English
Related papers

Related papers: Internal Knowledge Without External Expression: Pr…

200 papers

Language models cannot be random. This paper introduces Entropic Deviation (ED), the normalised KL divergence between a model's token distribution and the uniform distribution, and measures it systematically across 31,200 generations…

Computation and Language · Computer Science 2026-04-28 Jarosław Hryszko

Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may…

Computation and Language · Computer Science 2024-03-05 Collin Burns , Haotian Ye , Dan Klein , Jacob Steinhardt

Large language models (LLMs) demonstrate the capacity to reconstruct and trace learned content from their training data under specific elicitation conditions, yet this capability does not manifest in standard generation contexts. This…

Computation and Language · Computer Science 2026-03-20 Toshiyuki Shigemura

This work presents a framework for assessing whether large language models (LLMs) encode more factual knowledge in their parameters than what they express in their outputs. While a few studies hint at this possibility, none has clearly…

Computation and Language · Computer Science 2025-08-07 Zorik Gekhman , Eyal Ben David , Hadas Orgad , Eran Ofek , Yonatan Belinkov , Idan Szpektor , Jonathan Herzig , Roi Reichart

We study the feasibility of identifying epistemic uncertainty (reflecting a lack of knowledge), as opposed to aleatoric uncertainty (reflecting entropy in the underlying distribution), in the outputs of large language models (LLMs) over…

Machine Learning · Computer Science 2024-02-28 Gustaf Ahdritz , Tian Qin , Nikhil Vyas , Boaz Barak , Benjamin L. Edelman

We present a setup for training, evaluating and interpreting neural language models, that uses artificial, language-like data. The data is generated using a massive probabilistic grammar (based on state-split PCFGs), that is itself derived…

Computation and Language · Computer Science 2023-10-24 Jaap Jumelet , Willem Zuidema

Large Language Models are known to capture real-world knowledge, allowing them to excel in many downstream tasks. Despite recent advances, these models are still prone to what are commonly known as hallucinations, causing them to emit…

Machine Learning · Computer Science 2024-12-10 Roi Cohen , Konstantin Dobler , Eden Biran , Gerard de Melo

While idiosyncrasies of the Chinese classifier system have been a richly studied topic among linguists (Adams and Conklin, 1973; Erbaugh, 1986; Lakoff, 1986), not much work has been done to quantify them with statistical methods. In this…

Computation and Language · Computer Science 2020-05-26 Shijia Liu , Hongyuan Mei , Adina Williams , Ryan Cotterell

We posit that large language models (LLMs) should be capable of expressing their intrinsic uncertainty in natural language. For example, if the LLM is equally likely to output two contradicting answers to the same question, then its…

Computation and Language · Computer Science 2024-09-27 Gal Yona , Roee Aharoni , Mor Geva

Recent NLP tasks have benefited a lot from pre-trained language models (LM) since they are able to encode knowledge of various aspects. However, current LM evaluations focus on downstream performance, hence lack to comprehensively inspect…

Computation and Language · Computer Science 2020-12-01 Zhiruo Wang , Renfen Hu

Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an observation formalized as the Platonic Representation Hypothesis. Whether this…

Computation and Language · Computer Science 2026-05-25 Muhammad Usama , Dong Eui Chang

This paper investigates the capabilities of Large Language Models (LLMs) in the context of understanding their knowledge and uncertainty over questions. Specifically, we focus on addressing known-unknown questions, characterized by high…

Computation and Language · Computer Science 2024-07-03 Alfonso Amayuelas , Kyle Wong , Liangming Pan , Wenhu Chen , William Wang

Large language models (LLMs) are increasingly used in high-stakes settings, where overconfident responses can mislead users. Reliable confidence estimation has been shown to enhance trust and task accuracy. Yet existing methods face…

Computation and Language · Computer Science 2025-09-30 Linwei Tao , Yi-Fan Yeh , Bo Kai , Minjing Dong , Tao Huang , Tom A. Lamb , Jialin Yu , Philip H. S. Torr , Chang Xu

While large language models (LLMs) demonstrate strong capabilities across diverse user queries, they still suffer from hallucinations, often arising from knowledge misalignment between pre-training and fine-tuning. To address this…

Computation and Language · Computer Science 2026-04-08 Joosung Lee , Hwiyeol Jo , Donghyeon Ko , Kyubyung Chae , Cheonbok Park , Jeonghoon Kim

In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) and revolutionized various fields by providing a few task-relevant demonstrations in the prompt. However, trustworthy issues with LLM's response,…

Computation and Language · Computer Science 2024-04-01 Chen Ling , Xujiang Zhao , Xuchao Zhang , Wei Cheng , Yanchi Liu , Yiyou Sun , Mika Oishi , Takao Osaki , Katsushi Matsuda , Jie Ji , Guangji Bai , Liang Zhao , Haifeng Chen

We show that a GPT-3 model can learn to express uncertainty about its own answers in natural language -- without use of model logits. When given a question, the model generates both an answer and a level of confidence (e.g. "90% confidence"…

Computation and Language · Computer Science 2022-06-14 Stephanie Lin , Jacob Hilton , Owain Evans

Can large language models (LLMs) express their uncertainty in situations where they lack sufficient parametric knowledge to generate reasonable responses? This work aims to systematically investigate LLMs' behaviors in such situations,…

Computation and Language · Computer Science 2024-02-19 Genglin Liu , Xingyao Wang , Lifan Yuan , Yangyi Chen , Hao Peng

Interpretability research now offers a variety of techniques for identifying abstract internal mechanisms in neural networks. Can such techniques be used to predict how models will behave on out-of-distribution examples? In this work, we…

Machine Learning · Computer Science 2025-11-12 Jing Huang , Junyi Tao , Thomas Icard , Diyi Yang , Christopher Potts

Intuitively, unfamiliarity should lead to lack of confidence. In reality, current algorithms often make highly confident yet wrong predictions when faced with relevant but unfamiliar examples. A classifier we trained to recognize gender is…

Computer Vision and Pattern Recognition · Computer Science 2020-09-09 Zhizhong Li , Derek Hoiem

Reliable Large Language Models (LLMs) should abstain when confidence is insufficient. However, prior studies often treat refusal as a generic "I don't know'', failing to distinguish input-level ambiguity (data uncertainty) from capability…

Computation and Language · Computer Science 2026-04-21 Jingyi Ren , Ante Wang , Yunghwei Lai , Xiaolong Wang , Linlu Gong , Weitao Li , Weizhi Ma , Yang Liu
‹ Prev 1 2 3 10 Next ›