English
Related papers

Related papers: Learning to Faithfully Rationalize by Construction

200 papers

Neural document ranking models perform impressively well due to superior language understanding gained from pre-training tasks. However, due to their complexity and large number of parameters, these (typically transformer-based) models are…

Information Retrieval · Computer Science 2022-12-02 Jurek Leonhardt , Koustav Rudra , Avishek Anand

Document-level models for information extraction tasks like slot-filling are flexible: they can be applied to settings where information is not necessarily localized in a single sentence. For example, key features of a diagnosis in a…

Computation and Language · Computer Science 2022-05-19 Liyan Tang , Dhruv Rajan , Suyash Mohan , Abhijeet Pradhan , R. Nick Bryan , Greg Durrett

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

Interpretability is central for scientific machine learning, as understanding \emph{why} models make predictions enables hypothesis generation and validation. While tabular foundation models show strong performance, existing explanation…

Machine Learning · Computer Science 2026-04-01 Luan Borges Teodoro Reis Sena , Francisco Galuppo Azevedo

Transformers have been shown to be able to perform deductive reasoning on a logical rulebase containing rules and statements written in natural language. Recent works show that such models can also produce the reasoning steps (i.e., the…

Computation and Language · Computer Science 2022-03-22 Soumya Sanyal , Harman Singh , Xiang Ren

Multimodal classifiers function as opaque black box models. While several techniques exist to interpret their predictions, very few of them are as intuitive and accessible as natural language explanations (NLEs). To build trust, such…

Computation and Language · Computer Science 2025-12-09 Dibyanayan Bandyopadhyay , Soham Bhattacharjee , Mohammed Hasanuzzaman , Asif Ekbal

With the ever-increasing complexity of neural language models, practitioners have turned to methods for understanding the predictions of these models. One of the most well-adopted approaches for model interpretability is feature-based…

Computation and Language · Computer Science 2021-06-10 Muhammad Bilal Zafar , Michele Donini , Dylan Slack , Cédric Archambeau , Sanjiv Das , Krishnaram Kenthapadi

Large language models (LLMs) are increasingly used as automatic judges for summarization and dialogue evaluation. Prior work has documented biases such as position, verbosity, and style preferences, but largely focuses on outcomes, leaving…

Computation and Language · Computer Science 2026-05-26 Riya Tapwal , Abhishek Kumar , Carsten Maple

Large language models (LMs) beyond a certain scale, demonstrate the emergent capability of generating free-text rationales for their predictions via chain-of-thought (CoT) prompting. While CoT can yield dramatically improved performance,…

Computation and Language · Computer Science 2023-09-01 Peifeng Wang , Zhengyang Wang , Zheng Li , Yifan Gao , Bing Yin , Xiang Ren

Large language models (LLMs) can explain their predictions through post-hoc or Chain-of-Thought (CoT) explanations. But an LLM could make up reasonably sounding explanations that are unfaithful to its underlying reasoning. Recent work has…

Computation and Language · Computer Science 2024-09-20 Letitia Parcalabescu , Anette Frank

Explaining predictions of black-box neural networks is crucial when applied to decision-critical tasks. Thus, attribution maps are commonly used to identify important image regions, despite prior work showing that humans prefer explanations…

Machine Learning · Computer Science 2023-12-20 Tom Nuno Wolf , Fabian Bongratz , Anne-Marie Rickmann , Sebastian Pölsterl , Christian Wachinger

Explainable NLP techniques primarily explain by answering "Which tokens in the input are responsible for this prediction?''. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by…

Computation and Language · Computer Science 2023-12-05 Eleftheria Briakou , Navita Goyal , Marine Carpuat

Existing explanation methods for image classification struggle to provide faithful and plausible explanations. This paper addresses this issue by proposing a post-hoc natural language explanation method that can be applied to any CNN-based…

Artificial Intelligence · Computer Science 2025-03-19 Adam Wojciechowski , Mateusz Lango , Ondrej Dusek

Faithfulness is arguably the most critical metric to assess the reliability of explainable AI. In NLP, current methods for faithfulness evaluation are fraught with discrepancies and biases, often failing to capture the true reasoning of…

Computation and Language · Computer Science 2024-12-02 Supriya Manna , Niladri Sett

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

LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithfulness metrics have critical limitations, typically relying on…

Artificial Intelligence · Computer Science 2026-02-04 Harry Mayne , Justin Singh Kang , Dewi Gould , Kannan Ramchandran , Adam Mahdi , Noah Y. Siegel

Prediction without justification has limited applicability. As a remedy, we learn to extract pieces of input text as justifications -- rationales -- that are tailored to be short and coherent, yet sufficient for making the same prediction.…

Computation and Language · Computer Science 2016-11-04 Tao Lei , Regina Barzilay , Tommi Jaakkola

In recent years, model explanation methods have been designed to interpret model decisions faithfully and intuitively so that users can easily understand them. In this paper, we propose a framework, Faithful Attention Explainer (FAE),…

Computation and Language · Computer Science 2024-05-28 Yao Rong , David Scheerer , Enkelejda Kasneci

Expressive text encoders such as RNNs and Transformer Networks have been at the center of NLP models in recent work. Most of the effort has focused on sentence-level tasks, capturing the dependencies between words in a single sentence, or…

Computation and Language · Computer Science 2021-09-15 Manuel Widmoser , Maria Leonor Pacheco , Jean Honorio , Dan Goldwasser

Pretrained transformer-based models such as BERT have demonstrated state-of-the-art predictive performance when adapted into a range of natural language processing tasks. An open problem is how to improve the faithfulness of explanations…

Computation and Language · Computer Science 2021-09-01 George Chrysostomou , Nikolaos Aletras