English
Related papers

Related papers: Interpretation of NLP models through input margina…

200 papers

The lack of interpretability and trust is a much-criticised feature of deep neural networks. In fully connected nets, the signalling between inner layers is scrambled because backpropagation training does not require perceptrons to be…

Signal Processing · Electrical Eng. & Systems 2021-01-28 Jake L. Amey , Jake Keeley , Tajwar Choudhury , Ilya Kuprov

In science and medicine, model interpretations may be reported as discoveries of natural phenomena or used to guide patient treatments. In such high-stakes tasks, false discoveries may lead investigators astray. These applications would…

Machine Learning · Statistics 2020-08-18 Collin Burns , Jesse Thomason , Wesley Tansey

Large Language Models (LLMs) have demonstrated exceptional code generation capabilities, yet their token-level mechanisms remain underexplored, particularly in compressed models. Through systematic analysis of programming language token…

Software Engineering · Computer Science 2026-02-10 Viacheslav Siniaev , Iaroslav Chelombitko , Aleksey Komissarov

Language models often struggle with idiomatic, figurative, or context-sensitive inputs, not because they produce flawed outputs, but because they misinterpret the input from the outset. We propose an input-only method for anticipating such…

Computation and Language · Computer Science 2025-09-25 Maggie Mi , Aline Villavicencio , Nafise Sadat Moosavi

This research aims to unravel how large language models (LLMs) iteratively refine token predictions through internal processing. We utilized a logit lens technique to analyze the model's token predictions derived from intermediate…

Computation and Language · Computer Science 2025-06-10 Jaturong Kongmanee

In this paper we present a technique of NLP to tackle the problem of inference relation (NLI) between pairs of sentences in a target language of choice without a language-specific training dataset. We exploit a generic translation dataset,…

Computation and Language · Computer Science 2023-09-07 Lorenzo Corradi , Alessandro Manenti , Francesca Del Bonifro , Francesco Setti , Dario Del Sorbo

Text preprocessing is often the first step in the pipeline of a Natural Language Processing (NLP) system, with potential impact in its final performance. Despite its importance, text preprocessing has not received much attention in the deep…

Computation and Language · Computer Science 2018-08-24 Jose Camacho-Collados , Mohammad Taher Pilehvar

In NLP, models are usually evaluated by reporting single-number performance scores on a number of readily available benchmarks, without much deeper analysis. Here, we argue that - especially given the well-known fact that benchmarks often…

Computation and Language · Computer Science 2022-10-05 Daniel Simig , Tianlu Wang , Verna Dankers , Peter Henderson , Khuyagbaatar Batsuren , Dieuwke Hupkes , Mona Diab

Language modeling has shifted in recent years from a distribution over strings to prediction models with textual inputs and outputs for general-purpose tasks. This position paper highlights the often overlooked implications of this shift…

Computation and Language · Computer Science 2026-05-13 Eitan Wagner , Omri Abend

Natural language processing (NLP) enables the understanding and generation of meaningful human language, typically using a pre-trained complex architecture on a large dataset to learn the language and next fine-tune its weights to implement…

Computation and Language · Computer Science 2025-09-04 Yarden Tzach , Ronit D. Gross , Ella Koresh , Shalom Rosner , Or Shpringer , Tal Halevi , Ido Kanter

Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes." This opacity raises concerns about their interpretability…

Machine Learning · Computer Science 2024-11-27 Pirzada Suhail , Amit Sethi

The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox…

Machine Learning · Computer Science 2018-03-14 Osbert Bastani , Carolyn Kim , Hamsa Bastani

Despite the extensive success of pretrained language models as encoders for building NLP systems, they haven't seen prominence as decoders for sequence generation tasks. We explore the question of whether these models can be adapted to be…

Computation and Language · Computer Science 2020-08-21 Nishant Subramani , Nivedita Suresh

A fundamental advantage of neural models for NLP is their ability to learn representations from scratch. However, in practice this often means ignoring existing external linguistic resources, e.g., WordNet or domain specific ontologies such…

Computation and Language · Computer Science 2017-04-26 Ye Zhang , Matthew Lease , Byron C. Wallace

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…

Computation and Language · Computer Science 2025-01-31 Didier Chételat , Joseph Cotnareanu , Rylee Thompson , Yingxue Zhang , Mark Coates

Recently, state-of-the-art NLP models gained an increasing syntactic and semantic understanding of language, and explanation methods are crucial to understand their decisions. Occlusion is a well established method that provides…

Computation and Language · Computer Science 2020-04-22 David Harbecke , Christoph Alt

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically…

Computation and Language · Computer Science 2024-04-04 Josh Magnus Ludan , Qing Lyu , Yue Yang , Liam Dugan , Mark Yatskar , Chris Callison-Burch

This article presents the prediction difference analysis method for visualizing the response of a deep neural network to a specific input. When classifying images, the method highlights areas in a given input image that provide evidence for…

Computer Vision and Pattern Recognition · Computer Science 2017-02-16 Luisa M Zintgraf , Taco S Cohen , Tameem Adel , Max Welling

Unsupervised neural grammar induction aims to learn interpretable hierarchical structures from language data. However, existing models face an expressiveness bottleneck, often resulting in unnecessarily large yet underperforming grammars.…

Computation and Language · Computer Science 2025-09-26 Jinwook Park , Kangil Kim

We describe a procedure for removing dependency on a cohort of training data from a trained deep network that improves upon and generalizes previous methods to different readout functions and can be extended to ensure forgetting in the…

Machine Learning · Computer Science 2020-10-30 Aditya Golatkar , Alessandro Achille , Stefano Soatto