中文
相关论文

相关论文: Clarify, Abstain or Answer? Strategising in Conver…

200 篇论文

Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external evidence, but it also introduces knowledge conflicts when retrieved contextual knowledge (CK) and parametric knowledge (PK) disagree or are…

信息检索 · 计算机科学 2026-05-20 Xi Zhu , Ziqi Wang , Kai Mei , Wujiang Xu , Minghao Guo , Bangji Yang , Jiajun Fan , Dimitris N. Metaxas

Retrieval-Augmented Generation (RAG) is the prevailing paradigm for grounding Large Language Models (LLMs), yet the mechanisms governing how models integrate groups of conflicting retrieved evidence remain opaque. Does an LLM answer a…

人工智能 · 计算机科学 2026-01-13 Atharv Naphade

Large language models (LLMs) have been proposed as alternatives to human experts for estimating unknown quantities with associated uncertainty, a process known as Bayesian elicitation. We test this by asking eleven LLMs to estimate…

人工智能 · 计算机科学 2026-04-03 Luka Hobor , Mario Brcic , Mihael Kovac , Kristijan Poje

Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks, yet they still struggle to reliably verify the correctness of their own outputs. Existing solutions to this verification challenge often…

计算与语言 · 计算机科学 2025-06-13 Yuhua Jiang , Yuwen Xiong , Yufeng Yuan , Chao Xin , Wenyuan Xu , Yu Yue , Qianchuan Zhao , Lin Yan

Large Language Models (LLMs) can produce surprisingly sophisticated estimates of their own uncertainty. However, it remains unclear to what extent this expressed confidence is tied to the reasoning, knowledge, or decision making of the…

机器学习 · 计算机科学 2026-01-13 Jiawei Wang , Yanfei Zhou , Siddartha Devic , Deqing Fu

Large Language Models (LLMs) have demonstrated exceptional capabilities, yet selecting the most reliable response from multiple LLMs remains a challenge, particularly in resource-constrained settings. Existing approaches often depend on…

Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer). This weakness is even evident in temporal question answering, where models frequently…

计算与语言 · 计算机科学 2026-03-05 Xinyu Zhou , Chang Jin , Carsten Eickhoff , Zhijiang Guo , Seyed Ali Bahrainian

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

While large language models (LLMs) are proficient at question-answering (QA), it is not always clear how (or even if) an answer follows from their latent "beliefs". This lack of interpretability is a growing impediment to widespread use of…

计算与语言 · 计算机科学 2023-10-31 Nora Kassner , Oyvind Tafjord , Ashish Sabharwal , Kyle Richardson , Hinrich Schuetze , Peter Clark

Large Language Models (LLMs) often exhibit knowledge disparities across languages. Encouraging LLMs to \textit{abstain} when faced with knowledge gaps is a promising strategy to reduce hallucinations in multilingual settings. Current…

计算与语言 · 计算机科学 2025-06-04 Yuxi Sun , Aoqi Zuo , Wei Gao , Jing Ma

Large language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We study whether post-training can make a model's self-assessment explicit: when the model is…

机器学习 · 计算机科学 2026-05-15 Junyu Guo , Shangding Gu , Ming Jin , Costas Spanos , Javad Lavaei

In recent years, Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations? A popular concept, referred to as self-refinement, postulates that LLMs can detect and…

Retrieval-augmented generation (RAG) improves Large Language Models (LLMs) by incorporating external information into the response generation process. However, how context-faithful LLMs are and what factors influence LLMs' context…

计算与语言 · 计算机科学 2025-07-11 Yuepei Li , Kang Zhou , Qiao Qiao , Bach Nguyen , Qing Wang , Qi Li

Recently, Large Language Models (LLMs) have been increasingly used to support various decision-making tasks, assisting humans in making informed decisions. However, when LLMs confidently provide incorrect information, it can lead humans to…

信息检索 · 计算机科学 2025-10-16 Chaeyun Jang , Deukhwan Cho , Seanie Lee , Hyungi Lee , Juho Lee

Large language models (LLMs) can produce erroneous responses that sound fluent and convincing, raising the risk that users will rely on these responses as if they were correct. Mitigating such overreliance is a key challenge. Through a…

人机交互 · 计算机科学 2025-02-13 Sunnie S. Y. Kim , Jennifer Wortman Vaughan , Q. Vera Liao , Tania Lombrozo , Olga Russakovsky

This paper considers the challenges Large Language Models (LLMs) face when reasoning over text that includes information involving uncertainty explicitly quantified via probability values. This type of reasoning is relevant to a variety of…

计算与语言 · 计算机科学 2024-12-30 Aliakbar Nafar , Kristen Brent Venable , Parisa Kordjamshidi

Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), where computational constraints and autonomous operation…

人工智能 · 计算机科学 2026-05-26 Ashwath Vaithinathan Aravindan , Mayank Kejriwal

Although large language models (LLMs) are highly interactive and extendable, current approaches to ensure reliability in deployments remain mostly limited to rejecting outputs with high uncertainty in order to avoid misinformation. This…

机器学习 · 计算机科学 2025-06-10 T. Duy Nguyen-Hien , Desi R. Ivanova , Yee Whye Teh , Wee Sun Lee

Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. However, these explanations can misrepresent the model's "reasoning" process, i.e., they can be unfaithful. This,…

计算与语言 · 计算机科学 2025-05-21 Katie Matton , Robert Osazuwa Ness , John Guttag , Emre Kıcıman

Despite widespread success in language understanding and generation, large language models (LLMs) exhibit unclear and often inconsistent behavior when faced with tasks that require probabilistic reasoning. In this work, we present the first…

‹ 上一页 1 2 3 10 下一页 ›