Software migration is garnering increasing attention with the evolution of software and society. Early studies mainly relied on handcrafted translation rules to translate between two languages, the translation process is error-prone and time-consuming. In recent years, researchers have begun to explore the use of pre-trained large language models (LLMs) in code translation. However, code translation is a complex task that LLMs would generate mistakes during code translation, they all produce certain types of errors when performing code translation tasks, which include (1) compilation error, (2) runtime error, (3) functional error, and (4) non-terminating execution. We found that the root causes of these errors are very similar (e.g. failure to import packages, errors in loop boundaries, operator errors, and more). In this paper, we propose a general corrector, namely Rectifier, which is a micro and universal model for repairing translation errors. It learns from errors generated by existing LLMs and can be widely applied to correct errors generated by any LLM. The experimental results on translation tasks between C++, Java, and Python show that our model has effective repair ability, and cross experiments also demonstrate the robustness of our method.

This study explores the innovative use of Large Language Models (LLMs) as analytical tools for interpreting complex financial regulations. The primary objective is to design effective prompts that guide LLMs in distilling verbose and intricate regulatory texts, such as the Basel III capital requirement regulations, into a concise mathematical framework that can be subsequently translated into actionable code. This novel approach aims to streamline the implementation of regulatory mandates within the financial reporting and risk management systems of global banking institutions. A case study was conducted to assess the performance of various LLMs, demonstrating that GPT-4 outperforms other models in processing and collecting necessary information, as well as executing mathematical calculations. The case study utilized numerical simulations with asset holdings -- including fixed income, equities, currency pairs, and commodities -- to demonstrate how LLMs can effectively implement the Basel III capital adequacy requirements. Keywords: Large Language Models, Prompt Engineering, LLMs in Finance, Basel III, Minimum Capital Requirements, LLM Ethics

For text-based AI systems to interact in the real world, causal reasoning is an essential skill. Since interventional data is costly to generate, we study to what extent an agent can learn causal reasoning from passive data. Specifically, we consider an axiomatic training setup where an agent learns from multiple demonstrations of a causal axiom (or rule), rather than incorporating the axiom as an inductive bias or inferring it from data values. A key question is whether the agent would learn to generalize from the axiom demonstrations to new scenarios. For example, if a transformer model is trained on demonstrations of the causal transitivity axiom over small graphs, would it generalize to applying the transitivity axiom over large graphs? Our results, based on a novel axiomatic training scheme, indicate that such generalization is possible. We consider the task of inferring whether a variable causes another variable, given a causal graph structure. We find that a 67 million parameter transformer model, when trained on linear causal chains (along with some noisy variations) can generalize well to new kinds of graphs, including longer causal chains, causal chains with reversed order, and graphs with branching; even when it is not explicitly trained for such settings. Our model performs at par (or even better) than many larger language models such as GPT-4, Gemini Pro, and Phi-3. Overall, our axiomatic training framework provides a new paradigm of learning causal reasoning from passive data that can be used to learn arbitrary axioms, as long as sufficient demonstrations can be generated.

Have you ever needed to write a recommendation letter for a student or co-worker and struggled to remember their contributions? Or maybe you're applying for a job or internship and don't know how to start your cover letter. Language Models (LMs), like ChatGPT [1], have become useful tools for writing various types of content, including professional documents like recommendation or cover letters [2, 3]. By providing just a few details, such as the person's name, age, gender, and current position, you can quickly generate initial drafts of these documents. With ChatGPT, users can quickly create an initial draft of a reference letter by specifying a few details about the individual.

Large language models (LLMs) can spend extra compute during inference to generate intermediate thoughts, which helps to produce better final responses. Since Chain-of-Thought (Wei et al., 2022), many such System 2 techniques have been proposed such as Rephrase and Respond (Deng et al., 2023a), System 2 Attention (Weston and Sukhbaatar, 2023) and Branch-Solve-Merge (Saha et al., 2023). In this work we investigate self-supervised methods to ``compile'' (distill) higher quality outputs from System 2 techniques back into LLM generations without intermediate reasoning token sequences, as this reasoning has been distilled into System 1. We show that several such techniques can be successfully distilled, resulting in improved results compared to the original System 1 performance, and with less inference cost than System 2. We posit that such System 2 distillation will be an important feature of future continually learning AI systems, enabling them to focus System 2 capabilities on the reasoning tasks that they cannot yet do well.

Prompting is a flexible and adaptable way of providing instructions to a Large Language Model (LLM). Contextual prompts include context in the form of a document or dialogue along with the natural language instructions to the LLM, often constraining the LLM to restrict facts to that of the given context while complying with the instructions. Masking the context, it acts as template for prompts. In this paper, we present an iterative method to generate better templates using an LLM from an existing set of prompt templates without revealing the context to the LLM. Multiple methods of optimising prompts using the LLM itself are explored to check the effect of few shot sampling methods on iterative propagation while maintaining linguistic styles and syntax on optimisation of prompt templates, yielding a 103.87% improvement using the best performing method. Comparison of the results of multiple contextual tasks demonstrate the ability of LLMs to maintain syntax while learning to replicate linguistic styles. Additionally, the effect on the output with different methods of prompt template generation is shown.

While preliminary findings indicate that multilingual LLMs exhibit reduced bias compared to monolingual ones, a comprehensive understanding of the effect of multilingual training on bias mitigation, is lacking. This study addresses this gap by systematically training six LLMs of identical size (2.6B parameters) and architecture: five monolingual models (English, German, French, Italian, and Spanish) and one multilingual model trained on an equal distribution of data across these languages, all using publicly available data. To ensure robust evaluation, standard bias benchmarks were automatically translated into the five target languages and verified for both translation quality and bias preservation by human annotators. Our results consistently demonstrate that multilingual training effectively mitigates bias. Moreover, we observe that multilingual models achieve not only lower bias but also superior prediction accuracy when compared to monolingual models with the same amount of training data, model architecture, and size.

Methodological advancements to automate the generation of differential diagnosis (DDx) to predict a list of potential diseases as differentials given patients' symptom descriptions are critical to clinical reasoning and applications such as decision support. However, providing reasoning or interpretation for these differential diagnoses is more meaningful. Fortunately, large language models (LLMs) possess powerful language processing abilities and have been proven effective in various related tasks. Motivated by this potential, we investigate the use of LLMs for interpretable DDx. First, we develop a new DDx dataset with expert-derived interpretation on 570 public clinical notes. Second, we propose a novel framework, named Dual-Inf, that enables LLMs to conduct bidirectional inference for interpretation. Both human and automated evaluation demonstrate the effectiveness of Dual-Inf in predicting differentials and diagnosis explanations. Specifically, the performance improvement of Dual-Inf over the baseline methods exceeds 32% w.r.t. BERTScore in DDx interpretation. Furthermore, experiments verify that Dual-Inf (1) makes fewer errors in interpretation, (2) has great generalizability, (3) is promising for rare disease diagnosis and explanation.

Evaluating the degree of reproduction of copyright-protected content by language models (LMs) is of significant interest to the AI and legal communities. Although both literal and non-literal similarities are considered by courts when assessing the degree of reproduction, prior research has focused only on literal similarities. To bridge this gap, we introduce CopyBench, a benchmark designed to measure both literal and non-literal copying in LM generations. Using copyrighted fiction books as text sources, we provide automatic evaluation protocols to assess literal and non-literal copying, balanced against the model utility in terms of the ability to recall facts from the copyrighted works and generate fluent completions. We find that, although literal copying is relatively rare, two types of non-literal copying -- event copying and character copying -- occur even in models as small as 7B parameters. Larger models demonstrate significantly more copying, with literal copying rates increasing from 0.2% to 10.5% and non-literal copying from 2.3% to 6.9% when comparing Llama3-8B and 70B models, respectively. We further evaluate the effectiveness of current strategies for mitigating copying and show that (1) training-time alignment can reduce literal copying but may increase non-literal copying, and (2) current inference-time mitigation methods primarily reduce literal but not non-literal copying.

Multi-agent reinforcement learning (MARL) methods struggle with the non-stationarity of multi-agent systems and fail to adaptively learn online when tested with novel agents. Here, we leverage large language models (LLMs) to create an autonomous agent that can handle these challenges. Our agent, Hypothetical Minds, consists of a cognitively-inspired architecture, featuring modular components for perception, memory, and hierarchical planning over two levels of abstraction. We introduce the Theory of Mind module that scaffolds the high-level planning process by generating hypotheses about other agents' strategies in natural language. It then evaluates and iteratively refines these hypotheses by reinforcing hypotheses that make correct predictions about the other agents' behavior. Hypothetical Minds significantly improves performance over previous LLM-agent and RL baselines on a range of competitive, mixed motive, and collaborative domains in the Melting Pot benchmark, including both dyadic and population-based environments. Additionally, comparisons against LLM-agent baselines and ablations reveal the importance of hypothesis evaluation and refinement for succeeding on complex scenarios.