Papers by Francesca Toni
GrASP: A Library for Extracting and Exploring Human-Interpretable Textual Patterns (2022.lrec-1)
Copied to clipboard
| Challenge: | a Python library is available for extracting patterns from textual data. |
| Approach: | They propose a Python library for extracting patterns from textual data . it integrates a public implementation of the existing GrASP algorithm . |
| Outcome: | The proposed library integrates a public implementation of the existing GrASP algorithm. |
Can Large Language Models perform Relation-based Argument Mining? (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for RbAM fail to perform satisfactorily across different datasets. |
| Approach: | They propose to use relation-based argument mining to determine agreement (support) and disagreement (attack) relations amongst textual arguments in binary and ternary settings. |
| Outcome: | The proposed method outperforms the best performing (RoBERTa-based) baseline on two open-source LLMs and with GPT-3.5-turbo on several datasets for (binary and ternary) RbAM. |
Evaluating Uncertainty Quantification Methods in Argumentative Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | ArgLLMs are an explainable LLM framework for decision-making based on computational argumentation in which uncertainty quantification plays a critical role. |
| Approach: | They propose to integrate LLM UQ methods into argumentative LLMs to evaluate their performance on claim verification tasks. |
| Outcome: | The proposed method outperforms more complex approaches on claim verification tasks. |
Explanation-Based Human Debugging of NLP Models: A Survey (2021.tacl-1)
Copied to clipboard
| Challenge: | In this paper, we review literature that exploits explanations to enable humans to fix bugs in NLP models. |
| Approach: | They review literature that exploits explanations to enable humans to fix bugs in NLP models. |
| Outcome: | The proposed approach is described in detail in this paper and is based on three dimensions of the problem explanation-based human debugging (EBHD). |
Explainable Automated Fact-Checking for Public Health Claims (2020.emnlp-main)
Copied to clipboard
| Challenge: | a few blind spots exist in the state-of-the-art in fact-checking for political claims. |
| Approach: | They propose to use a dataset of 11.8K claims to explain fact-check labels for claims . they define and evaluate three coherence properties of explanation quality with humans . |
| Outcome: | The proposed model can be trained on in-domain data and evaluates its coherence properties with humans and computationally. |
A Graph-Based Method for Unsupervised Knowledge Discovery from Financial Texts (2022.lrec-1)
Copied to clipboard
| Challenge: | A financial analyst's work involves manually reviewing lengthy filings and financial news articles in order to extract relevant pieces of information. |
| Approach: | They propose an end-to-end, fully unsupervised method for knowledge discovery from financial texts that integrates existing resources to construct a knowledge graph of companies and related entities. |
| Outcome: | The proposed method calculates the environmental rating for companies in the S&P 500 based on company filings with the SEC and provides an independent assessment of its outputs with an independent MSCI source. |
FIND: Human-in-the-Loop Debugging Deep Text Classifiers (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models are limited in the number of available datasets and lack the necessary tools to improve them. |
| Approach: | They propose a framework which enables humans to debug deep learning text classifiers by disabling irrelevant hidden features. |
| Outcome: | Experiments show that using FIND, humans can improve CNN text classifiers trained on different types of imperfect datasets. |
Human-grounded Evaluations of Explanation Methods for Text Classification (D19-1)
Copied to clipboard
| Challenge: | Explainable Artificial Intelligence (XAI) is aimed at providing explanations for decisions made by AI systems. |
| Approach: | They propose to use model-agnostic and model-specific explanation methods for CNNs for text classification to provide human-grounded evaluations. |
| Outcome: | The proposed methods could be used to explain models' results and improve AIs and humans in many cases. |
Towards a Framework for Evaluating Explanations in Automated Fact Verification (2024.lrec-main)
Copied to clipboard
| Challenge: | A growing interest has emerged in rationalizing explanations to provide short and coherent justifications for predictions. |
| Approach: | They propose a formal framework for rationalizing explanations to support their evaluation systematically. |
| Outcome: | The proposed framework is tailored to rationalizing explanations of increasingly complex structures, from free-form explanations to argumentative explanations with the richest structure. |
Explainable Automated Fact-Checking: A Survey (2020.coling-main)
Copied to clipboard
| Challenge: | Steady progress has been made in fact-checking and its orthogonal tasks. |
| Approach: | They propose to use fact-checking explanations to explain predictions by comparing existing explanations against desirable properties to find out what makes for good explanations. |
| Outcome: | The proposed explanations are compared against desirable properties and show how they may lead to improvements in the research area. |