| Challenge: | Existing explanations of a model's behavior are not used in interactive tasks like Visual Question Answering (VQA). |
| Approach: | They analyze existing explanations and their role in making a VQA model more predictable to a human by using human-in-the-loop approaches that treat the model as a black-box. |
| Outcome: | The proposed explanations make a model more predictable to humans, whereas human-in-the-loop approaches treat it as a black-box do. |
Similar Papers
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to visual question answering represent images using pre-trained CNNs . but they rarely provide any insight, apart from the answer, into the VQA process . |
| Approach: | They propose to break up the end-to-end VQA into two steps: explaining and reasoning . they first extract attributes and generate descriptions as explanations for an image . a reasoning module utilizes these explanations in place of the image to infer an answer . |
| Outcome: | The proposed system achieves comparable performance with baselines, but with added benefits of explanability and the ability to improve with higher quality explanations. |
Are Red Roses Red? Evaluating Consistency of Question-Answering Models (P19-1)
Copied to clipboard
| Challenge: | Existing question-answering systems are limited in their ability to test reasoning and comprehension. |
| Approach: | They propose a method to automatically extract implications from QA datasets to evaluate models' consistency . they use a heuristic to generate such questions and retrain models with implication-augmented data . |
| Outcome: | The proposed method shows that generated implications are well formed and valid . retraining with implication-augmented data improves consistency on both synthetic and human-generated implications. |
Do Explanations Help Users Detect Errors in Open-Domain QA? An Evaluation of Spoken vs. Visual Explanations (2021.findings-acl)
Copied to clipboard
| Challenge: | despite interest in explainable AI, there is increasing skepticism as to whether explanations are useful to end-users in downstream applications. |
| Approach: | They conduct user studies to measure whether explanations help users decide when to accept or reject an ODQA system's answer. |
| Outcome: | The proposed study shows that explanations outperform baselines across modalities but the best strategy varies with the modality. |
Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? (2020.acl-main)
Copied to clipboard
| Challenge: | a new study examines the impact of algorithmic explanations on simulatability of machine learning models . a model is simulatable when a person can predict its behavior on new inputs . |
| Approach: | They conduct human subject tests to isolate effect of algorithmic explanations on simulatability . they find ratings of explanations are not predictive of how helpful they are . |
| Outcome: | The results provide the first reliable estimates of how explanations influence simulatability . they show that ratings are not predictive of how helpful explanations are . |
On the Diversity and Limits of Human Explanations (2022.naacl-main)
Copied to clipboard
| Challenge: | a growing effort in NLP aims to build datasets of human explanations, but it remains unclear whether they serve their intended goals. |
| Approach: | They argue that the term "explanation" is overloaded and refers to a broad range of notions with different properties and ramifications. |
| Outcome: | The proposed datasets examine the diversity of explanations and their use in NLP. |
What’s Different between Visual Question Answering for Machine “Understanding” Versus for Accessibility? (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing benchmarking datasets for visual question answering focus on machine "understanding" but it remains unclear how progress on those datasets corresponds to improvements in this real-world use case. |
| Approach: | They evaluate the visual question answering task by evaluating a variety of VQA models. |
| Outcome: | The proposed model can achieve high scores on tasks thought to require human-like comprehension, including image tagging and captioning. |
The Illusion of Competence: Evaluating the Effect of Explanations on Users’ Mental Models of Visual Question Answering Systems (2024.emnlp-main)
Copied to clipboard
Judith Sieker, Simeon Junker, Ronja Utescher, Nazia Attari, Heiko Wersing, Hendrik Buschmeier, Sina Zarrieß
| Challenge: | Using visual inputs, we hypothesize that explanations will make limited AI capabilities more transparent to users, but our results show that explanation increases users’ perceptions of the system’s competence regardless of its actual performance. |
| Approach: | They employ a visual question answer and explanation task where participants control the AI system’s limitations by manipulating visual inputs. |
| Outcome: | The proposed explanations do not increase users’ perceptions of the system’s competence regardless of its actual performance. |
Learning to Explain Selectively: A Case Study on Question Answering (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in machine learning (ML) have obstructed the use of NNs. |
| Approach: | They propose to learn to explain"selectively" for each decision that the user makes . they use a model to choose the best explanation from a set of candidates and update this model with feedback . |
| Outcome: | The proposed model improves human performance on a question-based task for experts and crowdworkers. |
On the Interaction of Belief Bias and Explanations (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to evaluate explainability fail to account for belief biases affecting human performance . previous studies have shown that neural models can make confident predictions relying on artifacts . |
| Approach: | They propose to account for belief bias in explainability by using models of varying quality and adversarial examples. |
| Outcome: | The proposed methods show that results change when using models of varying quality and adversarial examples. |
Uncovering the Full Potential of Visual Grounding Methods in VQA (2024.acl-long)
Copied to clipboard
| Challenge: | Visual Grounding (VG) methods in VQA aim to strengthen a model's reliance on question-relevant visual information. |
| Approach: | They propose to strengthen a model's reliance on question-relevant visual information by using a visual grounding method that is based on a question-related visual input. |
| Outcome: | The proposed methods can be much more effective when evaluation conditions are corrected. |