English
Related papers

Related papers: Bilinear representation mitigates reversal curse a…

200 papers

Massive language models are the core of modern NLP modeling and have been shown to encode impressive amounts of commonsense and factual information. However, that knowledge exists only within the latent parameters of the model, inaccessible…

Computation and Language · Computer Science 2020-07-03 Pat Verga , Haitian Sun , Livio Baldini Soares , William W. Cohen

Efforts to interpret reinforcement learning (RL) models often rely on high-level techniques such as attribution or probing, which provide only correlational insights and coarse causal control. This work proposes replacing nonlinearities in…

Machine Learning · Computer Science 2024-12-03 Narmeen Oozeer , Sinem Erisken , Alice Rigg

Recent probing studies reveal that large language models exhibit linear subspaces that separate true from false statements, yet the mechanism behind their emergence is unclear. We introduce a transparent, one-layer transformer toy model…

Computation and Language · Computer Science 2025-10-20 Shauli Ravfogel , Gilad Yehudai , Tal Linzen , Joan Bruna , Alberto Bietti

In naturalistic learning problems, a model's input contains a wide range of features, some useful for the task at hand, and others not. Of the useful features, which ones does the model use? Of the task-irrelevant features, which ones does…

Machine Learning · Computer Science 2020-10-26 Katherine L. Hermann , Andrew K. Lampinen

Arguments in favor of injecting symbolic knowledge into neural architectures abound. When done right, constraining a sub-symbolic model can substantially improve its performance and sample complexity and prevent it from predicting invalid…

Machine Learning · Computer Science 2019-12-24 Stefano Teso

Approximate Bayesian inference on the basis of summary statistics is well-suited to complex problems for which the likelihood is either mathematically or computationally intractable. However the methods that use rejection suffer from the…

Computation · Statistics 2010-05-04 M. G. B. Blum , O. Francois

We tackle the problem of computing counterfactual explanations -- minimal changes to the features that flip an undesirable model prediction. We propose a solution to this question for linear Support Vector Machine (SVMs) models. Moreover,…

Machine Learning · Computer Science 2022-12-16 Sebastian Salazar , Samuel Denton , Ansaf Salleb-Aouissi

Recent progress in language modeling has expanded the range of tasks that can be approached through natural language interfaces, including problems that require structured reasoning. However, it remains unclear how effectively…

Machine Learning · Computer Science 2026-04-30 Michal Podstawski

Probing and enhancing large language models' reasoning capacity remains a crucial open question. Here we re-purpose the reverse dictionary task as a case study to probe LLMs' capacity for conceptual inference. We use in-context learning to…

Computation and Language · Computer Science 2024-02-27 Ningyu Xu , Qi Zhang , Menghan Zhang , Peng Qian , Xuanjing Huang

Large vision-language models (VLMs) often benefit from intermediate visual cues, either injected via external tools or generated as latent visual tokens during reasoning, but these mechanisms still overlook fine-grained visual evidence…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Shuoshuo Zhang , Yizhen Zhang , Jingjing Fu , Lei Song , Jiang Bian , Yujiu Yang , Rui Wang

Counterfactual explanations are widely used to interpret machine learning predictions by identifying minimal changes to input features that would alter a model's decision. However, most existing counterfactual methods have not been tested…

Machine Learning · Computer Science 2026-02-03 Leonidas Christodoulou , Chang Sun

Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on understanding of the…

Computation and Language · Computer Science 2022-12-08 Jiaxuan Li , Lang Yu , Allyson Ettinger

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…

Computation and Language · Computer Science 2023-10-31 Nora Kassner , Oyvind Tafjord , Ashish Sabharwal , Kyle Richardson , Hinrich Schuetze , Peter Clark

Contextualized or discourse aware commonsense inference is the task of generating coherent commonsense assertions (i.e., facts) from a given story, and a particular sentence from that story. Some problems with the task are: lack of…

Computation and Language · Computer Science 2023-02-13 Pedro Colon-Hernandez , Henry Lieberman , Yida Xin , Claire Yin , Cynthia Breazeal , Peter Chin

In this thesis, we develop various techniques for working with sets in machine learning. Each input or output is not an image or a sequence, but a set: an unordered collection of multiple objects, each object described by a feature vector.…

Machine Learning · Computer Science 2021-03-09 Yan Zhang

Grasping the commonsense properties of everyday concepts is an important prerequisite to language understanding. While contextualised language models are reportedly capable of predicting such commonsense properties with human-level…

Computation and Language · Computer Science 2022-10-07 Amit Gajbhiye , Luis Espinosa-Anke , Steven Schockaert

Language models now provide an interface to express and often solve general problems in natural language, yet their ultimate computational capabilities remain a major topic of scientific debate. Unlike a formal computer, a language model is…

Computation and Language · Computer Science 2026-02-11 Alex Lewandowski , Marlos C. Machado , Dale Schuurmans

A common approach in neuroscience is to study neural representations as a means to understand a system -- increasingly, by relating the neural representations to the internal representations learned by computational models. However, a…

Neurons and Cognition · Quantitative Biology 2025-08-14 Andrew Kyle Lampinen , Stephanie C. Y. Chan , Yuxuan Li , Katherine Hermann

We formalize a structural property of the causal (autoregressive) language modeling (CLM) objective: reversal invariance. Formally, the next-token prediction loss assigns identical likelihood to a corpus and its reversal, implying that…

Computation and Language · Computer Science 2025-11-04 Mihir Sahasrabudhe

We are often interested in decomposing complex, structured data into simple components that explain the data. The linear version of this problem is well-studied as dictionary learning and factor analysis. In this work, we propose a…

Machine Learning · Computer Science 2024-07-29 Avrim Blum , Kavya Ravichandran