arXiv ·
This paper introduces ProgramFC, a fact-checking model that decomposes complex claims into simpler sub-tasks using a library of functions. The model uses LLMs to generate reasoning programs and executes them by delegating sub-tasks, enhancing explainability and data efficiency. Experiments on fact-checking datasets demonstrate ProgramFC's superior performance compared to baseline methods, with publicly available code and data.
KAUST ·
KAUST researchers led by Pascal Saikaly are developing microbial electrochemical technologies (METs) for wastewater treatment and energy recovery. The team combines METs with membrane filtration, creating a hybrid air-biocathode microbial fuel cell-membrane bioreactor (MFC-MBR) for simultaneous wastewater treatment and ultrafiltration. This system uses an electrically conductive ultrafiltration membrane as a biocathode for electricity generation and passive oxygen transfer. Why it matters: This innovation offers a sustainable approach to water reclamation by reducing energy consumption and producing reusable water, which addresses critical water scarcity challenges in the region and globally.
KAUST ·
KAUST researchers have developed a saliva-powered microbial fuel cell (MFC) that generates electricity using electrogenic bacteria to consume waste and release electrons. The micro-MFC uses graphene as an anode and an air cathode, achieving high current densities (1190 A m-3). The MFC produced 40 times more power than through the use of a carbon cloth anode. Why it matters: This technology offers a novel way to power lab-on-chip or portable diagnostic devices, particularly in remote or dangerous areas, and may offer alternatives to energy-intensive water purification technologies.
MBZUAI ·
Liangming Pan from UCSB presented research on building reliable generative AI agents by integrating symbolic representations with LLMs. The neuro-symbolic strategy combines the flexibility of language models with precise knowledge representation and verifiable reasoning. The work covers Logic-LM, ProgramFC, and learning from automated feedback, aiming to address LLM limitations in complex reasoning tasks. Why it matters: Improving the reliability of LLMs is crucial for high-stakes applications in finance, medicine, and law within the region and globally.