ProtoTEx: Explaining Model Decisions with Prototype Tensors

Das, Anubrata; Chitrank, Gupta,; Kovatchev, Venelin; Lease, Matthew; Li, Junyi Jessy

doi:10.18653/v1/2022.acl-long.213

Cited by 8 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Explaining the veracity can also be formulated as a summarization problem over the gathered evidence to explain a fact-check (Atanasova, Simonsen, Lioma and Augenstein, 2020a;Kotonya and Toni, 2020b). Finally, case-based explanations can provide the user with similar, human-labeled instances (Das, Gupta, Kovatchev, Lease and Li, 2022).…”

Section: Explaining Veracity Predictionmentioning

confidence: 99%

“…As explainable NLP develops, automated fact-checking tasks also need to evolve and provide explanations that are accessible to human stakeholders yet faithful to the underlying model. For example, case-based explanations are mostly unexplored in automated fact-checking, although working systems have been proposed for propaganda detection (Das et al, 2022).…”

Section: Veracity Prediction and Explanationmentioning

confidence: 99%

See 1 more Smart Citation

The State of Human-centered NLP Technology for Fact-checking

Das,

Liu,

Kovatchev

et al. 2023

Preprint

View full text Add to dashboard Cite

Misinformation threatens modern society by promoting distrust in science, changing narratives in public health, heightening social polarization, and disrupting democratic elections and financial markets, among a myriad of other societal harms. To address this, a growing cadre of professional fact-checkers and journalists provide high-quality investigations into purported facts. However, these largely manual efforts have struggled to match the enormous scale of the problem. In response, a growing body of Natural Language Processing (NLP) technologies have been proposed for more scalable fact-checking. Despite tremendous growth in such research, however, practical adoption of NLP technologies for fact-checking still remains in its infancy today.In this work, we review the capabilities and limitations of the current NLP technologies for fact-checking. Our particular focus is to further chart the design space for how these technologies can be harnessed and refined in order to better meet the needs of human fact-checkers. To do so, we review key aspects of NLP-based fact-checking: task formulation, dataset construction, modeling, and human-centered strategies, such as explainable models and human-in-the-loop approaches. Next, we review the efficacy of applying NLP-based fact-checking tools to assist human fact-checkers. We recommend that future research include collaboration with fact-checker stakeholders early on in NLP research, as well as incorporation of human-centered design practices in model development, in order to further guide technology development for human use and practical adoption. Finally, we advocate for more research on benchmark development supporting extrinsic evaluation of human-centered fact-checking technologies.

show abstract

Section: Explaining Veracity Predictionmentioning

confidence: 99%

Section: Veracity Prediction and Explanationmentioning

confidence: 99%

The State of Human-centered NLP Technology for Fact-checking

Das,

Liu,

Kovatchev

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Hence, it is beneficial to encourage prototype segregation, that is, a broader projection onto the dataset and a more diverse representation of different samples. Besides normalizing prototype distances, which has been shown to influence prototype segregation (Das et al, 2022), proto-lm introduces an additional hyperparameter, K. This parameter controls the number of prototypes that each training example associates and disassociates with during training. As changing K also influences the decision-making process of the model by altering the number of samples the models compare for each input, we examine the impact of K on both prototype segregation and model performance.…”

Section: Prototype Uniqueness and Performancementioning

confidence: 99%

“…We employ workers from Amazon Mechanical Turk to crowdsource our evaluations and presented 3 workers with 50 examples each from the SST2 and QNLI datasets, along with explanations for the model's decisions in the settings mentioned in §5.2. We use the best performing models for SST2 and QNLI (those presented in Table 1), since previous studies found that the utility of PE's are reliant on model accuracy (Das et al, 2022). Additionally, we assess the accuracy of the human annotators in relation to the ground truth labels.…”

Section: Simulatability Experimentsmentioning

confidence: 99%

Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models

Xie,

Vosoughi,

Hassanpour

2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

Large Language Models (LLMs) have significantly advanced the field of Natural Language Processing (NLP), but their lack of interpretability has been a major concern. Current methods for interpreting LLMs are post hoc, applied after inference time, and have limitations such as their focus on low-level features and lack of explainability at higherlevel text units. In this work, we introduce proto-lm, a prototypical network-based whitebox framework that allows LLMs to learn immediately interpretable embeddings during the fine-tuning stage while maintaining competitive performance. Our method's applicability and interpretability are demonstrated through experiments on a wide range of NLP tasks, and our results indicate a new possibility of creating interpretable models without sacrificing performance. This novel approach to interpretability in LLMs can pave the way for more interpretable models without the need to sacrifice performance. We release our code at https://github.com/yx131/proto-lm.

show abstract

“…We adapt their idea and show how to apply it to clinical natural language. Recently, Ming et al (2019) and Das et al (2022) applied the concept of prototypical networks to text classification and showed how prototypical texts help to interpret predictions. In contrast to their work and following Chen et al (2019), we identify prototypical parts rather than whole documents by using label-wise attention.…”

Section: Manual Analysis By Medical Doctorsmentioning

confidence: 99%

This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text

Aken¹,

Papaioannou²,

Naik³

et al. 2022

Preprint

View full text Add to dashboard Cite

The use of deep neural models for diagnosis prediction from clinical text has shown promising results. However, in clinical practice such models must not only be accurate, but provide doctors with interpretable and helpful results. We introduce ProtoPatient, a novel method based on prototypical networks and label-wise attention with both of these abilities. ProtoPatient makes predictions based on parts of the text that are similar to prototypical patients-providing justifications that doctors understand. We evaluate the model on two publicly available clinical datasets and show that it outperforms existing baselines. Quantitative and qualitative evaluations with medical doctors further demonstrate that the model provides valuable explanations for clinical decision support.

show abstract

ProtoTEx: Explaining Model Decisions with Prototype Tensors

Cited by 8 publications

References 24 publications

The State of Human-centered NLP Technology for Fact-checking

The State of Human-centered NLP Technology for Fact-checking

Proto-lm: A Prototypical Network-Based Framework for Built-in Interpretability in Large Language Models

This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text

Contact Info

Product

Resources

About