English
Related papers

Related papers: Rationalizing Neural Predictions

200 papers

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.…

Computation and Language · Computer Science 2019-06-05 Allen Nie , Erin D. Bennett , Noah D. Goodman

Qualitative relationships illustrate how changing one property (e.g., moving velocity) affects another (e.g., kinetic energy) and constitutes a considerable portion of textual knowledge. Current approaches use either semantic parsers to…

Computation and Language · Computer Science 2021-06-07 Mucheng Ren , Heyan Huang , Yang Gao

Machine learning models support decision-making, yet the reasons behind their predictions are opaque. Clear and reliable explanations help users make informed decisions and avoid blindly trusting model outputs. However, many existing…

Logic in Computer Science · Computer Science 2026-03-03 Francisco Mateus Rocha Filho , Ajalmar Rêgo da Rocha Neto , Thiago Alves Rocha

Automated reasoning about uncertain knowledge has many applications. One difficulty when developing such systems is the lack of a completely satisfactory integration of logic and probability. We address this problem directly. Expressive…

Logic in Computer Science · Computer Science 2012-09-13 Marcus Hutter , John W. Lloyd , Kee Siong Ng , William T. B. Uther

A standard paradigm for sentiment analysis is to rely on a singular LLM and makes the decision in a single round under the framework of in-context learning. This framework suffers the key disadvantage that the single-turn output generated…

Computation and Language · Computer Science 2023-11-06 Xiaofei Sun , Xiaoya Li , Shengyu Zhang , Shuhe Wang , Fei Wu , Jiwei Li , Tianwei Zhang , Guoyin Wang

Recent research on model interpretability in natural language processing extensively uses feature scoring methods for identifying which parts of the input are the most important for a model to make a prediction (i.e. explanation or…

Computation and Language · Computer Science 2021-12-07 George Chrysostomou , Nikolaos Aletras

The eventual goal of a language model is to accurately predict the value of a missing word given its context. We present an approach to word prediction that is based on learning a representation for each word as a function of words and…

Computation and Language · Computer Science 2007-05-23 Yair Even-Zohar , Dan Roth

Predicting the future is an important component of decision making. In most situations, however, there is not enough information to make accurate predictions. In this paper, we develop a theory of causal reasoning for predictive inference…

Artificial Intelligence · Computer Science 2013-04-10 Thomas L. Dean , Keiji Kanazawa

In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, there is no comparably principled basis to justify trust in the content of the text…

Artificial Intelligence · Computer Science 2026-05-15 Leslie G. Valiant

Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions…

Artificial Intelligence · Computer Science 2023-12-18 Wei Liu , Haozhao Wang , Jun Wang , Zhiying Deng , YuanKai Zhang , Cheng Wang , Ruixuan Li

While the need for interpretable machine learning has been established, many common approaches are slow, lack fidelity, or hard to evaluate. Amortized explanation methods reduce the cost of providing interpretations by learning a global…

Machine Learning · Statistics 2021-03-03 Neil Jethani , Mukund Sudarshan , Yindalon Aphinyanaphongs , Rajesh Ranganath

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…

Computation and Language · Computer Science 2023-11-07 Zeming Chen , Gail Weiss , Eric Mitchell , Asli Celikyilmaz , Antoine Bosselut

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains…

Artificial Intelligence · Computer Science 2018-02-05 Menaka Narayanan , Emily Chen , Jeffrey He , Been Kim , Sam Gershman , Finale Doshi-Velez

Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when conditions in training may differ from those in practice.…

Machine Learning · Computer Science 2018-10-03 Andrew Slavin Ross

We present the surprising finding that a language model's reasoning capabilities can be improved by training on synthetic datasets of chain-of-thought (CoT) traces from more capable models, even when all of those traces lead to an incorrect…

Artificial Intelligence · Computer Science 2026-01-26 Abhranil Chandra , Ayush Agrawal , Arian Hosseini , Sebastian Fischmeister , Rishabh Agarwal , Navin Goyal , Aaron Courville

Reasoning requires going beyond pattern matching or memorization of solutions to identify and implement "algorithmic procedures" that can be used to deduce answers to hard problems. Doing so requires realizing the most relevant primitives,…

Artificial Intelligence · Computer Science 2025-10-03 Yuxiao Qu , Anikait Singh , Yoonho Lee , Amrith Setlur , Ruslan Salakhutdinov , Chelsea Finn , Aviral Kumar

Decisions in organizations are about evaluating alternatives and choosing the one that would best serve organizational goals. To the extent that the evaluation of alternatives could be formulated as a predictive task with appropriate…

Human-Computer Interaction · Computer Science 2022-06-30 Charles Wan , Rodrigo Belo , Leid Zejnilović

Reasoning, the ability to logically draw conclusions from existing knowledge, is a hallmark of human. Together with perception, they constitute the two major themes of artificial intelligence. While deep learning has pushed the limit of…

Artificial Intelligence · Computer Science 2024-10-18 Zhaocheng Zhu

Advances in machine reading comprehension (MRC) rely heavily on the collection of large scale human-annotated examples in the form of (question, paragraph, answer) triples. In contrast, humans are typically able to generalize with only a…

Computation and Language · Computer Science 2020-10-15 Qinyuan Ye , Xiao Huang , Elizabeth Boschee , Xiang Ren

While most approaches to automatically recognizing entailment relations have used classifiers employing hand engineered features derived from complex natural language processing pipelines, in practice their performance has been only…

Computation and Language · Computer Science 2016-03-02 Tim Rocktäschel , Edward Grefenstette , Karl Moritz Hermann , Tomáš Kočiský , Phil Blunsom
‹ Prev 1 4 5 6 7 8 10 Next ›