Related papers: Mitigating Temporal Misalignment by Discarding Out…

Scientific reasoning rarely stops at what is directly observable; it often requires uncovering hidden structure from data. From estimating reaction constants in chemistry to inferring demand elasticities in economics, this latent structure…

Through systematic empirical investigation, we uncover a fundamental and concerning property of Large Language Models: while they can safely learn facts that don't contradict their knowledge, attempting to update facts with contradictory…

Language models are prone to hallucination - generating text that is factually incorrect. Finetuning models on high-quality factual information can potentially reduce hallucination, but concerns remain; obtaining factual gold data can be…

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…

Large Language Models (LLMs) encapsulate a surprising amount of factual world knowledge. However, their performance on temporal questions and historical knowledge is limited because they often cannot understand temporal scope and…

Temporal logic rules are often used in control and robotics to provide structured, human-interpretable descriptions of trajectory data. These rules have numerous applications including safety validation using formal methods, constraining…

Foundation models encompass an extensive knowledge base and offer remarkable transferability. However, this knowledge becomes outdated or insufficient over time. The challenge lies in continuously updating foundation models to accommodate…

State-of-the-art models of lexical semantic change detection suffer from noise stemming from vector space alignment. We have empirically tested the Temporal Referencing method for lexical semantic change and show that, by avoiding…

Leveraging contextual knowledge has become standard practice in automated claim verification, yet the impact of temporal reasoning has been largely overlooked. Our study demonstrates that time positively influences the claim verification…

The Internet contains a wealth of knowledge -- from the birthdays of historical figures to tutorials on how to code -- all of which may be learned by language models. However, while certain pieces of information are ubiquitous on the web,…

Reasoning large language models achieve impressive test-time scaling by thinking for longer, but this performance gain comes at significant compute cost. Directly limiting test-time budget hurts overall performance, but not all problems are…

Large language models must balance their weight-encoded knowledge with in-context information from prompts to generate accurate responses. This paper investigates this interplay by analyzing how models of varying capacities within the same…

Large Language Models (LLMs) have revolutionized numerous applications, making them an integral part of our digital ecosystem. However, their reliability becomes critical, especially when these models are exposed to misinformation. We…

Probabilistic forecasting of multivariate time series is essential for various downstream tasks. Most existing approaches rely on the sequences being uniformly spaced and aligned across all variables. However, real-world multivariate time…

End-to-end models in NLP rarely encode external world knowledge about length of time. We introduce two effective models for duration prediction, which incorporate external knowledge by reading temporal-related news sentences (time-aware…

Large Language Models (LLMs) show remarkable proficiency in natural language tasks, yet their frequent overconfidence-misalignment between predicted confidence and true correctness-poses significant risks in critical decision-making…

Large language models have led to significant progress across many NLP tasks, although their massive sizes often incur substantial computational costs. Distillation has become a common practice to compress these large and highly capable…

Released Large Language Models (LLMs) are often paired with a claimed knowledge cutoff date, or the dates at which training data was gathered. Such information is crucial for applications where the LLM must provide up to date information.…

Knowledge Base Question Answering (KBQA) systems have the goal of answering complex natural language questions by reasoning over relevant facts retrieved from Knowledge Bases (KB). One of the major challenges faced by these systems is their…

Despite the recent observation that large language models (LLMs) can store substantial factual knowledge, there is a limited understanding of the mechanisms of how they acquire factual knowledge through pretraining. This work addresses this…