English
Related papers

Related papers: Learning opacity in Stratal Maximum Entropy Gramma…

200 papers

In this work, we investigate how Large Language Models (LLMs) adapt their internal representations when encountering inputs of increasing difficulty, quantified as the degree of out-of-distribution (OOD) shift. We reveal a consistent and…

Computation and Language · Computer Science 2026-03-20 Mingyu Jin , Yutong Yin , Jingcheng Niu , Qingcheng Zeng , Wujiang Xu , Mengnan Du , Wei Cheng , Zhaoran Wang , Tianlong Chen , Dimitris N. Metaxas

The efficient sparse coding and reconstruction of signal vectors via linear observations has received a tremendous amount of attention over the last decade. In this context, the automated learning of a suitable basis or overcomplete…

Information Theory · Computer Science 2015-06-19 Andreas M. Tillmann

Large language models (LLMs) produce fluent but unsupported answers - hallucinations - limiting safe deployment in high-stakes domains. We propose ECLIPSE, a framework that treats hallucination as a mismatch between a model's semantic…

Machine Learning · Computer Science 2025-12-04 Mainak Singha

Across many data domains, co-occurrence statistics about the joint appearance of objects are powerfully informative. By transforming unsupervised learning problems into decompositions of co-occurrence statistics, spectral algorithms provide…

Computation and Language · Computer Science 2021-11-15 Moontae Lee , Sungjun Cho , Kun Dong , David Mimno , David Bindel

Researchers in textual entailment have begun to consider inferences involving 'downward-entailing operators', an interesting and important class of lexical items that change the way inferences are made. Recent work proposed a method for…

Computation and Language · Computer Science 2010-11-30 Cristian Danescu-Niculescu-Mizil , Lillian Lee

Deep learning techniques are increasingly popular in the textual entailment task, overcoming the fragility of traditional discrete models with hard alignments and logics. In particular, the recently proposed attention models (Rockt\"aschel…

Computation and Language · Computer Science 2017-09-05 Kai Zhao , Liang Huang , Mingbo Ma

Systems for language understanding have become remarkably strong at overcoming linguistic imperfections in tasks involving phrase matching or simple reasoning. Yet, their accuracy drops dramatically as the number of reasoning steps…

Computation and Language · Computer Science 2020-05-04 Daniel Khashabi , Erfan Sadeqi Azer , Tushar Khot , Ashish Sabharwal , Dan Roth

Precisely how humans process relational patterns of information in knowledge, language, music, and society is not well understood. Prior work in the field of statistical learning has demonstrated that humans process such information by…

Language models demonstrate remarkable abilities when pre-trained on large text corpora and fine-tuned for specific tasks, but how and why pre-training shapes the success of the final model remains poorly understood. Notably, although…

Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either…

Computation and Language · Computer Science 2020-02-28 Duygu Ataman , Wilker Aziz , Alexandra Birch

When humans learn a new concept, they might ignore examples that they cannot make sense of at first, and only later focus on such examples, when they are more useful for learning. We propose incorporating this idea of tunable sensitivity…

Machine Learning · Statistics 2016-11-24 Gil Keren , Sivan Sabato , Björn Schuller

A range of studies have concluded that neural word prediction models can distinguish grammatical from ungrammatical sentences with high accuracy. However, these studies are based primarily on monolingual evidence from English. To…

Computation and Language · Computer Science 2020-05-22 Aaron Mueller , Garrett Nicolai , Panayiota Petrou-Zeniou , Natalia Talmina , Tal Linzen

We introduce a dataset of concept learning tasks that helps uncover implicit biases in large language models. Using in-context concept learning experiments, we found that language models may have a bias toward upward monotonicity in…

Computation and Language · Computer Science 2025-11-27 Leroy Z. Wang

Representation learning systems typically rely on massive amounts of labeled data in order to be trained to high accuracy. Recently, high-dimensional parametric models like neural networks have succeeded in building rich representations…

Machine Learning · Statistics 2016-03-03 Theofanis Karaletsos , Serge Belongie , Gunnar Rätsch

We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource…

Computation and Language · Computer Science 2020-04-29 Katharina Kann , Samuel R. Bowman , Kyunghyun Cho

Recent work in learning ontologies (hierarchical and partially-ordered structures) has leveraged the intrinsic geometry of spaces of learned representations to make predictions that automatically obey complex structural constraints. We…

Computation and Language · Computer Science 2017-08-03 Xiang Li , Luke Vilnis , Andrew McCallum

Interpretability methods aim to understand the algorithm implemented by a trained model (e.g., a Transofmer) by examining various aspects of the model, such as the weight matrices or the attention patterns. In this work, through a…

Machine Learning · Computer Science 2023-12-05 Kaiyue Wen , Yuchen Li , Bingbin Liu , Andrej Risteski

In Monte Carlo simulations of lattice field theory with a $\theta$ term, one confronts the complex weight problem, or the sign problem. This is circumvented by performing the Fourier transform of the topological charge distribution $P(Q)$.…

High Energy Physics - Lattice · Physics 2017-02-01 Masahiro Imachi , Yasuhiko Shinno , Hiroshi Yoneyama

Manifold learning and dimensionality reduction techniques are ubiquitous in science and engineering, but can be computationally expensive procedures when applied to large data sets or when similarities are expensive to compute. To date,…

Machine Learning · Statistics 2017-04-05 Keith Levin , Vince Lyzinski

Machine learning models allow us to compare languages by showing how hard a task in each language might be to learn and perform well on. Following this line of investigation, we explore what makes a language "hard to pronounce" by modelling…

Computation and Language · Computer Science 2022-02-11 Domenic Rosati
‹ Prev 1 3 4 5 6 7 10 Next ›