CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report)
- URL: http://arxiv.org/abs/2407.08497v2
- Date: Mon, 11 Nov 2024 11:19:27 GMT
- Title: CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report)
- Authors: Xiang Yin, Nico Potyka, Francesca Toni,
- Abstract summary: We propose an iterative algorithm named Counterfactual Explanations for Quantitative bipolar Argumentation frameworks (CE-QArg)
CE-QArg can identify valid and cost-effective counterfactual explanations based on two core modules, polarity and priority.
We discuss some formal properties of our counterfactual explanations and empirically evaluate CE-QArg on randomly generated QBAFs.
- Score: 18.505289553533164
- License:
- Abstract: There is a growing interest in understanding arguments' strength in Quantitative Bipolar Argumentation Frameworks (QBAFs). Most existing studies focus on attribution-based methods that explain an argument's strength by assigning importance scores to other arguments but fail to explain how to change the current strength to a desired one. To solve this issue, we introduce counterfactual explanations for QBAFs. We discuss problem variants and propose an iterative algorithm named Counterfactual Explanations for Quantitative bipolar Argumentation frameworks (CE-QArg). CE-QArg can identify valid and cost-effective counterfactual explanations based on two core modules, polarity and priority, which help determine the updating direction and magnitude for each argument, respectively. We discuss some formal properties of our counterfactual explanations and empirically evaluate CE-QArg on randomly generated QBAFs.
Related papers
- GRS-QA -- Graph Reasoning-Structured Question Answering Dataset [50.223851616680754]
We introduce the Graph Reasoning-Structured Question Answering dataset (GRS-QA), which includes both semantic contexts and reasoning structures for QA pairs.
Unlike existing M-QA datasets, GRS-QA explicitly captures intricate reasoning pathways by constructing reasoning graphs.
Our empirical analysis reveals that LLMs perform differently when handling questions with varying reasoning structures.
arXiv Detail & Related papers (2024-11-01T05:14:03Z) - Explaining Bayesian Networks in Natural Language using Factor Arguments. Evaluation in the medical domain [5.999262679775618]
We introduce the notion of factor argument independence to address the question of defining when arguments should be presented jointly or separately.
We present an algorithm that produces a list of all independent factor arguments ordered by their strength.
Our proposal has been validated in the medical domain through a human-driven evaluation study.
arXiv Detail & Related papers (2024-10-23T17:33:27Z) - Applying Attribution Explanations in Truth-Discovery Quantitative Bipolar Argumentation Frameworks [18.505289553533164]
Argument Attribution Explanations (AAEs) and Relation Attribution Explanations (RAEs) are used to explain the strength of arguments under gradual semantics.
We apply AAEs and RAEs to Truth Discovery QBAFs, which assess the trustworthiness of sources and their claims.
We find that both AAEs and RAEs can provide interesting explanations and can give non-trivial and surprising insights.
arXiv Detail & Related papers (2024-09-09T17:36:39Z) - Counterfactual and Semifactual Explanations in Abstract Argumentation: Formal Foundations, Complexity and Computation [19.799266797193344]
Argumentation-based systems often lack explainability while supporting decision-making processes.
Counterfactual and semifactual explanations are interpretability techniques.
We show that counterfactual and semifactual queries can be encoded in weak-constrained Argumentation Framework.
arXiv Detail & Related papers (2024-05-07T07:27:27Z) - Explaining Arguments' Strength: Unveiling the Role of Attacks and Supports (Technical Report) [13.644164255651472]
We propose a novel theory of Relation Attribution Explanations (RAEs)
RAEs offer fine-grained insights into the role of attacks and supports in quantitative bipolar argumentation towards obtaining the arguments' strength.
We show the application value of RAEs in fraud detection and large language models case studies.
arXiv Detail & Related papers (2024-04-22T16:02:48Z) - Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering [59.495717939664246]
Large language models have manifested remarkable capabilities by leveraging chain-of-thought (CoT) reasoning techniques to solve intricate questions.
We propose a novel approach called the selective filtering reasoner (SelF-Reasoner) that assesses the entailment relationship between the question and the candidate reasoning chain.
SelF-Reasoner improves the fine-tuned T5 baseline consistently over the ScienceQA, ECQA, and LastLetter tasks.
arXiv Detail & Related papers (2024-03-28T06:28:35Z) - Argument Attribution Explanations in Quantitative Bipolar Argumentation
Frameworks (Technical Report) [17.9926469947157]
We propose a novel theory of Argument Explanations (AAEs) by incorporating the spirit of feature attribution from machine learning.
AAEs are used to determine the influence of arguments towards topic arguments of interest.
We study desirable properties of AAEs, including some new ones and some partially adapted from the literature to our setting.
arXiv Detail & Related papers (2023-07-25T15:36:33Z) - Explanation Selection Using Unlabeled Data for Chain-of-Thought
Prompting [80.9896041501715]
Explanations that have not been "tuned" for a task, such as off-the-shelf explanations written by nonexperts, may lead to mediocre performance.
This paper tackles the problem of how to optimize explanation-infused prompts in a blackbox fashion.
arXiv Detail & Related papers (2023-02-09T18:02:34Z) - Logical Satisfiability of Counterfactuals for Faithful Explanations in
NLI [60.142926537264714]
We introduce the methodology of Faithfulness-through-Counterfactuals.
It generates a counterfactual hypothesis based on the logical predicates expressed in the explanation.
It then evaluates if the model's prediction on the counterfactual is consistent with that expressed logic.
arXiv Detail & Related papers (2022-05-25T03:40:59Z) - Maieutic Prompting: Logically Consistent Reasoning with Recursive
Explanations [71.2950434944196]
We develop Maieutic Prompting, which infers a correct answer to a question even from the noisy and inconsistent generations of language models.
Maieutic Prompting achieves up to 20% better accuracy than state-of-the-art prompting methods.
arXiv Detail & Related papers (2022-05-24T06:36:42Z) - From Checking to Inference: Actual Causality Computations as
Optimization Problems [79.87179017975235]
We present a novel approach to formulate different notions of causal reasoning, over binary acyclic models, as optimization problems.
We show that both notions are efficiently automated. Using models with more than $8000$ variables, checking is computed in a matter of seconds, with MaxSAT outperforming ILP in many cases.
arXiv Detail & Related papers (2020-06-05T10:56:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.