Scientists working on the Short-Baseline Near Detector (SBND) at Fermi National Accelerator Laboratory have identified the detector’s first neutrino interactions.
Get the latest international news and world events from around the world.
Strong magnetic second harmonic generation effect discovered in two-dimensional CrPS₄ monolayer
A research team led by Professor Sheng Zhigao at the Hefei Institutes of Physical Science of the Chinese Academy of Sciences has, for the first time, observed the strong nonlinear magnetic second harmonic generation (MSHG) induced by the ferromagnetic order in monolayer CrPS4, with the help of the Steady High Magnetic Field Facility.
Unprecedented spin properties revealed in new artificial materials
In conjunction with research staff from the Charles University of Prague and the CFM (CSIC-UPV/EHU) center in San Sebastian, CIC nanoGUNE’s Nanodevices group has designed a new complex material with emerging properties in the field of spintronics. This discovery, published in the journal Nature Materials, opens up a range of fresh possibilities for the development of novel, more efficient and more advanced electronic devices, such as those that integrate magnetic memories into processors.
Scientists prove long-standing wave amplification theory
Physicists at the University of Southampton have tested and proven a 50-year-old theory for the first time using electro-magnetic waves. They have shown that the energy of waves can be increased by bouncing “twisted waves”—those with angular momentum—off of an object which is rotating in a specific way.
Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers
Abstract: Recent advancements in large language models (LLMs) have sparked optimism about their potential to accelerate scientific discovery, with a growing number of works proposing research agents that autonomously generate and validate new ideas. Despite this, no evaluations have shown that LLM systems can take the very first step of producing novel, expert-level ideas, let alone perform the entire research process. We address this by establishing an experimental design that evaluates research idea generation while controlling for confounders and performs the first head-to-head comparison between expert NLP researchers and an LLM ideation agent. By recruiting over 100 NLP researchers to write novel ideas and blind reviews of both LLM and human ideas, we obtain the first statistically significant conclusion on current LLM capabilities for research ideation: we find LLM-generated ideas are judged as more novel (p < 0.05) than human expert ideas while being judged slightly weaker on feasibility. Studying our agent baselines closely, we identify open problems in building and evaluating research agents, including failures of LLM self-evaluation and their lack of diversity in generation. Finally, we acknowledge that human judgements of novelty can be difficult, even by experts, and propose an end-to-end study design which recruits researchers to execute these ideas into full projects, enabling us to study whether these novelty and feasibility judgements result in meaningful differences in research outcome.
From: Chenglei Si [view email].