While the reasoning capabilities of Large Language Models (LLMs) are steadily improving, they still lack the depth and nuance of human reasoning when it comes to fast-moving societal issues. Additionally, LLMs fall short if the data available for a topic on the internet is biased, for example, when certain viewpoints are under-represented online.

LLMs also suffer from the hallucination problem, occasionally generating outputs that are inaccurate or misleading in subtle ways that are difficult to detect.

Despite these limitations, LLMs can often generate a valuable set of initial arguments. Humans can then refine these arguments or study the information retrieved to craft better, more nuanced questions.

Beyond providing an initial set of arguments, AI tools can also assist with several operational tasks, such as:

• Detecting potential duplicate arguments.
• Summarizing and interpretting the information presented on topic pages. (See AI Post-processing)
• Offering a second opinion on the relative strength of submitted arguments.

Rigorous mathematical results show that the ranking algorithm is pretty fast at identifying the top arguments. With a bit of patience, you'll be surprised by the quality of the results that rise to the top!

For those with a mathematical background, it may initially appear that ranking \( n \) arguments requires on the order of \( n^2 \) pairwise comparisons. However, it can be shown that the correct order is \( n \log(n) \). To see why, consider a simpler, deterministic example: finding the largest number in a list of \( n \) numbers using pairwise comparisons. Basic algorithmic analysis shows that this takes \( O(n) \) comparisons. The platform’s setting is probabilistic rather than deterministic—because the outcomes of pairwise comparisons are noisy—and this changes the problem in important ways. Even so, it can still be shown that identifying the run time increases only to \( O(n \log(n)) \), not \( O(n^2) \).

For more details, see the section titled Simple does it: eliciting the Borda rule with naive sampling in this paper by Lee et al. (Learn more)

On nlite, fact-checking relies mainly on crowdsourced verification—a collaborative effort among users. This decentralized approach is often considered more reliable than fact-checking by a single organization, and it has grown in popularity across social media platforms [1, 2].

That said, the platform facilitates this process by making it mandatory for authors to select a Source Type when submitting an argument or counter. There are two source types to choose from: Self-explanatory and Linked References. The Self-explanatory type refers to arguments that are merely based on logical principles and do not require external references. In contrast, when the Linked References option is selected, the argument submitter acknowledges that (i) certain parts of the argument require external references, and that (ii) they are linking those references to the submission. That's where the name Linked References comes from. This requirement nudges argument submitters to check if any references are needed to support their claims and, if so, to provide them. (Learn more)

Our answer consists of two parts.

1. Friend groups: One way nlite is commonly used is to investigate controversial topics within friend groups. While people may have differing opinions in these environments, they often do not intentionally distort data to misrepresent the other side. In such cases, nlite serves as a tool to make discussions more efficient.

2. Broader environments: In more public or diverse settings, where bad-faith actors may be present, nlite incorporates safeguards to minimize manipulation. A current area of focus is the development of an algorithm that helps detect the possible presence of two subgroups of users: one with good intentions that aims at ranking arguments in the proper order, and another with bad intentions that aims at ranking arguments either in reverse order or randomly.

   It's important to note that if manipulative behavior is detected, the platform can always publicize it, potentially damaging the perpetrators' reputation more than any early benefits they might gain.

We suggest assessing arguments along the following dimensions:

• Logical coherence
• Inclusion of required references
• Clarity of expression
• Respectful tone

If you’ve reviewed the arguments on both sides and still feel unsure, that often means it’s time to ask new questions to dig deeper into the conversation.

However, if you believe the discussion is already fairly mature, here are a few tips that might help:

1. Use AI tools to summarize and interpret content. While AI may not be ideal for generating entirely new arguments from scratch, it excels at processing, organizing, and summarizing complex material. To facilitate this, the platform has a built-in AI tool. To access it, click the three dots next to the topic title and select AI Post-processing at the bottom of the menu. This opens a dedicated page where you can ask any questions about the topic page content. Responses are currently generated using ChatGPT, and the content submitted on the topic page is sent to this platform as context to guide the responses it provides. (Learn more)
2. Good decision-making doesn’t require absolute certainty. Total certainty is unrealistic. Strong decision-makers assess the information available to them and use it to make the most informed choice possible.

This is a valid concern, as it is very likely that a good argument will be expressed in various ways by different people. If the platform’s ranking algorithm functions properly, all of these variants will rise to the top, leading to redundancy among the top items. To address this, the platform includes a mechanism to identify and remove duplicate arguments.

When users click the Evaluate Arguments button under a given viewpoint, the platform occasionally asks the following question along with the two selected arguments: Are the following arguments (essentially) making the same point? Responses to these questions are used to identify and eliminate duplicate arguments. (Learn More)

Great question! nlite is a valuable tool in the following two scenarios: (1) You are new to a topic and want to learn about it quickly and efficiently, or (2) You are already knowledgeable in a particular area and wish to share your expertise with others but lack an effective platform to do so. These scenarios are discussed in more detail below.

For learners: If you are new to a topic, nlite helps you collect relevant information much more efficiently. This is due to the concise and to-the-point structure of topic pages and the rigor with which the top arguments are identified. Note that the alternative would be to spend many hours watching debates or study lengthy articles. Even then, you wouldn't know whether you've just learned about the insights of a specific group of experts, or whether what you've come across are truly the best arguments that ever exist for the viewpoints in question.

For experts: If you are already knowledgeable and experienced in a field (we all have our own areas of expertise!) and would like to enlighten society with your knowledge, but lack an effective platform to do so, nlite gives you a powerful opportunity to share your insights. You don't need to be a well-known public figure to make an impact on nlite! The platform is designed to create an environment where the strength of one's arguments determines their influence, not their financial, political, or social backgrounds.