Large Language Models (LLMs), with their remarkable task-handling capabilities and innovative outputs, have catalyzed significant advancements across a spectrum of fields. However, their proficiency within specialized domains such as biomolecular studies remains limited. To address this challenge, we introduce Mol-Instructions, a comprehensive instruction dataset designed for the biomolecular domain. Mol-Instructions encompasses three key components: molecule-oriented instructions, protein-oriented instructions, and biomolecular text instructions. Each component aims to improve the understanding and prediction capabilities of LLMs concerning biomolecular features and behaviors. Through extensive instruction tuning experiments on LLMs, we demonstrate the effectiveness of Mol-Instructions in enhancing large models' performance in the intricate realm of biomolecular studies, thus fostering progress in the biomolecular research community. Mol-Instructions is publicly available for ongoing research and will undergo regular updates to enhance its applicability.

Text simplification (TS) systems rewrite text to make it more readable while preserving its content. However, what makes a text easy to read depends on the intended readers. Recent work has shown that pre-trained language models can simplify text using a wealth of techniques to control output simplicity, ranging from specifying only the desired reading grade level, to directly specifying low-level edit operations. Yet it remains unclear how to set these control parameters in practice. Existing approaches set them at the corpus level, disregarding the complexity of individual inputs and considering only one level of output complexity. In this work, we conduct an empirical study to understand how different control mechanisms impact the adequacy and simplicity of text simplification systems. Based on these insights, we introduce a simple method that predicts the edit operations required for simplifying a text for a specific grade level on an instance-per-instance basis. This approach improves the quality of the simplified outputs over corpus-level search-based heuristics.

Despite the ability to train capable LLMs, the methodology for maintaining their relevancy and rectifying errors remains elusive. To this end, the past few years have witnessed a surge in techniques for editing LLMs, the objective of which is to efficiently alter the behavior of LLMs within a specific domain without negatively impacting performance across other inputs. This paper embarks on a deep exploration of the problems, methods, and opportunities related to model editing for LLMs. In particular, we provide an exhaustive overview of the task definition and challenges associated with model editing, along with an in-depth empirical analysis of the most progressive methods currently at our disposal. We also build a new benchmark dataset to facilitate a more robust evaluation and pinpoint enduring issues intrinsic to existing techniques. Our objective is to provide valuable insights into the effectiveness and feasibility of each editing technique, thereby assisting the community in making informed decisions on the selection of the most appropriate method for a specific task or context. Code and datasets are available at https://github.com/zjunlp/EasyEdit.

Large language models are becoming increasingly pervasive and ubiquitous in society via deployment in sociotechnical systems. Yet these language models, be it for classification or generation, have been shown to be biased and behave irresponsibly, causing harm to people at scale. It is crucial to audit these language models rigorously. Existing auditing tools leverage either or both humans and AI to find failures. In this work, we draw upon literature in human-AI collaboration and sensemaking, and conduct interviews with research experts in safe and fair AI, to build upon the auditing tool: AdaTest (Ribeiro and Lundberg, 2022), which is powered by a generative large language model (LLM). Through the design process we highlight the importance of sensemaking and human-AI communication to leverage complementary strengths of humans and generative models in collaborative auditing. To evaluate the effectiveness of the augmented tool, AdaTest++, we conduct user studies with participants auditing two commercial language models: OpenAI's GPT-3 and Azure's sentiment analysis model. Qualitative analysis shows that AdaTest++ effectively leverages human strengths such as schematization, hypothesis formation and testing. Further, with our tool, participants identified a variety of failures modes, covering 26 different topics over 2 tasks, that have been shown before in formal audits and also those previously under-reported.

We propose eXtensible Prompt (X-Prompt) for prompting a large language model (LLM) beyond natural language (NL). X-Prompt instructs an LLM with not only NL but also an extensible vocabulary of imaginary words. Registering new imaginary words allows us to instruct the LLM to comprehend concepts that are difficult to describe with NL words, thereby making a prompt more descriptive. Also, these imaginary words are designed to be out-of-distribution (OOD) robust so that they can be (re)used like NL words in various prompts, distinguishing X-Prompt from soft prompt that is for fitting in-distribution data. We propose context-augmented learning (CAL) to learn imaginary words for general usability, enabling them to work properly in OOD (unseen) prompts. We experiment X-Prompt for zero-shot language style customization as a case study. The promising results of X-Prompt demonstrate its potential to facilitate advanced interaction beyond the natural language interface, bridging the communication gap between humans and LLMs.

Former USS Cole commander Kirk Lippold discusses how released Hamas hostages are arriving at an Israeli hospital on'Your World.' The U.S. Navy destroyer USS Carney has shot down an Iranian-made Houthi drone launched from Yemen, a military official confirms to Fox News. There was no damage to the Carney or any injuries to the U.S. personnel onboard. The warship had been sailing near the Bab el-Mandeb Strait at the time of the attack. The USS Carney shot down 15 drones and four cruise missiles fired from Yemen in the northern Red Sea last month during a nine-hour span, using its SM-2 surface-to-air missiles.

Your trip to the beach could someday be a lot safer, thanks to artificial intelligence. Researchers at the University of California Santa Cruz, led by Professor Alex Pang, are developing potentially life-saving A.I. algorithms geared toward detecting and monitoring potential dangers along the shoreline, according to the Santa Cruz Sentinel. The life-saving technology could also alert lifeguards of potential hazards and detect rip currents or riptides, which, according to water rescues and safety expert Gerry Dworkin, account for 80% of ocean lifeguard interventions. WHAT IS ARTIFICIAL INTELLIGENCE (AI)? Flags warn that the beach is closed to swimmers at Rockaway Beach in New York as high surf from Hurricane Franklin delivers strong rip tides and large waves to most of the eastern seaboard on August 31, 2023 in New York City.

Another former Google chief has issued an apocalyptic warning about artificial intelligence - saying it could'endanger' humans in five years. Billionaire Eric Schmidt, who served as Google's CEO from 2001 to 2011, said there were not enough safeguards placed on A.I and it was only a matter of time before humans lost control of the technology. He alluded to the dropping of nuclear weapons in Japan as a warning that without regulations in place, there may not be enough time to clean up the mess in the aftermath of potentially devastating societal impacts. Speaking at a health summit Tuesday, Schmidt said: 'After Nagasaki and Hiroshima, it took 18 years to get to a treaty over test bans and things like that. We don't have that kind of time today.'

The story of the computer hacker Gary McKinnon and his long battle against extradition to the US is to be turned into a feature film. It will tell the story of how a young man hunting for evidence of UFOs found his way into the Pentagon's system and carried out what US authorities described as "the biggest military computer hack of all time" and then faced the possibility of a long sentence in a US high-security prison. The film, The People v Gary McKinnon, will be directed by Paul McGuigan, who made Gangster Number 1 and Lucky Number Slevin. The screenplay is by Peter Harness, who has written scripts for Wallander, Doctor Who, McMafia and Sherlock as well as the film Is Anybody There? It will be produced by Wall to Wall Media and Warner Brothers.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. The Russian government is floating the idea of demanding a "loyalty agreement" from foreigners. A proposed law would restrict non-Russian residents from openly opposing the government, criticizing Russia's communist history or subverting traditional values. Foreign nationals would be required to sign an agreement prohibiting "hindering the activities of public authorities of the Russian Federation [or] discrediting in any form the foreign and domestic state policy of the Russian Federation, public authorities and their officials," according to translations from The Moscow Times.