Posts

Showing posts from June, 2024

2024-06-26: Paper Summary: RELIC: Investigating Large Language Model Responses using Self-Consistency

Image
Figure 1 Cheng et al.: RELIC allows users to search for information from large language models (A), view the model’s top response, and understand the variations between response samples to verify the correctness of the generated information (B). For long-form generated text, users can inspect the consistency of each individual claim (C) and find contradicting or supporting evidence from other samples (D). Steps (1-6) illustrate the user’s verification process of InstructGPT’s response regarding Don Featherstone.(Figure 1 in original paper ) Large Language Models (LLMs) have revolutionized natural language processing, achieving remarkable performance across various tasks, such as translation, summarization, and question-answering. Despite their success, understanding and evaluating their responses remains a significant challenge. In the paper " RELIC (Response Evaluation through Linguistic Insight and Consistency)," published in CHI 2024 by Furui Cheng , VilĂ©m Zouhar , Si...

2024-06-12: Paper Summary: Exploring the Use of Personalized AI for Identifying Misinformation on Social Media

Image
Figure 1 Jahanbakhsh et al. Assess tweets with AI assistance (UI used in Step 3). Participants assess each tweet in their feed while seeing AI model predictions. As shown in this screenshot, the user is in the middle of an experiment and has assessed the top tweet, while the rest of the tweets in this feed (for which the AI model predictions are shown) have not been assessed yet. The AI model predictions may change in response to user feedback. The tweets for which the AI predictions have recently changed are shown on the left pane. Newly changed predictions are differentiated visually with a border and a notification icon, similar to the bottom tweet in the image (Figure 3 in original paper ). In recent years,  misinformation on social media  platforms has been a tremendous concern. The  spread of inaccurate or misleading information weakens the credibility of online content and also poses serious threats to social trust, public opinion, and even democratic pro...