中文
相关论文

相关论文: An Existence Proof for Neural Language Models That…

200 篇论文

The logical negation property (LNP), which implies generating different predictions for semantically opposite inputs, is an important property that a trustworthy language model must satisfy. However, much recent evidence shows that…

计算与语言 · 计算机科学 2022-08-12 Myeongjun Jang , Frank Mtumbuka , Thomas Lukasiewicz

Suspense is an affective response to narrative text that is believed to involve complex cognitive processes in humans. Several psychological models have been developed to describe this phenomenon and the circumstances under which text might…

We propose Neural Reasoner, a framework for neural network-based reasoning over natural language sentences. Given a question, Neural Reasoner can infer over multiple supporting facts and find an answer to the question in specific forms.…

人工智能 · 计算机科学 2015-08-25 Baolin Peng , Zhengdong Lu , Hang Li , Kam-Fai Wong

The functional interpretation of language-related ERP components has been a central debate in psycholinguistics for decades. We advance an information-theoretic model of human language processing in the brain in which incoming linguistic…

计算与语言 · 计算机科学 2024-11-13 Jiaxuan Li , Richard Futrell

Humans effortlessly go beyond literal meanings: If you mow the lawn, I will give you fifty dollars, is typically understood as implying that the speaker will pay only if the lawn is mowed, whereas If you are hungry, there is pizza in the…

计算与语言 · 计算机科学 2026-05-21 Paolo Morosi , Nikoleta Pantelidou , Fritz Günther , Elena Pagliarini , Evelina Leivada

Model interpretability has become an important problem in machine learning (ML) due to the increased effect that algorithmic decisions have on humans. Counterfactual explanations can help users understand not only why ML models make certain…

机器学习 · 计算机科学 2021-12-20 Ana Lucic , Harrie Oosterhuis , Hinda Haned , Maarten de Rijke

Recent advances in AI have been significantly driven by the capabilities of large language models (LLMs) to solve complex problems in ways that resemble human thinking. However, there is an ongoing debate about the extent to which LLMs are…

机器学习 · 计算机科学 2024-08-16 Javier González , Aditya V. Nori

Predicting upcoming events is critical to our ability to interact with our environment. Transformer models, trained on next-word prediction, appear to construct representations of linguistic input that can support diverse downstream tasks.…

计算与语言 · 计算机科学 2023-11-10 Eghbal A. Hosseini , Evelina Fedorenko

This work presents a detailed linguistic analysis into why larger Transformer-based pre-trained language models with more parameters and lower perplexity nonetheless yield surprisal estimates that are less predictive of human reading times.…

计算与语言 · 计算机科学 2022-12-26 Byung-Doh Oh , William Schuler

Large language models (LLMs) are capable of answering knowledge-intensive complex questions with chain-of-thought (CoT) reasoning. However, they tend to generate factually incorrect reasoning steps when the required knowledge is not…

计算与语言 · 计算机科学 2023-11-27 Shulin Cao , Jiajie Zhang , Jiaxin Shi , Xin Lv , Zijun Yao , Qi Tian , Juanzi Li , Lei Hou

Phrases are fundamental linguistic units through which humans convey semantics. This study critically examines the capacity of API-based large language models (LLMs) to comprehend phrase semantics, utilizing three human-annotated datasets.…

计算与语言 · 计算机科学 2024-10-04 Rui Meng , Ye Liu , Lifu Tu , Daqing He , Yingbo Zhou , Semih Yavuz

Concerns with the safety and reliability of applying large-language models (LLMs) in unpredictable real-world applications motivate this study, which examines how task phrasing can lead to presumptions in LLMs, making it difficult for them…

计算与语言 · 计算机科学 2026-05-04 Kenneth J. K. Ong

Providing plausible responses to why questions is a challenging but critical goal for language based human-machine interaction. Explanations are challenging in that they require many different forms of abstract knowledge and reasoning.…

计算与语言 · 计算机科学 2019-06-05 Allen Nie , Erin D. Bennett , Noah D. Goodman

Causal reasoning is a cornerstone of human intelligence and a critical capability for artificial systems aiming to achieve advanced understanding and decision-making. This thesis delves into various dimensions of causal reasoning and…

计算与语言 · 计算机科学 2025-04-22 Zhijing Jin

Prediction in language has traditionally been studied using simple designs in which neural responses to expected and unexpected words are compared in a categorical fashion. However, these designs have been contested as being `prediction…

神经元与认知 · 定量生物学 2019-09-11 Micha Heilbron , Benedikt Ehinger , Peter Hagoort , Floris P. de Lange

The self-rationalising capabilities of large language models (LLMs) have been explored in restricted settings, using task/specific data sets. However, current LLMs do not (only) rely on specifically annotated data; nonetheless, they…

计算与语言 · 计算机科学 2024-12-18 Jenny Kunz , Marco Kuhlmann

Understanding how humans process natural language has long been a vital research direction. The field of natural language processing (NLP) has recently experienced a surge in the development of powerful language models. These models have…

计算与语言 · 计算机科学 2023-11-20 Zhengqi He , Taro Toyoizumi

What happens when a language model thinks without words? Standard reasoning LLMs verbalize intermediate steps as chain-of-thought; latent reasoning transformers (LRTs) instead perform deliberation entirely in continuous hidden space. We…

计算与语言 · 计算机科学 2026-02-10 Jasmine Cui , Charles Ye

Large language models (LLMs) increasingly mimic human cognition in various language-based tasks. However, their capacity for metacognition - particularly in predicting memory performance - remains unexplored. Here, we introduce a…

计算与语言 · 计算机科学 2025-10-14 Markus Huff , Elanur Ulakçı

In this paper we introduce Latent Tree Language Model (LTLM), a novel approach to language modeling that encodes syntax and semantics of a given sentence as a tree of word roles. The learning phase iteratively updates the trees by moving…

计算与语言 · 计算机科学 2016-09-06 Tomas Brychcin