This study investigates the feasibility of developing an Artificial General Recommender (AGR), facilitated by recent advancements in Large Language Models (LLMs). An AGR comprises both conversationality and universality to engage in natural dialogues and generate recommendations across various domains. We propose ten fundamental principles that an AGR should adhere to, each with its corresponding testing protocols. We proceed to assess whether ChatGPT, a sophisticated LLM, can comply with the proposed principles by engaging in recommendation-oriented dialogues with the model while observing its behavior. Our findings demonstrate the potential for ChatGPT to serve as an AGR, though several limitations and areas for improvement are identified.

Segment Anything Model (SAM) has attracted significant attention recently, due to its impressive performance on various downstream tasks in a zero-short manner. Computer vision (CV) area might follow the natural language processing (NLP) area to embark on a path from task-specific vision models toward foundation models. However, deep vision models are widely recognized as vulnerable to adversarial examples, which fool the model to make wrong predictions with imperceptible perturbation. Such vulnerability to adversarial attacks causes serious concerns when applying deep models to security-sensitive applications. Therefore, it is critical to know whether the vision foundation model SAM can also be fooled by adversarial attacks. To the best of our knowledge, our work is the first of its kind to conduct a comprehensive investigation on how to attack SAM with adversarial examples. With the basic attack goal set to mask removal, we investigate the adversarial robustness of SAM in the full white-box setting and transfer-based black-box settings. Beyond the basic goal of mask removal, we further investigate and find that it is possible to generate any desired mask by the adversarial attack.

The task of generating code from a natural language description, or NL2Code, is considered a pressing and significant challenge in code intelligence. Thanks to the rapid development of pre-training techniques, surging large language models are being proposed for code, sparking the advances in NL2Code. To facilitate further research and applications in this field, in this paper, we present a comprehensive survey of 27 existing large language models for NL2Code, and also review benchmarks and metrics. We provide an intuitive comparison of all existing models on the HumanEval benchmark. Through in-depth observation and analysis, we provide some insights and conclude that the key factors contributing to the success of large language models for NL2Code are "Large Size, Premium Data, Expert Tuning". In addition, we discuss challenges and opportunities regarding the gap between models and humans. We also create a website https://nl2code.github.io to track the latest progress through crowd-sourcing. To the best of our knowledge, this is the first survey of large language models for NL2Code, and we believe it will contribute to the ongoing development of the field.

Although large language models (LLMs) have been touted for their ability to generate natural-sounding text, there are growing concerns around possible negative effects of LLMs such as data memorization, bias, and inappropriate language. Unfortunately, the complexity and generation capacities of LLMs make validating (and correcting) such concerns difficult. In this work, we introduce ReLM, a system for validating and querying LLMs using standard regular expressions. ReLM formalizes and enables a broad range of language model evaluations, reducing complex evaluation rules to simple regular expression queries. Our results exploring queries surrounding memorization, gender bias, toxicity, and language understanding show that ReLM achieves up to 15x higher system efficiency, 2.5x data efficiency, and increased statistical and prompt-tuning coverage compared to state-of-the-art ad-hoc queries. ReLM offers a competitive and general baseline for the increasingly important problem of LLM validation.

In this work, we determined whether large language models (LLMs) are psychologically safe. We designed unbiased prompts to systematically evaluate LLMs from a psychological perspective. First, we tested three different LLMs by using two personality tests: Short Dark Triad (SD-3) and Big Five Inventory (BFI). All models scored higher than the human average on SD-3, suggesting a relatively darker personality pattern. Despite being instruction fine-tuned with safety metrics to reduce toxicity, InstructGPT and FLAN-T5 still showed implicit dark personality patterns; both models scored higher than self-supervised GPT-3 on the Machiavellianism and narcissism traits on SD-3. Then, we evaluated the LLMs in the GPT-3 series by using well-being tests to study the impact of fine-tuning with more training data. We observed a continuous increase in the well-being scores of GPT-3 and InstructGPT. Following these observations, we showed that instruction fine-tuning FLAN-T5 with positive answers from BFI could effectively improve the model from a psychological perspective. On the basis of the findings, we recommended the application of more systematic and comprehensive psychological metrics to further evaluate and improve the safety of LLMs.

The causal capabilities of large language models (LLMs) is a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy. We further our understanding of LLMs and their causal implications, considering the distinctions between different types of causal reasoning tasks, as well as the entangled threats of construct and measurement validity. LLM-based methods establish new state-of-the-art accuracies on multiple causal benchmarks. Algorithms based on GPT-3.5 and 4 outperform existing algorithms on a pairwise causal discovery task (97%, 13 points gain), counterfactual reasoning task (92%, 20 points gain), and actual causality (86% accuracy in determining necessary and sufficient causes in vignettes). At the same time, LLMs exhibit unpredictable failure modes and we provide some techniques to interpret their robustness. Crucially, LLMs perform these causal tasks while relying on sources of knowledge and methods distinct from and complementary to non-LLM based approaches. Specifically, LLMs bring capabilities so far understood to be restricted to humans, such as using collected knowledge to generate causal graphs or identifying background causal context from natural language. We envision LLMs to be used alongside existing causal methods, as a proxy for human domain knowledge and to reduce human effort in setting up a causal analysis, one of the biggest impediments to the widespread adoption of causal methods. We also see existing causal methods as promising tools for LLMs to formalize, validate, and communicate their reasoning especially in high-stakes scenarios. In capturing common sense and domain knowledge about causal mechanisms and supporting translation between natural language and formal methods, LLMs open new frontiers for advancing the research, practice, and adoption of causality.

In this paper, we propose MPC (Modular Prompted Chatbot), a new approach for creating high-quality conversational agents without the need for fine-tuning. Our method utilizes pre-trained large language models (LLMs) as individual modules for long-term consistency and flexibility, by using techniques such as few-shot prompting, chain-of-thought (CoT), and external memory. Our human evaluation results show that MPC is on par with fine-tuned chatbot models in open-domain conversations, making it an effective solution for creating consistent and engaging chatbots.

A consistent body of evidence suggests that dream reports significantly vary from other types of textual transcripts with respect to semantic content. Furthermore, it appears to be a widespread belief in the dream/sleep research community that dream reports constitute rather ``unique'' strings of text. This might be a notable issue for the growing amount of approaches using natural language processing (NLP) tools to automatically analyse dream reports, as they largely rely on neural models trained on non-dream corpora scraped from the web. In this work, I will adopt state-of-the-art (SotA) large language models (LLMs), to study if and how dream reports deviate from other human-generated text strings, such as Wikipedia. Results show that, taken as a whole, DreamBank does not deviate from Wikipedia. Moreover, on average, single dream reports are significantly more predictable than Wikipedia articles. Preliminary evidence suggests that word count, gender, and visual impairment can significantly shape how predictable a dream report can appear to the model.

This paper presents our contribution to the MEDIQA-2023 Dialogue2Note shared task, encompassing both subtask A and subtask B. We approach the task as a dialogue summarization problem and implement two distinct pipelines: (a) a fine-tuning of a pre-trained dialogue summarization model and GPT-3, and (b) few-shot in-context learning (ICL) using a large language model, GPT-4. Both methods achieve excellent results in terms of ROUGE-1 F1, BERTScore F1 (deberta-xlarge-mnli), and BLEURT, with scores of 0.4011, 0.7058, and 0.5421, respectively. Additionally, we predict the associated section headers using RoBERTa and SciBERT based classification models. Our team ranked fourth among all teams, while each team is allowed to submit three runs as part of their submission. We also utilize expert annotations to demonstrate that the notes generated through the ICL GPT-4 are better than all other baselines. The code for our submission is available.

The'Fox & Friends' co-hosts discussed concerns surrounding artificial intelligence and how it will impact the internet moving forward. Astrophysicist Neil deGrasse Tyson sees artificial intelligence as a much-needed stress-test for modern society, with a view that it will lead humanity to refine some of its more outdated ideas and systems now that the "genie is out of the bottle." "Of course AI will replace jobs," Tyson said in comments to Fox News Digital. "Entire sectors of our economy have gone obsolete in the presence of technology ever since the dawn of the industrial era. "The historical flaw in the reasoning is to presume that when jobs disappear, there will be no other jobs for people to do," he argued. "More people are employed in the world than ever before, yet none of them are making buggy whips.