Social Simulacra: Creating Populated Prototypes for Social Computing Systems

Park, Joon Sung; Popowski, Lindsay; Cai, Carrie J.; Morris, Meredith Ringel; Liang, Percy; Bernstein, Michael S.

doi:10.1145/3526113.3545616

Cited by 112 publications

(139 citation statements)

References 44 publications

Supporting

Mentioning

134

Contrasting

Unclassified

Order By: Relevance

“…Our hypothesis (based on qualitative observation) is that ScatterShot consistently selects examples that represent patterns not contained in the seed examples, e.g., negative examples (where the outcome is N/A) when all seed examples are positive. While ScatterShot helps users explore most patterns in the unlabeled data as they reach higher 𝑛, early gains are especially useful in practice when users have low annotation budgets, e.g., prior work notes users selecting as few as five or ten examples [32,38].…”

Section: Resultsmentioning

confidence: 99%

ScatterShot: Interactive In-context Example Curation for Text Transformation

Weld

et al. 2023

Proceedings of the 28th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

The in-context learning capabilities of LLMs like GPT-3 allow annotators to customize an LLM to their specific tasks with a small number of examples. However, users tend to include only the most obvious patterns when crafting examples, resulting in underspecified in-context functions that fall short on unseen cases. Further, it is hard to know when "enough" examples have been included even for known patterns. In this work, we present ScatterShot, an interactive system for building high-quality demonstration sets for in-context learning. ScatterShot iteratively slices unlabeled data into task-specific patterns, samples informative inputs from underexplored or not-yet-saturated slices in an active learning manner, and helps users label more efficiently with the help of an LLM and the current example set. In simulation studies on two text perturbation scenarios, ScatterShot sampling improves the resulting few-shot functions by 4-5 percentage points over random sampling, with less variance as more examples are added. In a user study, ScatterShot greatly helps users in covering different patterns in the input space and labeling in-context examples more efficiently, resulting in better in-context learning and less user effort.

show abstract

Section: Resultsmentioning

confidence: 99%

ScatterShot: Interactive In-context Example Curation for Text Transformation

Weld

et al. 2023

Proceedings of the 28th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

show abstract

“…The short-term component temporarily buffers recent perceptions, while long-term memory consolidates important information over time. For instance, [109] employs a dual-layered memory structure to store an agent's experiences and knowledge, comprising a long-term memory and a shortterm memory. Long-term memory is utilized to preserve the agent's understanding and summarization of the entire world, while short-term memory is employed to retain the agent's comprehension and annotations of individual events.…”

Section: Memory Modulementioning

confidence: 99%

Genomic Surveillance for SARS-CoV-2 — China, September 26, 2022 to January 29, 2023

Wang¹,

Niu²,

Su³

et al. 2023

China CDC Weekly

View full text Add to dashboard Cite

Introduction: The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has generated 2,431 variants over the course of its global transmission over the past 3 years. To better evaluate the genomic variation of SARS-CoV-2 before and after the optimization of coronavirus disease 2019 (COVID-19) prevention and control strategies, we analyzed the genetic evolution branch composition and genomic variation of SARS-CoV-2 in both domestic and imported cases in China (the data from Hong Kong and Macau Special Administrativc Regions and Taiwan, China were not included) from September 26, 2022 to January 29, 2023.Methods: Analysis of the number of genome sequences, sampling time, dynamic changes of evolutionary branches, origin, and clinical typing of SARS-CoV-2 variants submitted by 31 provincial-level administrative divisions (PLADs) and Xinjiang Production and Construction Corp (XPCC) was conducted to assess the accuracy and timeliness of SARS-CoV-2 variant surveillance.Results: From September 26, 2022 to January 29, 2023, 20,013 valid genome sequences of domestic cases were reported in China, with 72 evolutionary branches. Additionally, 1,978 valid genome sequences of imported cases were reported, with 169 evolutionary branches. The prevalence of the Omicron variants of SARS-CoV-2 in both domestic and imported cases was consistent with that of international epidemic variants.Conclusions: This study provides an overview of the prevalence of Omicron variants of SARS-CoV-2 in China. After optimizing COVID-19 prevention and control strategies, no novel Omicron variants of SARS-CoV-2 with altered biological characteristics or public health significance have been identified since

show abstract

“…LLMs are trained on an existing corpus that may contain biased and problematic information [27,77]. Many have also suggested that cautions should be taken when using LLMs, particularly in the field of healthcare delivery [44].…”

Section: Ethical Considerationmentioning

confidence: 99%

Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data

Wei¹,

Kim²,

Jung³

et al. 2023

Preprint

View full text Add to dashboard Cite

Large Language Model How's your day so far? Prefix 📄 Information format 🤖 Persona modifier A Ongoing Dialogue History Insert as prompt Generate chatbot response B Work & Productivity ✅ Work done ✅ Rate productivity ✅ Other concerns at work ✅ What went well a C Going splendid so far. How is yours? I'm doing well, thanks for asking. Let's talk about your work and productivity yesterday. What work did you get done?Figure 1: An overview of our chatbot running on a large language model through zero-shot response generation, with only a prefix A○ consisting of persona modifier and information format and the ongoing dialogue history B ○. The example conversation is carried on about work a ○. GPT-3 was used for an underlying large language model C ○. Refer to the online demo at https://naver-ai.github.io/llm-chatbot.

show abstract

Social Simulacra: Creating Populated Prototypes for Social Computing Systems

Cited by 112 publications

References 44 publications

ScatterShot: Interactive In-context Example Curation for Text Transformation

ScatterShot: Interactive In-context Example Curation for Text Transformation

Genomic Surveillance for SARS-CoV-2 — China, September 26, 2022 to January 29, 2023

Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data

Contact Info

Product

Resources

About