中文
相关论文

相关论文: A Hierarchical Imprecise Probability Approach to R…

200 篇论文

The widespread adoption of large language models (LLMs) makes it important to recognize their strengths and limitations. We argue that in order to develop a holistic understanding of these systems we need to consider the problem that they…

计算与语言 · 计算机科学 2023-09-26 R. Thomas McCoy , Shunyu Yao , Dan Friedman , Matthew Hardy , Thomas L. Griffiths

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks in various domains. Despite their impressive performance, they can be unreliable due to factual errors in their generations. Assessing their…

计算与语言 · 计算机科学 2024-03-26 Jiahui Geng , Fengyu Cai , Yuxia Wang , Heinz Koeppl , Preslav Nakov , Iryna Gurevych

(Renyi Qu's Master's Thesis) Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from…

计算机视觉与模式识别 · 计算机科学 2024-06-04 Renyi Qu , Mark Yatskar

Large Language Models (LLMs) have the impressive ability to perform in-context learning (ICL) from only a few examples, but the success of ICL varies widely from task to task. Thus, it is important to quickly determine whether ICL is…

计算与语言 · 计算机科学 2023-10-27 Harvey Yiyun Fu , Qinyuan Ye , Albert Xu , Xiang Ren , Robin Jia

Large Language Models (LLMs) exhibit strong performance across various natural language processing (NLP) tasks but remain vulnerable to hallucinations, generating factually incorrect or misleading outputs. Uncertainty estimation, often…

机器学习 · 计算机科学 2025-11-12 Manh Nguyen , Sunil Gupta , Hung Le

Large Language Models (LLMs) based on the pre-trained fine-tuning paradigm have become pivotal in solving natural language processing tasks, consistently achieving state-of-the-art performance. Nevertheless, the theoretical understanding of…

机器学习 · 计算机科学 2024-10-02 Jing Luo , Huiyuan Wang , Weiran Huang

An accurate differential diagnosis (DDx) is essential for patient care, shaping therapeutic decisions and influencing outcomes. Recently, Large Language Models (LLMs) have emerged as promising tools to support this process by generating a…

人工智能 · 计算机科学 2025-10-07 Seungseop Lim , Gibaeg Kim , Hyunkyung Lee , Wooseok Han , Jean Seo , Jaehyo Yoo , Eunho Yang

Large Language Models (LLMs) have achieved remarkable success in various fields, prompting several studies to explore their potential in recommendation systems. However, these attempts have so far resulted in only modest improvements over…

信息检索 · 计算机科学 2024-09-20 Junyi Chen , Lu Chi , Bingyue Peng , Zehuan Yuan

Prompt optimization algorithms for Large Language Models (LLMs) excel in multi-step reasoning but still lack effective uncertainty estimation. This paper introduces a benchmark dataset to evaluate uncertainty metrics, focusing on Answer,…

机器学习 · 计算机科学 2024-12-30 Pei-Fu Guo , Yun-Da Tsai , Shou-De Lin

Assessing the effectiveness of large language models (LLMs) in performing different tasks is crucial for understanding their strengths and weaknesses. This paper presents Hierarchical Prompting Taxonomy (HPT), grounded on human cognitive…

计算与语言 · 计算机科学 2025-07-22 Devichand Budagam , Ashutosh Kumar , Mahsa Khoshnoodi , Sankalp KJ , Vinija Jain , Aman Chadha

Large language models (LLMs) are increasingly used in applications requiring factual accuracy, yet their outputs often contain hallucinated responses. While fact-checking can mitigate these errors, existing methods typically retrieve…

计算与语言 · 计算机科学 2026-01-07 Haoran Wang , Maryam Khalid , Qiong Wu , Jian Gao , Cheng Cao

Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict…

机器学习 · 计算机科学 2024-10-31 Yashvir S. Grewal , Edwin V. Bonilla , Thang D. Bui

This work focuses on Hierarchical Inference (HI) in edge intelligence systems, where a compact Local-ML model on an end-device works in conjunction with a high-accuracy Remote-ML model on an edge-server. HI aims to reduce latency, improve…

机器学习 · 计算机科学 2025-12-23 Sameep Chattopadhyay , Vinay Sutar , Jaya Prakash Champati , Sharayu Moharir

Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consistency can become brittle under calibration--deployment…

计算与语言 · 计算机科学 2026-04-20 Yanli Wang , Peng Kuang , Xiaoyu Han , Kaidi Xu , Haohan Wang

Large language models (LLMs) exhibit probabilistic output characteristics, yet conventional evaluation frameworks rely on deterministic scalar metrics. This study introduces a Bayesian approach for LLM capability assessment that integrates…

计算与语言 · 计算机科学 2025-05-01 Xiao Xiao , Yu Su , Sijing Zhang , Zhang Chen , Yadong Chen , Tian Liu

We investigate the predictability of large language model (LLM) capabilities: given records of past experiments using different model families, numbers of parameters, tasks, and numbers of in-context examples, can we accurately predict LLM…

计算与语言 · 计算机科学 2023-11-01 Qinyuan Ye , Harvey Yiyun Fu , Xiang Ren , Robin Jia

Evaluation of large language models (LLMs) is increasingly critical, yet standard benchmarking methods rely on average accuracy, overlooking both the inherent stochasticity of LLM outputs and the heterogeneity of benchmark items. Item…

机器学习 · 统计学 2026-05-11 Xinhao Qu , Qiang Heng , Hao Zeng , Xiaoqian Liu

Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current LLM-based human simulations remain insufficiently reliable, as evidenced by significant…

计算与语言 · 计算机科学 2025-12-02 Qian Wang , Jiaying Wu , Zichen Jiang , Zhenheng Tang , Bingqiao Luo , Nuo Chen , Wei Chen , Bingsheng He

Large language models (LLMs) have exhibited remarkable capabilities across various domains. The ability to call external tools further expands their capability to handle real-world tasks. However, LLMs often follow an opaque reasoning…

Utilizing large language models (LLMs) to achieve role-playing has gained great attention recently. The primary implementation methods include leveraging refined prompts and fine-tuning on role-specific datasets. However, these methods…

人工智能 · 计算机科学 2024-07-30 Libo Sun , Siyuan Wang , Xuanjing Huang , Zhongyu Wei