Large Language Models (LLMs) have already become quite proficient at solving simpler programming tasks like those in HumanEval or MBPP benchmarks. However, solving more complex and competitive programming tasks is still quite challenging for these models - possibly due to their tendency to generate solutions as monolithic code blocks instead of decomposing them into logical sub-tasks and sub-modules. On the other hand, experienced programmers instinctively write modularized code with abstraction for solving complex tasks, often reusing previously developed modules. To address this gap, we propose CodeChain, a novel framework for inference that elicits modularized code generation through a chain of self-revisions, each being guided by some representative sub-modules generated in previous iterations. Concretely, CodeChain first instructs the LLM to generate modularized codes through chain-of-thought prompting. Then it applies a chain of self-revisions by iterating the two steps: 1) extracting and clustering the generated sub-modules and selecting the cluster representatives as the more generic and re-usable implementations, and 2) augmenting the original chain-of-thought prompt with these selected module-implementations and instructing the LLM to re-generate new modularized solutions. We find that by naturally encouraging the LLM to reuse the previously developed and verified sub-modules, CodeChain can significantly boost both modularity as well as correctness of the generated solutions, achieving relative pass@1 improvements of 35% on APPS and 76% on CodeContests. It is shown to be effective on both OpenAI LLMs as well as open-sourced LLMs like WizardCoder. We also conduct comprehensive ablation studies with different methods of prompting, number of clusters, model sizes, program qualities, etc., to provide useful insights that underpin CodeChain's success.

Quantization is an indispensable technique for serving Large Language Models (LLMs) and has recently found its way into LoRA fine-tuning. In this work we focus on the scenario where quantization and LoRA fine-tuning are applied together on a pre-trained model. In such cases it is common to observe a consistent gap in the performance on downstream tasks between full fine-tuning and quantization plus LoRA fine-tuning approach. In response, we propose LoftQ (LoRA-Fine-Tuning-aware Quantization), a novel quantization framework that simultaneously quantizes an LLM and finds a proper low-rank initialization for LoRA fine-tuning. Such an initialization alleviates the discrepancy between the quantized and full-precision model and significantly improves generalization in downstream tasks. We evaluate our method on natural language understanding, question answering, summarization, and natural language generation tasks. Experiments show that our method is highly effective and outperforms existing quantization methods, especially in the challenging 2-bit and 2/4-bit mixed precision regimes. The code is available on https://github.com/yxli2123/LoftQ.

Counterfactual reasoning, a fundamental aspect of human cognition, involves contemplating alternatives to established facts or past events, significantly enhancing our abilities in planning and decision-making. In light of the advancements in current multi-modal large language models, we explore their effectiveness in counterfactual reasoning. To facilitate this investigation, we introduce a novel dataset, C-VQA, specifically designed to test the counterfactual reasoning capabilities of modern multi-modal large language models. This dataset is constructed by infusing original questions with counterfactual presuppositions, spanning various types such as numerical and boolean queries. It encompasses a mix of real and synthetic data, representing a wide range of difficulty levels. Our thorough evaluations of contemporary vision-language models using this dataset have revealed substantial performance drops, with some models showing up to a 40% decrease, highlighting a significant gap between current models and human-like vision reasoning capabilities. We hope our dataset will serve as a vital benchmark for evaluating the counterfactual reasoning capabilities of models. Code and dataset are publicly available at https://bzhao.me/C-VQA/.

In this work, we conduct an assessment of the optimization capabilities of LLMs across various tasks and data sizes. Each of these tasks corresponds to unique optimization domains, and LLMs are required to execute these tasks with interactive prompting. That is, in each optimization step, the LLM generates new solutions from the past generated solutions with their values, and then the new solutions are evaluated and considered in the next optimization step. Additionally, we introduce three distinct metrics for a comprehensive assessment of task performance from various perspectives. These metrics offer the advantage of being applicable for evaluating LLM performance across a broad spectrum of optimization tasks and are less sensitive to variations in test samples. By applying these metrics, we observe that LLMs exhibit strong optimization capabilities when dealing with small-sized samples. However, their performance is significantly influenced by factors like data size and values, underscoring the importance of further research in the domain of optimization tasks for LLMs.

This paper presents a comprehensive exploration of the evolution of prompt engineering and generation in the field of natural language processing (NLP). Starting from the early language models and information retrieval systems, we trace the key developments that have shaped prompt engineering over the years. The introduction of attention mechanisms in 2015 revolutionized language understanding, leading to advancements in controllability and context-awareness. Subsequent breakthroughs in reinforcement learning techniques further enhanced prompt engineering, addressing issues like exposure bias and biases in generated text. We examine the significant contributions in 2018 and 2019, focusing on fine-tuning strategies, control codes, and template-based generation. The paper also discusses the growing importance of fairness, human-AI collaboration, and low-resource adaptation. In 2020 and 2021, contextual prompting and transfer learning gained prominence, while 2022 and 2023 witnessed the emergence of advanced techniques like unsupervised pre-training and novel reward shaping. Throughout the paper, we reference specific research studies that exemplify the impact of various developments on prompt engineering. The journey of prompt engineering continues, with ethical considerations being paramount for the responsible and inclusive future of AI systems.

In this study, we explore the potential of Multimodal Large Language Models (MLLMs) in improving embodied decision-making processes for agents. While Large Language Models (LLMs) have been widely used due to their advanced reasoning skills and vast world knowledge, MLLMs like GPT4-Vision offer enhanced visual understanding and reasoning capabilities. We investigate whether state-of-the-art MLLMs can handle embodied decision-making in an end-to-end manner and whether collaborations between LLMs and MLLMs can enhance decision-making. To address these questions, we introduce a new benchmark called PCA-EVAL, which evaluates embodied decision-making from the perspectives of Perception, Cognition, and Action. Additionally, we propose HOLMES, a multi-agent cooperation framework that allows LLMs to leverage MLLMs and APIs to gather multimodal information for informed decision-making. We compare end-to-end embodied decision-making and HOLMES on our benchmark and find that the GPT4-Vision model demonstrates strong end-to-end embodied decision-making abilities, outperforming GPT4-HOLMES in terms of average decision accuracy (+3%). However, this performance is exclusive to the latest GPT4-Vision model, surpassing the open-source state-of-the-art MLLM by 26%. Our results indicate that powerful MLLMs like GPT4-Vision hold promise for decision-making in embodied agents, offering new avenues for MLLM research. The capacity to make well-informed decisions is essential for the survival and success of living organisms in their respective environments. Similarly, a major goal in embodied artificial intelligence is to develop agents, like robots, with sophisticated decision-making abilities. Recently, there has been a notable increase in leveraging exceptional reasoning capabilities and world knowledge of Large Language Models (LLMs) to enhance decision making in agents. However, LLMs are primarily designed to process textual context, creating a modality gap (Liang et al., 2022; Ren et al., 2023a) for the LLM-powered agent when dealing with multimodal observations in real-world scenarios.

Assessing factuality of text generated by large language models (LLMs) is an emerging yet crucial research area, aimed at alerting users to potential errors and guiding the development of more reliable LLMs. Nonetheless, the evaluators assessing factuality necessitate suitable evaluation themselves to gauge progress and foster advancements. This direction remains under-explored, resulting in substantial impediments to the progress of factuality evaluators. To mitigate this issue, we introduce a benchmark for Factuality Evaluation of large Language Models, referred to as felm. In this benchmark, we collect responses generated from LLMs and annotate factuality labels in a fine-grained manner. Contrary to previous studies that primarily concentrate on the factuality of world knowledge (e.g.~information from Wikipedia), felm focuses on factuality across diverse domains, spanning from world knowledge to math and reasoning. Our annotation is based on text segments, which can help pinpoint specific factual errors. The factuality annotations are further supplemented by predefined error types and reference links that either support or contradict the statement. In our experiments, we investigate the performance of several LLM-based factuality evaluators on felm, including both vanilla LLMs and those augmented with retrieval mechanisms and chain-of-thought processes. Our findings reveal that while retrieval aids factuality evaluation, current LLMs are far from satisfactory to faithfully detect factual errors.

Recent advancements in large language models (LLMs) have enabled a new research domain, LLM agents, for solving robotics and planning tasks by leveraging the world knowledge and general reasoning abilities of LLMs obtained during pretraining. However, while considerable effort has been made to teach the robot the "dos," the "don'ts" received relatively less attention. We argue that, for any practical usage, it is as crucial to teach the robot the "don'ts": conveying explicit instructions about prohibited actions, assessing the robot's comprehension of these restrictions, and, most importantly, ensuring compliance. Moreover, verifiable safe operation is essential for deployments that satisfy worldwide standards such as ISO 61508, which defines standards for safely deploying robots in industrial factory environments worldwide. Aiming at deploying the LLM agents in a collaborative environment, we propose a queryable safety constraint module based on linear temporal logic (LTL) that simultaneously enables natural language (NL) to temporal constraints encoding, safety violation reasoning and explaining, and unsafe action pruning. To demonstrate the effectiveness of our system, we conducted experiments in VirtualHome environment and on a real robot. The experimental results show that our system strictly adheres to the safety constraints and scales well with complex safety constraints, highlighting its potential for practical utility.

Traditionally, social choice theory has only been applicable to choices among a few predetermined alternatives but not to more complex decisions such as collectively selecting a textual statement. We introduce generative social choice, a framework that combines the mathematical rigor of social choice theory with the capability of large language models to generate text and extrapolate preferences. This framework divides the design of AI-augmented democratic processes into two components: first, proving that the process satisfies rigorous representation guarantees when given access to oracle queries; second, empirically validating that these queries can be approximately implemented using a large language model. We apply this framework to the problem of generating a slate of statements that is representative of opinions expressed as free-form text; specifically, we develop a democratic process with representation guarantees and use this process to represent the opinions of participants in a survey about chatbot personalization. We find that 93 out of 100 participants feel "mostly" or "perfectly" represented by the slate of five statements we extracted.

Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability. In this paper, we propose a novel framework to pre-train language models for enhancing their abilities of comparative reasoning over texts. While there have been approaches for NLP tasks that require comparative reasoning, they suffer from costly manual data labeling and limited generalizability to different tasks. Our approach introduces a novel method of collecting scalable data for text-based entity comparison, which leverages both structured and unstructured data. Moreover, we present a framework of pre-training language models via three novel objectives on comparative reasoning. Evaluation on downstream tasks including comparative question answering, question generation, and summarization shows that our pre-training framework significantly improves the comparative reasoning abilities of language models, especially under low-resource conditions. This work also releases the first integrated benchmark for comparative reasoning.