English
Related papers

Related papers: Gumbel Counterfactual Generation From Language Mod…

200 papers

In this paper, we demonstrate how to enhance the validity of causal inference with unstructured high-dimensional treatments like texts, by leveraging the power of generative Artificial Intelligence (GenAI). Specifically, we propose to use a…

Applications · Statistics 2025-09-09 Kosuke Imai , Kentaro Nakamura

Large Language Models (LLMs), despite achieving state-of-the-art results in a number of evaluation tasks, struggle to maintain their performance when logical reasoning is strictly required to correctly infer a prediction. In this work, we…

Computation and Language · Computer Science 2024-10-18 Kaveh Eskandari Miandoab , Vasanth Sarathy

Counterfactual frameworks have grown popular in machine learning for both explaining algorithmic decisions but also defining individual notions of fairness, more intuitive than typical group fairness conditions. However, state-of-the-art…

Artificial Intelligence · Computer Science 2023-01-09 Lucas de Lara , Alberto González-Sanz , Nicholas Asher , Laurent Risser , Jean-Michel Loubes

In attempts to produce ML models less reliant on spurious patterns in NLP datasets, researchers have recently proposed curating counterfactually augmented data (CAD) via a human-in-the-loop process in which given some documents and their…

Computation and Language · Computer Science 2021-03-25 Divyansh Kaushik , Amrith Setlur , Eduard Hovy , Zachary C. Lipton

Counterspeech is a key strategy against harmful online content, but scaling expert-driven efforts is challenging. Large Language Models (LLMs) present a potential solution, though their use in countering conspiracy theories is…

Computation and Language · Computer Science 2025-08-04 Mareike Lisker , Christina Gottschalk , Helena Mihaljević

This research is focused on generating achievable counterfactual explanations. Given a negative outcome computed by a machine learning model or a decision system, the novel CoGS approach generates (i) a counterfactual solution that…

Artificial Intelligence · Computer Science 2025-02-14 Sopam Dasgupta

Despite significant progress in text generation models, a serious limitation is their tendency to produce text that is factually inconsistent with information in the input. Recent work has studied whether textual entailment systems can be…

Computation and Language · Computer Science 2020-10-23 Tanya Goyal , Greg Durrett

Language models, while capable of generating remarkably coherent and seemingly accurate text, can occasionally produce undesirable content, including harmful or toxic outputs. In this paper, we present a new two-stage approach to detect and…

Machine Learning · Computer Science 2025-11-11 Bao Nguyen , Binh Nguyen , Duy Nguyen , Viet Anh Nguyen

We present an automated, contrastive evaluation pipeline for auditing the behavioral impact of interventions on large language models. Given a base model $M_1$ and an intervention model $M_2$, our method compares their free-form,…

Computation and Language · Computer Science 2026-05-07 Quintin Pope , Ajay Hayagreeve Balaji , Jacques Thibodeau , Xiaoli Fern

Large Language Models have demonstrated remarkable capabilities across diverse tasks, yet they frequently generate hallucinations outputs that are fluent but factually incorrect or unsupported. We propose Counterfactual Probing, a novel…

Computation and Language · Computer Science 2025-08-05 Yijun Feng

Causal inference has shown potential in enhancing the predictive accuracy, fairness, robustness, and explainability of Natural Language Processing (NLP) models by capturing causal relationships among variables. The emergence of generative…

Computation and Language · Computer Science 2025-03-24 Xiaoyu Liu , Paiheng Xu , Junda Wu , Jiaxin Yuan , Yifan Yang , Yuhang Zhou , Fuxiao Liu , Tianrui Guan , Haoliang Wang , Tong Yu , Julian McAuley , Wei Ai , Furong Huang

To examine whether intersectional bias can be observed in language generation, we examine \emph{GPT-2} and \emph{GPT-NEO} models, ranging in size from 124 million to ~2.7 billion parameters. We conduct an experiment combining up to three…

Computation and Language · Computer Science 2021-07-19 Liam Magee , Lida Ghahremanlou , Karen Soldatic , Shanthi Robertson

Consider the case where causal relations among variables can be described as a Gaussian linear structural equation model. This paper deals with the problem of clarifying how the variance of a response variable would have changed if a…

Artificial Intelligence · Computer Science 2012-07-09 Zhihong Cai , Manabu Kuroki

Counterfactuals can explain classification decisions of neural networks in a human interpretable way. We propose a simple but effective method to generate such counterfactuals. More specifically, we perform a suitable diffeomorphic…

Machine Learning · Computer Science 2022-06-17 Ann-Kathrin Dombrowski , Jan E. Gerken , Klaus-Robert Müller , Pan Kessel

Understanding the behavior of large language models (LLMs) is crucial for ensuring their safe and reliable use. However, existing explainable AI (XAI) methods for LLMs primarily rely on word-level explanations, which are often…

Computation and Language · Computer Science 2025-08-08 Furui Cheng , Vilém Zouhar , Robin Shing Moon Chan , Daniel Fürst , Hendrik Strobelt , Mennatallah El-Assady

Existing tools for explaining complex models and systems are associational rather than causal and do not provide mechanistic understanding. We propose a new notion called counterfactual explainability for causal attribution that is…

Machine Learning · Statistics 2025-10-07 Zijun Gao , Qingyuan Zhao

This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original ap-proach to train conditional language models from scratch by only using reinforcement learning (RL). AsRL methods unsuccessfully scale to large…

Artificial Intelligence · Computer Science 2021-09-21 Alice Martin Donati , Guillaume Quispe , Charles Ollion , Sylvain Le Corff , Florian Strub , Olivier Pietquin

Treebanks traditionally treat punctuation marks as ordinary words, but linguists have suggested that a tree's "true" punctuation marks are not observed (Nunberg, 1990). These latent "underlying" marks serve to delimit or separate…

Computation and Language · Computer Science 2019-06-28 Xiang Lisa Li , Dingquan Wang , Jason Eisner

Adversarial examples in NLP are receiving increasing research attention. One line of investigation is the generation of word-level adversarial examples against fine-tuned Transformer models that preserve naturalness and grammaticality.…

Computation and Language · Computer Science 2022-10-24 Maximilian Mozes , Bennett Kleinberg , Lewis D. Griffin

This work describes the task of metaphoric paraphrase generation, in which we are given a literal sentence and are charged with generating a metaphoric paraphrase. We propose two different models for this task: a lexical replacement…

Computation and Language · Computer Science 2020-03-02 Kevin Stowe , Leonardo Ribeiro , Iryna Gurevych
‹ Prev 1 8 9 10 Next ›