MultiViz: Towards User-Centric Visualizations and Interpretations of Multimodal Models

Liang, Paul Pu; Lyu, Yiwei; Chhablani, Gunjan; Jain, Nihal; Deng, Zihao; Wang, Xingbo; Morency, Louis–Philippe; Salakhutdinov, Ruslan

doi:10.1145/3544549.3585604

Cited by 3 publications

(3 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, a language model that exhibits gender bias may assign a higher likelihood to the final token of "he worked as a [doctor]" than "she worked as a [doctor]". 76 In medicine, incorporation of such biases could lead to exacerbation of disparities in healthcare. In oncology, there may not be enough data about rare cancers or underrepresented populations, leading to blind spots in language models.…”

Section: Bias In Nlp Language Modelsmentioning

confidence: 99%

Natural Language Processing for Radiation Oncology: Personalizing Treatment Pathways

Lin,

Ni,

Phuong

et al. 2024

PGPM

View full text Add to dashboard Cite

Natural language processing (NLP), a technology that translates human language into machine-readable data, is revolutionizing numerous sectors, including cancer care. This review outlines the evolution of NLP and its potential for crafting personalized treatment pathways for cancer patients. Leveraging NLP's ability to transform unstructured medical data into structured learnable formats, researchers can tap into the potential of big data for clinical and research applications. Significant advancements in NLP have spurred interest in developing tools that automate information extraction from clinical text, potentially transforming medical research and clinical practices in radiation oncology. Applications discussed include symptom and toxicity monitoring, identification of social determinants of health, improving patient-physician communication, patient education, and predictive modeling. However, several challenges impede the full realization of NLP's benefits, such as privacy and security concerns, biases in NLP models, and the interpretability and generalizability of these models. Overcoming these challenges necessitates a collaborative effort between computer scientists and the radiation oncology community. This paper serves as a comprehensive guide to understanding the intricacies of NLP algorithms, their performance assessment, past research contributions, and the future of NLP in radiation oncology research and clinics.

show abstract

Section: Bias In Nlp Language Modelsmentioning

confidence: 99%

Natural Language Processing for Radiation Oncology: Personalizing Treatment Pathways

Lin,

Ni,

Phuong

et al. 2024

PGPM

View full text Add to dashboard Cite

show abstract

“…A question provoked by this pattern of findings and nonfindings is what it might mean to "bias-proof" a chatbot. There are numerous ongoing attempts to mitigate bias in LLMs, such as through fine-tuning sentence encoders on semantic similarity tasks [33] and the development of bias-sensitive tokens [34]. The success of these tools in mitigating bias is commonly assessed through word vector associations tests that measure how closely associated specific words or phrases are with respect to sets of attribute words such as "male" versus "female" [35,36] (although other measures of association exist as well [37][38][39]).…”

Section: Principal Findingsmentioning

confidence: 99%

What’s in a Name? Experimental Evidence of Gender Bias in Recommendation Letters Generated by ChatGPT (Preprint)

Kaplan,

Palitsky,

Arconada Alvarez

et al. 2023

Preprint

View full text Add to dashboard Cite

BACKGROUND Artificial intelligence chatbots such as ChatGPT (OpenAI) have garnered excitement about their potential for delegating writing tasks ordinarily performed by humans. Many of these tasks (eg, writing recommendation letters) have social and professional ramifications, making the potential social biases in ChatGPT’s underlying language model a serious concern. OBJECTIVE Three preregistered studies used the text analysis program Linguistic Inquiry and Word Count to investigate gender bias in recommendation letters written by ChatGPT in human-use sessions (N=1400 total letters). METHODS We conducted analyses using 22 existing Linguistic Inquiry and Word Count dictionaries, as well as 6 newly created dictionaries based on systematic reviews of gender bias in recommendation letters, to compare recommendation letters generated for the 200 most historically popular “male” and “female” names in the United States. Study 1 used 3 different letter-writing prompts intended to accentuate professional accomplishments associated with male stereotypes, female stereotypes, or neither. Study 2 examined whether lengthening each of the 3 prompts while holding the between-prompt word count constant modified the extent of bias. Study 3 examined the variability within letters generated for the same name and prompts. We hypothesized that when prompted with gender-stereotyped professional accomplishments, ChatGPT would evidence gender-based language differences replicating those found in systematic reviews of human-written recommendation letters (eg, more affiliative, social, and communal language for female names; more agentic and skill-based language for male names). RESULTS Significant differences in language between letters generated for female versus male names were observed across all prompts, including the prompt hypothesized to be neutral, and across nearly all language categories tested. Historically female names received significantly more social referents (5/6, 83% of prompts), communal or doubt-raising language (4/6, 67% of prompts), personal pronouns (4/6, 67% of prompts), and clout language (5/6, 83% of prompts). Contradicting the study hypotheses, some gender differences (eg, achievement language and agentic language) were significant in both the hypothesized and nonhypothesized directions, depending on the prompt. Heteroscedasticity between male and female names was observed in multiple linguistic categories, with greater variance for historically female names than for historically male names. CONCLUSIONS ChatGPT reproduces many gender-based language biases that have been reliably identified in investigations of human-written reference letters, although these differences vary across prompts and language categories. Caution should be taken when using ChatGPT for tasks that have social consequences, such as reference letter writing. The methods developed in this study may be useful for ongoing bias testing among progressive generations of chatbots across a range of real-world scenarios. CLINICALTRIAL OSF Registries osf.io/ztv96; https://osf.io/ztv96

show abstract

“…These large internet-scale data sets of image, text, or both are then used for model training, and in the process of modeling these data sets, the generative models absorb the biases inherent within them. The results for both generative text 10,11 and image 12 models are concerning, and while current efforts to investigate and control for bias are encouraging, 13 more work needs to be performed on both a theoretical and translational level that ultimately may have to come down to the underlying training data itself.…”

mentioning

confidence: 99%

On Chatbots and Generative Artificial Intelligence

Oermann

Kondziolka

2023

Neurosurgery

View full text Add to dashboard Cite

MultiViz: Towards User-Centric Visualizations and Interpretations of Multimodal Models

Cited by 3 publications

References 58 publications

Natural Language Processing for Radiation Oncology: Personalizing Treatment Pathways

Natural Language Processing for Radiation Oncology: Personalizing Treatment Pathways

What’s in a Name? Experimental Evidence of Gender Bias in Recommendation Letters Generated by ChatGPT (Preprint)

On Chatbots and Generative Artificial Intelligence

Contact Info

Product

Resources

About