English
Related papers

Related papers: Probing structural constraints of negation in Pret…

200 papers

In neural network models of language, words are commonly represented using context-invariant representations (word embeddings) which are then put in context in the hidden layers. Since words are often ambiguous, representing the…

Computation and Language · Computer Science 2019-06-13 Laura Aina , Kristina Gulordava , Gemma Boleda

Despite achieving state-of-the-art performance on many NLP tasks, the high energy cost and long inference delay prevent Transformer-based pretrained language models (PLMs) from seeing broader adoption including for edge and mobile…

Computation and Language · Computer Science 2022-11-30 Canwen Xu , Julian McAuley

Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and…

Artificial Intelligence · Computer Science 2025-11-11 Hirohane Takagi , Gouki Minegishi , Shota Kizawa , Issey Sukeda , Hitomi Yanaka

Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…

Computation and Language · Computer Science 2023-10-10 Nayoung Choi

Gender bias in pretrained language models (PLMs) poses significant social and ethical challenges. Despite growing awareness, there is a lack of comprehensive investigation into how different models internally represent and propagate such…

Computation and Language · Computer Science 2025-03-11 Mahdi Zakizadeh , Mohammad Taher Pilehvar

Building on Petroni et al. (2019), we propose two new probing tasks analyzing factual knowledge stored in Pretrained Language Models (PLMs). (1) Negation. We find that PLMs do not distinguish between negated ("Birds cannot [MASK]") and…

Computation and Language · Computer Science 2020-05-18 Nora Kassner , Hinrich Schütze

Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text…

Computation and Language · Computer Science 2026-03-31 Yibo Yang

Model interpretability methods are often used to explain NLP model decisions on tasks such as text classification, where the output space is relatively small. However, when applied to language generation, where the output space often…

Computation and Language · Computer Science 2022-05-24 Kayo Yin , Graham Neubig

Sentence embeddings are central to modern NLP and AI systems, yet little is known about their internal structure. While we can compare these embeddings using measures such as cosine similarity, the contributing features are not…

Computation and Language · Computer Science 2025-06-11 Matthieu Tehenan , Vikram Natarajan , Jonathan Michala , Milton Lin , Juri Opitz

Language Models (LMs) have shown state-of-the-art performance in Natural Language Processing (NLP) tasks. Downstream tasks such as Named Entity Recognition (NER) or Part-of-Speech (POS) tagging are known to suffer from data imbalance…

Computation and Language · Computer Science 2024-04-12 Mehdi Ben Amor , Michael Granitzer , Jelena Mitrović

Pre-trained language models (PLM) are effective components of few-shot named entity recognition (NER) approaches when augmented with continued pre-training on task-specific out-of-domain data or fine-tuning on in-domain data. However, their…

Computation and Language · Computer Science 2022-04-12 Yuxuan Chen , Jonas Mikkelsen , Arne Binder , Christoph Alt , Leonhard Hennig

The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction. However, their effectiveness in in-context learning remains…

Next-token prediction (NTP) over large text corpora has become the go-to paradigm to train large language models. Yet, it remains unclear how NTP influences the mapping of linguistic patterns to geometric properties of the resulting model…

Computation and Language · Computer Science 2025-02-20 Yize Zhao , Tina Behnia , Vala Vakilian , Christos Thrampoulidis

Neural networks are widely regarded as black-box models, creating significant challenges in understanding their inner workings, especially in natural language processing (NLP) applications. To address this opacity, model explanation…

Computation and Language · Computer Science 2025-01-10 Melkamu Mersha , Mingiziem Bitewa , Tsion Abay , Jugal Kalita

Both humans and large language models (LLMs) exhibit content effects: biases in which the plausibility of the semantic content of a reasoning problem influences judgments regarding its logical validity. While this phenomenon in humans is…

Computation and Language · Computer Science 2026-04-21 Leonardo Bertolazzi , Sandro Pezzelle , Raffaella Bernardi

Vision-Language Models (VLMs) like CLIP struggle to understand negation, often embedding affirmatives and negatives similarly (e.g., matching "no dog" with dog images). Existing methods refine negation understanding via fine-tuning CLIP's…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Junhao Xiao , Zhiyu Wu , Hao Lin , Yi Chen , Yahui Liu , Xiaoran Zhao , Zixu Wang , Zejiang He

We address whether neural models for Natural Language Inference (NLI) can learn the compositional interactions between lexical entailment and negation, using four methods: the behavioral evaluation methods of (1) challenge test sets and (2)…

Computation and Language · Computer Science 2020-11-24 Atticus Geiger , Kyle Richardson , Christopher Potts

Simile interpretation (SI) and simile generation (SG) are challenging tasks for NLP because models require adequate world knowledge to produce predictions. Previous works have employed many hand-crafted resources to bring knowledge-related…

Computation and Language · Computer Science 2022-04-28 Weijie Chen , Yongzhu Chang , Rongsheng Zhang , Jiashu Pu , Guandan Chen , Le Zhang , Yadong Xi , Yijiang Chen , Chang Su

Measurement of social bias in language models is typically by token probability (TP) metrics, which are broadly applicable but have been criticized for their distance from real-world language model use cases and harms. In this work, we test…

Computation and Language · Computer Science 2026-01-16 Virginia K. Felkner , Allison Lim , Jonathan May

We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involving negation, they do possess internal components that…

Computation and Language · Computer Science 2026-05-06 Zhejian Zhou , Tianyi Zhou , Robin Jia , Jonathan May