中文
相关论文

相关论文: A CAP-like Trilemma for Large Language Models: Cor…

200 篇论文

One of the long-standing goals in optimisation and constraint programming is to describe a problem in natural language and automatically obtain an executable, efficient model. Large language models appear to bring this vision closer,…

人工智能 · 计算机科学 2025-11-20 Alessio Pellegrino , Jacopo Mauro

This paper investigates the influence of cognitive biases on Large Language Models (LLMs) outputs. Cognitive biases, such as confirmation and availability biases, can distort user inputs through prompts, potentially leading to unfaithful…

计算与语言 · 计算机科学 2025-06-17 Yan Sun , Stanley Kok

Advances in the general capabilities of large language models (LLMs) have led to their use for information retrieval, and as components in automated decision systems. A faithful representation of probabilistic reasoning in these models may…

人工智能 · 计算机科学 2025-04-21 Gabriel Freedman , Francesca Toni

Large language models (LLMs) are a promising venue for natural language understanding and generation tasks. However, current LLMs are far from reliable: they are prone to generate non-factual information and, more crucially, to contradict…

机器学习 · 计算机科学 2024-04-22 Diego Calanzone , Stefano Teso , Antonio Vergari

With the widespread application of Large Language Models (LLMs) to various domains, concerns regarding the trustworthiness of LLMs in safety-critical scenarios have been raised, due to their unpredictable tendency to hallucinate and…

计算与语言 · 计算机科学 2024-11-04 Xin Qiu , Risto Miikkulainen

Large Language Models (LLMs) are expected to be predictable and trustworthy to support reliable decision-making systems. Yet current LLMs often show inconsistencies in their judgments. In this work, we examine logical preference consistency…

计算与语言 · 计算机科学 2025-02-11 Yinhong Liu , Zhijiang Guo , Tianya Liang , Ehsan Shareghi , Ivan Vulić , Nigel Collier

As large language models (LLMs) grow more capable, they face increasingly diverse and complex tasks, making reliable evaluation challenging. The paradigm of LLMs as judges has emerged as a scalable solution, yet prior work primarily focuses…

计算与语言 · 计算机科学 2025-11-03 Weiyuan Li , Xintao Wang , Siyu Yuan , Rui Xu , Jiangjie Chen , Qingqing Dong , Yanghua Xiao , Deqing Yang

Large language models (LLMs) have rapidly become indispensable tools for acquiring information and supporting human decision-making. However, ensuring that these models uphold fairness across varied contexts is critical to their safe and…

计算机与社会 · 计算机科学 2026-03-05 Xulang Zhang , Rui Mao , Erik Cambria

This essay proposes an interpretive analogy between large language models (LLMs) and quasicrystals, systems that exhibit global coherence without periodic repetition, generated through local constraints. While LLMs are typically evaluated…

计算与语言 · 计算机科学 2025-04-22 Jose Manuel Guevara-Vela

While large language models (LLMs) have demonstrated remarkable capabilities in language modeling, recent studies reveal that they often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training.…

机器学习 · 计算机科学 2025-06-12 Shurui Gui , Shuiwang Ji

The widespread adoption of Large Language Models (LLMs) has become commonplace, particularly with the emergence of open-source models. More importantly, smaller models are well-suited for integration into consumer devices and are frequently…

计算与语言 · 计算机科学 2024-08-16 Aisha Khatun , Daniel G. Brown

Language models (LMs) are increasingly used as simulacra for people, yet their ability to match the distribution of views of a specific demographic group and be \textit{distributionally aligned} remains uncertain. This notion of…

计算与语言 · 计算机科学 2024-11-11 Nicole Meister , Carlos Guestrin , Tatsunori Hashimoto

As Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks, concerns regarding the potential negative societal impacts of LLM-generated content have also arisen. To evaluate the…

计算与语言 · 计算机科学 2025-02-25 Song Wang , Peng Wang , Tong Zhou , Yushun Dong , Zhen Tan , Jundong Li

Large language models (LLMs) exhibit outstanding performance in machine translation via in-context learning. In contrast to sentence-level translation, document-level translation (DOCMT) by LLMs based on in-context learning faces two major…

计算与语言 · 计算机科学 2024-06-12 Menglong Cui , Jiangcun Du , Shaolin Zhu , Deyi Xiong

Integrating segmentation into Multimodal Large Language Models (MLLMs) presents a core trilemma: simultaneously preserving dialogue ability, achieving high segmentation performance, and ensuring fast inference. Prevailing paradigms are…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Jiazhen Liu , Mingkuan Feng , Long Chen

As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may correct itself and produce the correct answer. Unfortunately,…

人机交互 · 计算机科学 2024-05-10 Yoonjoo Lee , Kihoon Son , Tae Soo Kim , Jisu Kim , John Joon Young Chung , Eytan Adar , Juho Kim

Large language model (LLM) evaluations often assume there is a single correct response -- a gold label -- for each item in the evaluation corpus. However, some tasks can be ambiguous -- i.e., they provide insufficient information to…

机器学习 · 计算机科学 2024-11-22 Luke Guerdan , Hanna Wallach , Solon Barocas , Alexandra Chouldechova

In-context learning (ICL) has emerged as a particularly remarkable characteristic of Large Language Models (LLM): given a pretrained LLM and an observed dataset, LLMs can make predictions for new data points from the same distribution…

机器学习 · 统计学 2024-06-04 Fabian Falck , Ziyu Wang , Chris Holmes

The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability. Despite strong performance, these models are often treated as black boxes, with limited systematic investigation of their…

机器学习 · 计算机科学 2026-05-13 Konstantinos P. Panousis , Diego Marcos

The conformity bias exhibited by large language models (LLMs) can pose a significant challenge to decision-making in LLM-based multi-agent systems (LLM-MAS). While many prior studies have treated "conformity" simply as a matter of opinion…

人工智能 · 计算机科学 2026-04-22 Mikako Bito , Keita Nishimoto , Kimitaka Asatani , Ichiro Sakata