相关论文: Zero-Shot Belief: A Hard Problem for LLMs

Recent advances in multimodal language models (MLLMs) have made thinking with images a dominant paradigm for multimodal reasoning. However, existing methods still fail to ensure evidence-answer consistency, where correct answers must be…

Zero-shot textual explanations aim to make image classifiers more transparent by probing their internal representations, without relying on task-specific supervision or LVLMs. However, existing methods often miss the features that truly…

Large language models (LLMs) have showcased impressive multilingual machine translation ability. However, unlike encoder-decoder style models, decoder-only LLMs lack an explicit alignment between source and target contexts. Analyzing…

We compare various forms of prompts to represent event types and develop a unified framework to incorporate the event type specific prompts for supervised, few-shot, and zero-shot event detection. The experimental results demonstrate that a…

Fact tracing seeks to identify specific training examples that serve as the knowledge source for a given query. Existing approaches to fact tracing rely on assessing the similarity between each training sample and the query along a certain…

Today, the training of large language models (LLMs) can involve personally identifiable information and copyrighted material, incurring dataset misuse. To mitigate the problem of dataset misuse, this paper explores \textit{dataset…

Verifying and attributing factual claims is essential for the safe and effective use of large language models (LLMs) in healthcare. A core component of factuality evaluation is fact decomposition, the process of breaking down complex…

Financial news plays a central role in shaping investor sentiment and short-term dynamics in commodity markets. Many downstream financial applications, such as commodity price prediction or sentiment modeling, therefore rely on the ability…

This paper investigates Distributed Hypothesis testing (DHT), in which a source $\mathbf{X}$ is encoded given that side information $\mathbf{Y}$ is available at the decoder only. Based on the received coded data, the receiver aims to decide…

The proliferation of financial misinformation poses a severe threat to market stability and investor trust, misleading market behavior and creating critical information asymmetry. Detecting such misleading narratives is inherently…

Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading…

The increasing fluency and widespread usage of large language models (LLMs) highlight the desirability of corresponding tools aiding detection of LLM-generated text. In this paper, we identify a property of the structure of an LLM's…

Human annotators frequently disagree on emotion labels, yet most evaluations of Large Language Model (LLM) emotion annotation collapse these judgments into a single gold standard, discarding the distributional information that disagreement…

In this paper, we focus on the challenging task of reliably estimating factual knowledge that is embedded inside large language models (LLMs). To avoid reliability concerns with prior approaches, we propose to eliminate prompt engineering…

Autonomous vehicles need precise knowledge on dynamic objects in their surroundings. Especially in urban areas with many objects and possible occlusions, an infrastructure system based on a multi-sensor setup can provide the required…

LLMs are increasingly used as long-running conversational agents, yet every major benchmark evaluating their memory treats user information as static facts to be stored and retrieved. That's the wrong model. People change their minds, and…

Large Language Models (LLMs) often provide chain-of-thought (CoT) reasoning traces that appear plausible, but may hide internal biases. We call these *unverbalized biases*. Monitoring models via their stated reasoning is therefore…

High-Energy Physics experiments are facing a multi-fold data increase with every new iteration. This is certainly the case for the upcoming High-Luminosity LHC upgrade. Such increased data processing requirements forces revisions to almost…

LLM-based approaches have recently achieved impressive results in zero-shot stance detection. However, they still struggle in complex real-world scenarios, where stance understanding requires dynamic background knowledge, target definitions…

Performing knowledge transfer from a large teacher network to a smaller student is a popular task in modern deep learning applications. However, due to growing dataset sizes and stricter privacy regulations, it is increasingly common not to…