The discovery of novel Ionic Liquids (ILs) is hindered by critical challenges in property prediction, including limited data, poor model accuracy, and fragmented workflows. Leveraging the power of Large Language Models (LLMs), we introduce AIonopedia, to the best of our knowledge, the first LLM agent for IL discovery. Powered by an LLM-augmented multimodal domain foundation model for ILs, AIonopedia enables accurate property predictions and incorporates a hierarchical search architecture for molecular screening and design. Trained and evaluated on a newly curated and comprehensive IL dataset, our model delivers superior performance. Complementing these results, evaluations on literature-reported systems indicate that the agent can perform effective IL modification. Moving beyond offline tests, the practical efficacy was further confirmed through real-world wet-lab validation, in which the agent demonstrated exceptional generalization capabilities on challenging out-of-distribution tasks, underscoring its ability to accelerate real-world IL discovery.

Recent improvements in the quality of the generations by large language models have spurred research into identifying machine-generated text. Systems proposed for the task often achieve high performance. However, humans and machines can produce text in different styles and in different domains, and it remains unclear whether machine generated-text detection models favour particular styles or domains. In this paper, we critically examine the classification performance for detecting machine-generated text by evaluating on texts with varying writing styles. We find that classifiers are highly sensitive to stylistic changes and differences in text complexity, and in some cases degrade entirely to random classifiers. We further find that detection systems are particularly susceptible to misclassify easy-to-read texts while they have high performance for complex texts.

Recent research trends in computational biology have increasingly focused on integrating text and bio-entity modeling, especially in the context of molecules and proteins. However, previous efforts like BioT5 faced challenges in generalizing across diverse tasks and lacked a nuanced understanding of molecular structures, particularly in their textual representations (e.g., IUPAC). This paper introduces BioT5+, an extension of the BioT5 framework, tailored to enhance biological research and drug discovery. BioT5+ incorporates several novel features: integration of IUPAC names for molecular understanding, inclusion of extensive bio-text and molecule data from sources like bioRxiv and PubChem, the multi-task instruction tuning for generality across tasks, and a numerical tokenization technique for improved processing of numerical data. These enhancements allow BioT5+ to bridge the gap between molecular representations and their textual descriptions, providing a more holistic understanding of biological entities, and largely improving the grounded reasoning of bio-text and bio-sequences. The model is pre-trained and fine-tuned with a large number of experiments, including \emph{3 types of problems (classification, regression, generation), 15 kinds of tasks, and 21 total benchmark datasets}, demonstrating the remarkable performance and state-of-the-art results in most cases. BioT5+ stands out for its ability to capture intricate relationships in biological data, thereby contributing significantly to bioinformatics and computational biology. Our code is available at \url{https://github.com/QizhiPei/BioT5}.

Large language models (LLMs) have established great success in the general domain of natural language processing. Their emerging task generalization and free-form dialogue capabilities can greatly help to design Chemical General Intelligence (CGI) to assist real-world research in chemistry. However, the existence of specialized language and knowledge in the field of chemistry, such as the highly informative SMILES notation, hinders the performance of general-domain LLMs in chemistry. To this end, we develop ChemDFM, the first LLM towards CGI. ChemDFM-13B is trained on 34B tokens from chemical literature, textbooks, and instructions as well as various data from the general domain. Therefore, it can store, understand, and reason over chemical knowledge and languages while still possessing advanced free-form language comprehension capabilities. Extensive quantitative evaluation shows that ChemDFM can significantly outperform the representative open-sourced LLMs. Moreover, ChemDFM can also surpass GPT-4 on a great portion of chemical tasks, despite the significant size difference. Further qualitative evaluations demonstrate the efficiency and effectiveness of ChemDFM in real-world research scenarios. We will open-source the ChemDFM model soon.

Generative pre-trained Transformer (GPT) has demonstrates its great success in natural language processing and related techniques have been adapted into molecular modeling. Considering that text is the most important record for scientific discovery, in this paper, we propose MolXPT, a unified language model of text and molecules pre-trained on SMILES (a sequence representation of molecules) wrapped by text. Briefly, we detect the molecule names in each sequence and replace them to the corresponding SMILES. In this way, the SMILES could leverage the information from surrounding text, and vice versa. The above wrapped sequences, text sequences from PubMed and SMILES sequences from PubChem are all fed into a language model for pre-training. Experimental results demonstrate that MolXPT outperforms strong baselines of molecular property prediction on MoleculeNet, performs comparably to the best model in text-molecule translation while using less than half of its parameters, and enables zero-shot molecular generation without finetuning.

We present an empirical evaluation of various outputs generated by nine of the most widely-available large language models (LLMs). Our analysis is done with off-the-shelf, readily-available tools. We find a correlation between percentage of memorized text, percentage of unique text, and overall output quality, when measured with respect to output pathologies such as counterfactual and logically-flawed statements, and general failures like not staying on topic. Overall, 80.0% of the outputs evaluated contained memorized data, but outputs containing the most memorized content were also more likely to be considered of high quality. We discuss and evaluate mitigation strategies, showing that, in the models evaluated, the rate of memorized text being output is reduced. We conclude with a discussion on potential implications around what it means to learn, to memorize, and to evaluate quality text.

There is no doubt that GPT-4, the latest iteration of the artificial-intelligence engine created by the company OpenAI, is innovative and cool. It can create a poem in the style of Basho, spell out the chord progression and time signature for a simple tune, and provide a seven-step recipe for a peanut-butter-and-jelly sandwich. When I asked it to write a musical about a narcissistic politician who holds the fate of the world in his hands, it delivered a story in two acts, with a protagonist named Alex Sterling who "navigates a maze of power, manipulation, and the consequences of his decisions," as he sings "Narcissus in the Mirror," "The Price of Power," and about a dozen other invented songs. Those songs appear to have been created out of thin air; certainly, no human conceived them. Still, Alex's story, which "explores themes of self-discovery, redemption, and the responsibility of leadership," is quite familiar.

Something incredible is happening in AI right now, and it is not entirely to the good. Everybody is talking about systems such as ChatGPT (OpenAI), Dall-E 2, and Lensa that generate text and images that look remarkably human-like, with astonishingly little effort. These systems can be incredibly fun to play with. Take this example, generated with ChatGPT by Henry Minsky (son of Marvin Minsky, one of AI's founders), who asked ChatGPT to "Describe losing your sock in the dryer in the style of the Declaration of Independence": When in the course of household events, it becomes necessary for one to dissolve the bonds that have connected a sock to its mate, and to assume among the powers of the laundry room, the separate and equal station to which the laws of physics and of household maintenance entitle it, a decent respect to the opinions of socks requires that it should declare the causes which impel it to go missing. We hold these truths to be self-evident, that all socks are created equal, and are endowed by their manufacturer with certain unalienable rights.

Large language models have emerged abilities including chain-of-thought to answer math word problems step by step. Solving math word problems not only requires abilities to disassemble problems via chain-of-thought but also needs to calculate arithmetic expressions correctly for each step. To the best of our knowledge, there is no work to focus on evaluating the arithmetic ability of large language models. In this work, we propose an arithmetic dataset MATH 401 to test the latest large language models including GPT-4, ChatGPT, InstrctGPT, Galactica, and LLaMA with various arithmetic expressions and provide a detailed analysis of the ability of large language models. MATH 401 and evaluation codes are released at \url{https://github.com/GanjinZero/math401-llm}.

Less than four months after releasing ChatGPT, the text-generating AI that seems to have pushed us into a science-fictional age of technology, OpenAI has unveiled a new product called GPT-4. Rumors and hype about this program have circulated for more than a year: Pundits have said that it would be unfathomably powerful, writing 60,000-word books from single prompts and producing videos out of whole cloth. Today's announcement suggests that GPT-4's abilities, while impressive, are more modest: It performs better than the previous model on standardized tests and other benchmarks, works across dozens of languages, and can take images as input--meaning that it's able, for instance, to describe the contents of a photo or a chart. Unlike ChatGPT, this new model is not currently available for public testing (although you can apply or pay for access), so the obtainable information comes from OpenAI's blog post, and from a New York Times story based on a demonstration. From what we know, relative to other programs, GPT-4 appears to have added 150 points to its SAT score, now a 1410 out of 1600, and jumped from the bottom to the top 10 percent of performers on a simulated bar exam.