms of complexity. To address this gap, we introduce the Temporal…

Motion prediction is among the most fundamental tasks in autonomous driving. Traditional methods of motion forecasting primarily encode vector information of maps and historical trajectory data of traffic participants, lacking a…

While most conversational AI systems focus on textual dialogue only, conditioning utterances on visual context (when it's available) can lead to more realistic conversations. Unfortunately, a major challenge for incorporating visual context…

Context engineering has emerged as a pivotal paradigm for unlocking the potential of Large Language Models (LLMs) in Software Engineering (SE) tasks, enabling performance gains at test time without model fine-tuning. Despite its success,…

The fundamental challenge of using Large Language Models (LLMs) for reliable, enterprise-grade analytics, such as sentiment prediction, is the conflict between the LLMs' inherent stochasticity (generative, non-deterministic nature) and the…

Recent advances in natural language processing (NLP) and large language models (LLMs) have enabled the systematic use of large-scale textual data from news, social media, and reports to create datasets with socio-economic impacts of climate…

Navigating health questions can be daunting in the modern information landscape. Large language models (LLMs) may provide tailored, accessible information, but also risk being inaccurate, biased or misleading. We present insights from 4…

We present a new perspective on how readers integrate context during real-time language comprehension. Our proposals build on surprisal theory, which posits that the processing effort of a linguistic unit (e.g., a word) is an affine…

To deliver high-quality, personalized responses, large language models (LLMs) must effectively incorporate context -- personal, demographic, and cultural information specific to an end-user. For example, asking the model to explain Newton's…

Long-context modeling is one of the critical capabilities of language AI for digesting and reasoning over complex information pieces. In practice, long-context capabilities are typically built into a pre-trained language model~(LM) through…

Meta-evaluation of automatic evaluation metrics -- assessing evaluation metrics themselves -- is crucial for accurately benchmarking natural language processing systems and has implications for scientific inquiry, production model…

Editing Large language models (LLMs) with real-world, unstructured knowledge is essential for correcting and updating their internal parametric knowledge. In this work, we revisit the fundamental next-token prediction (NTP) as a candidate…

This paper demonstrates that Semantic Context (SC), leveraging descriptive tool information, is a foundational component for robust tool orchestration. Our contributions are threefold. First, we provide a theoretical foundation using…

Text matching is a fundamental technique in both information retrieval and natural language processing. Text matching tasks share the same paradigm that determines the relationship between two given texts. The relationships vary from task…

Processing and reasoning over long contexts is crucial for many practical applications of Large Language Models (LLMs), such as document comprehension and agent construction. Despite recent strides in making LLMs process contexts with more…

We formalize a new concept for LLMs, context-enhanced learning. It involves standard gradient-based learning on text except that the context is enhanced with additional data on which no auto-regressive gradients are computed. This setting…

The development of Long-Context Large Language Models (LLMs) has markedly advanced natural language processing by facilitating the process of textual data across long documents and multiple corpora. However, Long-Context LLMs still face two…

This paper introduces a novel approach that leverages Large Language Models (LLMs) and Generative Agents to enhance time series forecasting by reasoning across both text and time series data. With language as a medium, our method adaptively…

Large Language Models (LLMs) have made significant strides in handling long sequences. Some models like Gemini could even to be capable of dealing with millions of tokens. However, their performance evaluation has largely been confined to…