English
Related papers

Related papers: Rationalizing Neural Predictions

200 papers

In this paper the theory of semi-bounded rationality is proposed as an extension of the theory of bounded rationality. In particular, it is proposed that a decision making process involves two components and these are the correlation…

Artificial Intelligence · Computer Science 2013-05-28 Tshilidzi Marwala

We propose a new interpretability method for neural networks, which is based on a novel mathematico-philosophical theory of reasons. Our method computes a vector for each neuron, called its reasons vector. We then can compute how strongly…

Machine Learning · Computer Science 2025-05-21 Levin Hornischer , Hannes Leitgeb

Providing explanations along with predictions is crucial in some text processing tasks. Therefore, we propose a new self-interpretable model that performs output prediction and simultaneously provides an explanation in terms of the presence…

Machine Learning · Computer Science 2019-09-30 Diane Bouchacourt , Ludovic Denoyer

Rational decision making in its linguistic description means making logical decisions. In essence, a rational agent optimally processes all relevant information to achieve its goal. Rationality has two elements and these are the use of…

Artificial Intelligence · Computer Science 2019-02-14 Tshilidzi Marwala

Two main approaches for evaluating the quality of machine-generated rationales are: 1) using human rationales as a gold standard; and 2) automated metrics based on how rationales affect model behavior. An open question, however, is how…

Computation and Language · Computer Science 2020-10-13 Samuel Carton , Anirudh Rathore , Chenhao Tan

Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations…

Computation and Language · Computer Science 2024-11-27 Tim Hartill

Saliency post-hoc explainability methods are important tools for understanding increasingly complex NLP models. While these methods can reflect the model's reasoning, they may not align with human intuition, making the explanations not…

Computation and Language · Computer Science 2024-08-20 Lucas E. Resck , Marcos M. Raimundo , Jorge Poco

Human explanations of natural language, rationales, form a tool to assess whether models learn a label for the right reasons or rely on dataset-specific shortcuts. Sufficiency is a common metric for estimating the informativeness of…

Computation and Language · Computer Science 2025-11-21 Jonathan Kamp , Lisa Beinborn , Antske Fokkens

Recent research has shown that rationales, or step-by-step chains of thought, can be used to improve performance in multi-step reasoning tasks. We reconsider rationale-augmented prompting for few-shot in-context learning, where (input ->…

Computation and Language · Computer Science 2022-07-05 Xuezhi Wang , Jason Wei , Dale Schuurmans , Quoc Le , Ed Chi , Denny Zhou

Generating high-quality stories spanning thousands of tokens requires competency across a variety of skills, from tracking plot and character arcs to keeping a consistent and engaging style. Due to the difficulty of sourcing labeled…

Computation and Language · Computer Science 2025-09-09 Alexander Gurung , Mirella Lapata

The current state-of-the-art in many natural language processing and automated knowledge base completion tasks is held by representation learning methods which learn distributed vector representations of symbols via gradient-based…

Neural and Evolutionary Computing · Computer Science 2017-12-29 Tim Rocktäschel

We present a model for pragmatically describing scenes, in which contrastive behavior results from a combination of inference-driven pragmatics and learned semantics. Like previous learned approaches to language generation, our model uses a…

Computation and Language · Computer Science 2016-09-27 Jacob Andreas , Dan Klein

An analyst observes an agent take a sequence of actions. The analyst does not have access to the agent's information and ponders whether the observed actions could be justified through a rational Bayesian model with a known utility…

Theoretical Economics · Economics 2025-04-08 Henrique de Oliveira , Rohit Lamba

We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or…

Computation and Language · Computer Science 2016-09-27 Ye Zhang , Iain Marshall , Byron C. Wallace

The generation of comprehensible explanations is an essential feature of modern artificial intelligence systems. In this work, we consider probabilistic logic programming, an extension of logic programming which can be useful to model…

Artificial Intelligence · Computer Science 2023-08-17 Germán Vidal

Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate. The selection can be optimized post-hoc for trained models or incorporated directly into the…

Machine Learning · Computer Science 2019-10-29 Shiyu Chang , Yang Zhang , Mo Yu , Tommi S. Jaakkola

Opinion summarization aims to generate concise summaries that present popular opinions of a large group of reviews. However, these summaries can be too generic and lack supporting details. To address these issues, we propose a new paradigm…

Computation and Language · Computer Science 2024-04-02 Haoyuan Li , Snigdha Chaturvedi

The features of a logically sound approach to a theory of statistical reasoning are discussed. A particular approach that satisfies these criteria is reviewed. This is seen to involve selection of a model, model checking, elicitation of a…

Statistics Theory · Mathematics 2018-05-09 Luai Al-Labadi , Zeynep Baskurt , Michael Evans

When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…

Computation and Language · Computer Science 2022-10-10 Pierre Colombo , Guillaume Staerman , Nathan Noiry , Pablo Piantanida

Human-annotated textual explanations are becoming increasingly important in Explainable Natural Language Processing. Rationale extraction aims to provide faithful (i.e., reflective of the behavior of the model) and plausible (i.e.,…

Computation and Language · Computer Science 2023-10-24 Mohammad Reza Ghasemi Madani , Pasquale Minervini