Reinforcement learning with verifiable rewards (RLVR) for Large Reasoning Models rests on variance reduction, which requires both a reliable baseline and high prompt diversity within each training batch. This is especially difficult in multi-domain training for general reasoning models, where prompts from different tas...
Yunho Choi, Jongwon Lim, Woojin Ahn et al.· 0 citations
Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an ambiguous expression to its intended meaning. Although prior work has proposed disambiguation-oriented benchmarks probing the role of vision, we observe that existing benchmarks r...
Jingheng Pan, Xintong Wang, Longyue Wang et al.· 0 citations
Accurate and consistent Emergency Severity Index (ESI) assignment remains a persistent challenge in emergency departments, where highly variable free-text triage documentation contributes to mistriage and workflow inefficiencies. This study evaluates whether open-source small language models (SLMs) can serve as reliabl...
Manar Aljohani, Brandon Ho, Kenneth McKinley et al.· 0 citations
Repeated praise, canned reassurance, familiar contrasts, and conspicuous vocabulary are recurring subjects in discussions of large language models. Their interpretation depends on context: a conventional phrase may be useful, while a fluent answer may reinforce a false belief. This critical review examines linguistic h...
Shuai Wu, Xue Li, Zhijun Wang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Background: Clinical notes contain extensive duplicated text from templates, copy-paste, and auto-populated fields ("note bloat"), diluting clinical signal, limiting longitudinal context, and increasing large language model (LLM) costs.
Methods: TRACE removes note bloat using note-level EHR metadata to identify templ...
Jordan L. Cahoon, Chloe Stanwyck, Asad Aali et al.· 0 citations
Humans exhibit remarkable abilities to coordinate in groups. As large language models (LLMs) become more capable, it remains an open question whether they can demonstrate comparable adaptive coordination and whether they use the same strategies as humans. To better understand this, we compare LLM and human performance...
Sahaj Singh Maini, Robert L. Goldstone, Zoran Tiganj· 0 citations
Simulating real personalities with large language models requires grounding generation in authentic personal data. Existing evaluation approaches rely on demographic surveys, personality questionnaires, or short AI-led interviews as proxies, but lack direct assessment against what individuals actually said. We address...
Humans are susceptible to undesirable behaviours and privacy leaks under the influence of alcohol. This paper investigates drunk language, i.e., text written under the influence of alcohol, as a driver for safety failures in large language models (LLMs). We investigate three mechanisms for inducing drunk language in LL...
Anudeex Shetty, Aditya Joshi, Salil S. Kanhere· 0 citations
As large language models are increasingly used in high-stakes domains, it is essential that their outputs reflect not average} human preference, rather range of varying perspectives. Achieving such pluralism, however, remains challenging. Existing approaches consider limited values or rely on prompt-level interventions...
Shenyan Zheng, Jiayou Zhong, Anudeex Shetty et al.· 0 citations
Tool use, such as web search, has become a standard capability even in freely available large language models (LLMs). However, existing benchmarks evaluate temporal reasoning mainly in static, non-tool-using settings, which poorly reflect how LLMs perform temporal reasoning in practice. We introduce Time Puzzles, a con...
Social media platforms play a pivotal role in shaping political discourse, but the scale and rapid evolution of online content make systematic analysis difficult. We introduce an end-to-end framework for inducing an interpretable topic taxonomy from unlabeled text corpora. The framework combines embedding-based cluster...
We examine how the cost of transforming qualitative information into precise numerical estimates--a form of integration cost--creates a structural friction in expectations formation. To isolate this integration cost from the costs of information awareness and acquisition, we exploit sell-side analyst reports, in which...
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
