相关论文: Mind the Shift: Decoding Monetary Policy Stance fr…

Entropy-based confidence signals are increasingly leveraged to improve reasoning in large language models (LLMs), yet existing approaches treat confidence as a static quantity -- typically aggregated over tokens. We show that the…

We pose the research question, "Can LLMs provide credible evaluation scores, suitable for constructing starter MCDM models that support commencing deliberation regarding climate and sustainability policies?" In this exploratory study we i.…

Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific…

Large language models (LLMs) demand considerable computational, energy, and financial resources during both training and deployment. While scaling laws for training have guided much of the field's recent progress, inference costs now…

Diffusion large language models (dLLMs) have emerged as a new architecture following auto regressive models. Their denoising process offers a powerful generative advantage, but they present significant challenges in learning and…

Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this…

Large Language Models (LLMs) often generate responses with inherent biases, undermining their reliability in real-world applications. Existing evaluation methods often overlook biases in long-form responses and the intrinsic variability of…

The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from preference data. This involves building datasets where each…

Taken traditionally as a no-go theorem against the theorization of inductive processes, Duhem-Quine thesis may interfere with the essence of statistical inference. This difficulty can be resolved by Micro-Macro duality \cite{Oj03, Oj05}…

Self-consistency with chain-of-thought prompting (CoT) has demonstrated remarkable performance gains on various challenging tasks, by utilizing multiple reasoning paths sampled from large language models (LLMs). However, self-consistency…

Producing trustworthy and reliable Large Language Models (LLMs) has become increasingly important as their usage becomes more widespread. Calibration seeks to achieve this by improving the alignment between the model's confidence and the…

When large language models (LLMs) are asked to perform certain tasks, how can we be sure that their learned representations align with reality? We propose a domain-agnostic framework for systematically evaluating distribution shifts in LLMs…

Text analysis of tabular data relies on two core operations: \emph{summarization} for corpus-level theme extraction and \emph{tagging} for row-level labeling. A critical limitation of employing large language models (LLMs) for these tasks…

With the remarkable development of large language models (LLMs), ensuring the factuality of output has become a challenge. However, having all the contents of the response with given knowledge or facts is not necessarily a good thing in…

Localization transitions represent a fundamental class of continuous phase transitions, yet they occur without any accompanying symmetry breaking. We resolve this by introducing the concept of dynamical translational symmetry (DTS), which…

Recent studies evaluate the value orientation of large language models (LLMs) using adapted social surveys, typically by prompting models with survey questions and comparing their responses to average human responses. This paper identifies…

A decade of rapid advances in artificial intelligence (AI) has opened new opportunities for clinical decision support systems (CDSS), with large language models (LLMs) demonstrating strong reasoning abilities on timely medical tasks.…

Large Language Models (LLMs) exhibit remarkable fluency and competence across various natural language tasks. However, recent research has highlighted their sensitivity to variations in input prompts. To deploy LLMs in a safe and reliable…

Text-based automated Cognitive Distortion detection is a challenging task due to its subjective nature, with low agreement scores observed even among expert human annotators, leading to unreliable annotations. We explore the use of Large…

Language model outputs are not always reliable, thus prompting research into how to adapt model responses based on uncertainty. Common approaches include: \emph{abstention}, where models refrain from generating responses when uncertain; and…