Large Reasoning Models (LRMs) with long chain-of-thought capabilities, optimized via reinforcement learning with verifiable rewards (RLVR), excel at objective reasoning tasks like mathematical problem solving and code generation. However, RLVR is known for degrading generation diversity, which causes LRMs to fall short on subjective reasoning that has multiple answers depending on different role perspectives. While recent studies recognize the importance of diversity-enhanced training in objective reasoning, limited attention has been given to subjective tasks. In this paper, we find that subjective reasoning can be improved by introducing perspective diversity and token-level diversity, with the former one providing a coherent scaffolding anchored to a real-world stakeholder group and the latter one broadening the answer search space. We propose MultiRole-R1, a diversity-enhanced training framework featuring an unsupervised data construction pipeline that synthesizes reasoning chains incorporating various role perspectives. It also employs reinforcement learning via Group Relative Policy Optimization with reward shaping, taking diversity as a reward signal in addition to verifiable reward. Training on subjective tasks solely, MultiRole-R1 increases the in-domain and out-of-domain accuracy by 14.1% and 7.64%, and even enhances the performance on advanced math reasoning such as AIME 2024. We further show that diversity is a more consistent indicator of accuracy than reasoning length.

--Japan's kairanban culture and idobata conversations have long functioned as traditional communication practices that foster nuanced dialogue among community members and contribute to the formation of social balance. Inspired by these information exchange processes, this study proposes a multi-agent inference framework (KCS+IBC) that integrates multiple large language models (LLMs) to achieve bias mitigation, improved explainability, and probabilistic prediction in sentiment analysis. In addition to sequentially sharing prediction results, the proposed method incorporates a mid-phase casual dialogue session to blend formal inference with individual perspectives and introduces probabilistic sentiment prediction. Experimental results show that KCS achieves accuracy comparable to that of a single LLM across datasets, while KCS+IBC exhibits a consistent decrease in entropy and a gradual increase in variance during the latter stages of inference, suggesting the framework's ability to balance aggregation and diversity of predictions. Future work will quantitatively assess the impact of these characteristics on bias correction and aim to develop more advanced sentiment analysis systems. Research in natural language processing (NLP) supports dialogue systems, document summarization, sentiment analysis and machine translation and it finds rapid real-world adoption across society [1]. Recent advances in large language models (LLMs) let us interpret ambiguous expressions and infer based on context, tasks that conventional methods could not handle, and they improve accuracy and flexibility in language understanding [2]. These benefits now reach all sectors.

Complex problem-solving requires cognitive flexibility--the capacity to entertain multiple perspectives while preserving their distinctiveness. This flexibility replicates the "wisdom of crowds" within a single individual, allowing them to "think with many minds." While mental simulation enables imagined deliberation, cognitive constraints limit its effectiveness. We propose synthetic deliberation, a Large Language Model (LLM)-based method that simulates discourse between agents embodying diverse perspectives, as a solution. Using a custom GPT-based model, we showcase its benefits: concurrent processing of multiple viewpoints without cognitive degradation, parallel exploration of perspectives, and precise control over viewpoint synthesis. By externalizing the deliberative process and distributing cognitive labor between parallel search and integration, synthetic deliberation transcends mental simulation's limitations. This approach shows promise for strategic planning, policymaking, and conflict resolution.

However, Moreover, the failure to acknowledge the socio-cultural concerns persist regarding the transparency and context context within which data is produced can introduce biases of data collection methodologies, especially when sourced into datasets. For example, algorithms trained on datasets through crowdsourcing platforms. Crowdsourcing often devoid of the historical context of segregation may inadvertently employs low-wage workers with poor working conditions perpetuate biases against certain minority groups and lacks consideration for the representativeness of annotators, [12]. Furthermore, the identities of workers involved in annotations leading to algorithms that fail to represent diverse are frequently overlooked, leading to a lack of diversity views and perpetuate biases against certain groups. To address in viewpoints captured within datasets. This bias is these limitations, we propose a methodology involving compounded by the common practice of aggregating annotations a co-design model that actively engages stakeholders at key through majority voting [5].

We study retrieving a set of documents that covers various perspectives on a complex and contentious question (e.g., will ChatGPT do more harm than good?). We curate a Benchmark for Retrieval Diversity for Subjective questions (BERDS), where each example consists of a question and diverse perspectives associated with the question, sourced from survey questions and debate websites. On this data, retrievers paired with a corpus are evaluated to surface a document set that contains diverse perspectives. Our framing diverges from most retrieval tasks in that document relevancy cannot be decided by simple string matches to references. Instead, we build a language model based automatic evaluator that decides whether each retrieved document contains a perspective. This allows us to evaluate the performance of three different types of corpus (Wikipedia, web snapshot, and corpus constructed on the fly with retrieved pages from the search engine) paired with retrievers. Retrieving diverse documents remains challenging, with the outputs from existing retrievers covering all perspectives on only 33.74% of the examples. We further study the impact of query expansion and diversity-focused reranking approaches and analyze retriever sycophancy. Together, we lay the foundation for future studies in retrieval diversity handling complex queries.

This practice can lead to more rational decision-making that is not heavily influenced by specific opinions or positions [12, 22, 23]. As the Internet is a primary source of information for many people and the volume of online information is immense, effectively helping people consume and share information from diverse perspectives is necessary but challenging [57, 93]. Researchers have proposed various support methods for this, including the development and use of computer technology. In particular, artificial intelligence (AI)-based recommendation systems have been designed to support efficient information consumption by learning users' demographic characteristics or online activity patterns and providing tailored information based on their preferences [77]. Although computer technology plays an important role in enabling people to access and share online information, it should be noted that providing information solely based on individuals' preferences and tendencies can inadvertently contribute to the formation of echo chambers [77], a phenomenon where individuals are exposed primarily to the like-minded groups or information, leading to a reinforcement of shared narratives [28]. Research has shown that echo chambers can have many negative outcomes, including the creation and dissemination of biased information [77], increased susceptibility to fake news [8, 27], resistance towards accepting scientific evidence [63], and the adoption of unbalanced perspectives [36]. To prevent users from becoming polarized towards a specific political stance, many studies have proposed the use of computer-based tools designed to present information from diverse perspectives [31, 48, 53, 62].

Collecting diverse human data on subjective NLP topics is costly and challenging. As Large Language Models (LLMs) have developed human-like capabilities, there is a recent trend in collaborative efforts between humans and LLMs for generating diverse data, offering potential scalable and efficient solutions. However, the extent of LLMs' capability to generate diverse perspectives on subjective topics remains an unexplored question. In this study, we investigate LLMs' capacity for generating diverse perspectives and rationales on subjective topics, such as social norms and argumentative texts. We formulate this problem as diversity extraction in LLMs and propose a criteria-based prompting technique to ground diverse opinions and measure perspective diversity from the generated criteria words. Our results show that measuring semantic diversity through sentence embeddings and distance metrics is not enough to measure perspective diversity. To see how far we can extract diverse perspectives from LLMs, or called diversity coverage, we employ a step-by-step recall prompting for generating more outputs from the model in an iterative manner. As we apply our prompting method to other tasks (hate speech labeling and story continuation), indeed we find that LLMs are able to generate diverse opinions according to the degree of task subjectivity.

Solve Problems That Matter: We serve some of the most important moments in people's lives. It's a responsibility we embrace by focusing obsessively on the issues that will have a quantifiable impact on our customers and our company growth. Yes Before No: We are optimistic about our ability to change lives by transforming outmoded processes. We believe our efforts can create a better future, and it is our attitude that will allow us to pull that future closer. Start With Why: We don't presume to understand the intentions of the people around us, whether coworkers or customers.

It is widely acknowledged that Ada Lovelace, born in the 19th century, was the first computer programmer but her contributions and that of many other brilliant women in science and technology have been erased and attributed to men. Even today, diverse voices in the male-dominated tech industry are overlooked and non-traditional backgrounds dismissed as "not techy enough". During a recent podcast series in collaboration with IBM, I had the opportunity to meet amazing women from multi-disciplinary backgrounds in key AI and technology roles at the tech giant. Their non-typical backgrounds give them an unique ability to identify opportunities as well as ethical gaps in AI that would be otherwise missed. Here are some highlights from our wide-ranging conversations that remind us of the critical importance of non-traditional backgrounds in technology.

Did you miss a session from the Future of Work Summit? This article was contributed by Wilson Pang, CTO at Appen. The new foundation of the artificial intelligence (AI) economy is flexible, remote work. Thanks to advances in technology that enable remote work at an unimaginable scale, organizations developing AI can now collaborate with people from almost anywhere, including previously inaccessible areas. People across the globe can now contribute to building AI in meaningful ways, particularly through data preparation and annotation work.