Language models still struggle on moral reasoning, despite their impressive performance in many other tasks. In particular, the Moral Scenarios task in MMLU (Multi-task Language Understanding) is among the worst performing tasks for many language models, including GPT-3. In this work, we propose a new prompting framework, Thought Experiments, to teach language models to do better moral reasoning using counterfactuals. Experiment results show that our framework elicits counterfactual questions and answers from the model, which in turn helps improve the accuracy on Moral Scenarios task by 9-16% compared to other zero-shot baselines. Interestingly, unlike math reasoning tasks, zero-shot Chain-of-Thought (CoT) reasoning doesn't work out of the box, and even reduces accuracy by around 4% compared to direct zero-shot. We further observed that with minimal human supervision in the form of 5 few-shot examples, the accuracy of the task can be improved to as much as 80%.

Natural Language Processing (NLP) domain is experiencing a revolution due to the capabilities of Pre-trained Large Language Models ( LLMs), fueled by ground-breaking Transformers architecture, resulting into unprecedented advancements. Their exceptional aptitude for assessing probability distributions of text sequences is the primary catalyst for outstanding improvement of both the precision and efficiency of NLP models. This paper introduces for the first time SecurityLLM, a pre-trained language model designed for cybersecurity threats detection. The SecurityLLM model is articulated around two key generative elements: SecurityBERT and FalconLLM. SecurityBERT operates as a cyber threat detection mechanism, while FalconLLM is an incident response and recovery system. To the best of our knowledge, SecurityBERT represents the inaugural application of BERT in cyber threat detection. Despite the unique nature of the input data and features, such as the reduced significance of syntactic structures in content classification, the suitability of BERT for this duty demonstrates unexpected potential, thanks to our pioneering study. We reveal that a simple classification model, created from scratch, and consolidated with LLMs, exceeds the performance of established traditional Machine Learning (ML) and Deep Learning (DL) methods in cyber threat detection, like Convolutional Neural Networks (CNN) or Recurrent Neural Networks (RNN). The experimental analysis, conducted using a collected cybersecurity dataset, proves that our SecurityLLM model can identify fourteen (14) different types of attacks with an overall accuracy of 98%

The rapid advancement of Large Language Models (LLMs) has led to extensive discourse regarding their potential to boost the return of quantitative stock trading strategies. This discourse primarily revolves around harnessing the remarkable comprehension capabilities of LLMs to extract sentiment factors which facilitate informed and high-frequency investment portfolio adjustments. To ensure successful implementations of these LLMs into the analysis of Chinese financial texts and the subsequent trading strategy development within the Chinese stock market, we provide a rigorous and encompassing benchmark as well as a standardized back-testing framework aiming at objectively assessing the efficacy of various types of LLMs in the specialized domain of sentiment factor extraction from Chinese news text data. To illustrate how our benchmark works, we reference three distinctive models: 1) the generative LLM (ChatGPT), 2) the Chinese language-specific pre-trained LLM (Erlangshen-RoBERTa), and 3) the financial domain-specific fine-tuned LLM classifier(Chinese FinBERT). We apply them directly to the task of sentiment factor extraction from large volumes of Chinese news summary texts. We then proceed to building quantitative trading strategies and running back-tests under realistic trading scenarios based on the derived sentiment factors and evaluate their performances with our benchmark. By constructing such a comparative analysis, we invoke the question of what constitutes the most important element for improving a LLM's performance on extracting sentiment factors. And by ensuring that the LLMs are evaluated on the same benchmark, following the same standardized experimental procedures that are designed with sufficient expertise in quantitative trading, we make the first stride toward answering such a question.

One impressive emergent capability of large language models (LLMs) is generation of code, including Structured Query Language (SQL) for databases. For the task of converting natural language text to SQL queries, Text-to-SQL, adaptation of LLMs is of paramount importance, both in in-context learning and fine-tuning settings, depending on the amount of adaptation data used. In this paper, we propose an LLM-based Text-to-SQL model SQL-PaLM, leveraging on PaLM-2, that pushes the state-of-the-art in both settings. Few-shot SQL-PaLM is based on an execution-based self-consistency prompting approach designed for Text-to-SQL, and achieves 77.3% in test-suite accuracy on Spider, which to our best knowledge is the first to outperform previous state-of-the-art with fine-tuning by a significant margin, 4%. Furthermore, we demonstrate that the fine-tuned SQL-PALM outperforms it further by another 1%. Towards applying SQL-PaLM to real-world scenarios we further evaluate its robustness on other challenging variants of Spider and demonstrate the superior generalization capability of SQL-PaLM. In addition, via extensive case studies, we demonstrate the impressive intelligent capabilities and various success enablers of LLM-based Text-to-SQL.

Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information. In this work, we propose search-augmented instruction learning (SAIL), which grounds the language generation and instruction following abilities on complex search results generated by in-house and external search engines. With an instruction tuning corpus, we collect search results for each training case from different search APIs and domains, and construct a new search-grounded training set containing \textit{(instruction, grounding information, response)} triplets. We then fine-tune the LLaMA-7B model on the constructed training set. Since the collected results contain unrelated and disputing languages, the model needs to learn to ground on trustworthy search results, filter out distracting passages, and generate the target response. The search result-denoising process entails explicit trustworthy information selection and multi-hop reasoning, since the retrieved passages might be informative but not contain the instruction-following answer. Experiments show that the fine-tuned SAIL-7B model has a strong instruction-following ability, and it performs significantly better on transparency-sensitive tasks, including open-ended question answering and fact checking.

The rapid advancement in machine learning has led to a surge in automatic data generation, making it increasingly challenging to differentiate between naturally or human-generated data and machine-generated data. Despite these advancements, the generation of creative data remains a challenge. This paper aims to investigate and comprehend the essence of creativity, both in general and within the context of natural language generation. We review various approaches to creative writing devices and tasks, with a specific focus on the generation of poetry. We aim to shed light on the challenges and opportunities in the field of creative data generation.

The recent release of large language model (LLM) based chatbots, such as ChatGPT, has attracted significant attention on foundation models. It is widely believed that foundation models will serve as the fundamental building blocks for future AI systems. As foundation models are in their early stages, the design of foundation model based systems has not yet been systematically explored. There is little understanding about the impact of introducing foundation models in software architecture. Therefore, in this paper, we propose a taxonomy of foundation model based systems, which classifies and compares the characteristics of foundation models and design options of foundation model based systems. Our taxonomy comprises three categories: foundation model pretraining and fine-tuning, architecture design of foundation model based systems, and responsible-AI-by-design. This taxonomy provides concrete guidance for making major design decisions when designing foundation model based systems and highlights trade-offs arising from design decisions.

Large Language Models (LLMs), consisting of 100 billion or more parameters, have demonstrated remarkable ability in complex multi-step reasoning tasks. However, the application of such generic advancements has been limited to a few fields, such as clinical or legal, with the field of financial reasoning remaining largely unexplored. To the best of our knowledge, the ability of LLMs to solve financial reasoning problems has never been dealt with, and whether it can be performed at any scale remains unknown. To address this knowledge gap, this research presents a comprehensive investigation into the potential application of LLMs in the financial domain. The investigation includes a detailed exploration of a range of subjects, including task formulation, synthetic data generation, prompting methods, and evaluation capability. Furthermore, the study benchmarks various GPT variants with parameter scales ranging from 2.8B to 13B, with and without instruction tuning, on diverse dataset sizes. By analyzing the results, we reveal that the ability to generate coherent financial reasoning first emerges at 6B parameters, and continues to improve with better instruction-tuning or larger datasets. Additionally, the study provides a publicly accessible dataset named sFIOG (Synthetic-Financial Investment Opinion Generation), consisting of 11,802 synthetic investment thesis samples, to support further research in the field of financial reasoning. Overall, this research seeks to contribute to the understanding of the efficacy of language models in the field of finance, with a particular emphasis on their ability to engage in sophisticated reasoning and analysis within the context of investment decision-making.

Large language models (LLMs) that have been trained on multilingual but not parallel text exhibit a remarkable ability to translate between languages. We probe this ability in an in-depth study of the pathways language model (PaLM), which has demonstrated the strongest machine translation (MT) performance among similarly-trained LLMs to date. We investigate various strategies for choosing translation examples for few-shot prompting, concluding that example quality is the most important factor. Using optimized prompts, we revisit previous assessments of PaLM's MT capabilities with more recent test sets, modern MT metrics, and human evaluation, and find that its performance, while impressive, still lags that of state-of-the-art supervised systems. We conclude by providing an analysis of PaLM's MT output which reveals some interesting properties and prospects for future work.

Words of estimative probability (WEP) are expressions of a statement's plausibility (probably, maybe, likely, doubt, likely, unlikely, impossible...). Multiple surveys demonstrate the agreement of human evaluators when assigning numerical probability levels to WEP. For example, highly likely corresponds to a median chance of 0.90+-0.08 in Fagen-Ulmschneider (2015)'s survey. In this work, we measure the ability of neural language processing models to capture the consensual probability level associated to each WEP. Firstly, we use the UNLI dataset (Chen et al., 2020) which associates premises and hypotheses with their perceived joint probability p, to construct prompts, e.g. "[PREMISE]. [WEP], [HYPOTHESIS]." and assess whether language models can predict whether the WEP consensual probability level is close to p. Secondly, we construct a dataset of WEP-based probabilistic reasoning, to test whether language models can reason with WEP compositions. When prompted "[EVENTA] is likely. [EVENTB] is impossible.", a causal language model should not express that [EVENTA&B] is likely. We show that both tasks are unsolved by off-the-shelf English language models, but that fine-tuning leads to transferable improvement.