The Information Retrieval in Software Engineering (IRSE) track aims to develop solutions for automated evaluation of code comments in a machine learning framework based on human and large language model generated labels. In this track, there is a binary classification task to classify comments as useful and not useful. The dataset consists of 9048 code comments and surrounding code snippet pairs extracted from open source github C based projects and an additional dataset generated individually by teams using large language models. Overall 56 experiments have been submitted by 17 teams from various universities and software companies. The submissions have been evaluated quantitatively using the F1-Score and qualitatively based on the type of features developed, the supervised learning model used and their corresponding hyper-parameters. The labels generated from large language models increase the bias in the prediction model but lead to less over-fitted results.
In software development, code comments play a crucial role in enhancing code comprehension and collaboration. This research paper addresses the challenge of objectively classifying code comments as "Useful" or "Not Useful." We propose a novel solution that harnesses contextualized embeddings, particularly BERT, to automate this classification process. We address this task by incorporating generated code and comment pairs. The initial dataset comprised 9048 pairs of code and comments written in C, labeled as either Useful or Not Useful. To augment this dataset, we sourced an additional 739 lines of code-comment pairs and generated labels using a Large Language Model Architecture, specifically BERT. The primary objective was to build classification models that can effectively differentiate between useful and not useful code comments. Various machine learning algorithms were employed, including Logistic Regression, Decision Tree, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Gradient Boosting, Random Forest, and a Neural Network. Each algorithm was evaluated using precision, recall, and F1-score metrics, both with the original seed dataset and the augmented dataset. This study showcases the potential of generative AI for enhancing binary code comment quality classification models, providing valuable insights for software developers and researchers in the field of natural language processing and software engineering.
The integration of Artificial Intelligence (AI) into education is a recent development, with chatbots emerging as a noteworthy addition to this transformative landscape. As online learning platforms rapidly advance, students need to adapt swiftly to excel in this dynamic environment. Consequently, understanding the acceptance of chatbots, particularly those employing Large Language Model (LLM) such as Chat Generative Pretrained Transformer (ChatGPT), Google Bard, and other interactive AI technologies, is of paramount importance. However, existing research on chatbots in education has overlooked key behavior-related aspects, such as Optimism, Innovativeness, Discomfort, Insecurity, Transparency, Ethics, Interaction, Engagement, and Accuracy, creating a significant literature gap. To address this gap, this study employs Partial Least Squares Structural Equation Modeling (PLS-SEM) to investigate the determinant of chatbots adoption in education among students, considering the Technology Readiness Index (TRI) and Technology Acceptance Model (TAM). Utilizing a five-point Likert scale for data collection, we gathered a total of 185 responses, which were analyzed using R-Studio software. We established 12 hypotheses to achieve its objectives. The results showed that Optimism and Innovativeness are positively associated with Perceived Ease of Use (PEOU) and Perceived Usefulness (PU). Conversely, Discomfort and Insecurity negatively impact PEOU, with only Insecurity negatively affecting PU. These findings provide insights for future technology designers, elucidating critical user behavior factors influencing chatbots adoption and utilization in educational contexts.
While transformer models exhibit strong capabilities on linguistic tasks, their complex architectures make them difficult to interpret. Recent work has aimed to reverse engineer transformer models into human-readable representations called circuits that implement algorithmic functions. We extend this research by analyzing and comparing circuits for similar sequence continuation tasks, which include increasing sequences of Arabic numerals, number words, and months. By applying circuit interpretability analysis, we identify a key sub-circuit in both GPT-2 Small and Llama-2-7B responsible for detecting sequence members and for predicting the next member in a sequence. Our analysis reveals that semantically related sequences rely on shared circuit subgraphs with analogous roles. Additionally, we show that this sub-circuit has effects on various math-related prompts, such as on intervaled circuits, Spanish number word and months continuation, and natural language word problems. Overall, documenting shared computational structures enables better model behavior predictions, identification of errors, and safer editing procedures. This mechanistic understanding of transformers is a critical step towards building more robust, aligned, and interpretable language models.
Large Language Models (LLMs) are huge artificial neural networks which primarily serve to generate text, but also provide a very sophisticated probabilistic model of language use. Since generating a semantically consistent text requires a form of effective memory, we investigate the memory properties of LLMs and find surprising similarities with key characteristics of human memory. We argue that the human-like memory properties of the Large Language Model do not follow automatically from the LLM architecture but are rather learned from the statistics of the training textual data. These results strongly suggest that the biological features of human memory leave an imprint on the way that we structure our textual narratives.
Self-training has proven to be an effective approach for cross-domain tasks, and in this study, we explore its application to cross-domain constituency parsing. Traditional self-training methods rely on limited and potentially low-quality raw corpora. To overcome this limitation, we propose enhancing self-training with the large language model (LLM) to generate domain-specific raw corpora iteratively. For the constituency parsing, we introduce grammar rules that guide the LLM in generating raw corpora and establish criteria for selecting pseudo instances. Our experimental results demonstrate that self-training for constituency parsing, equipped with an LLM, outperforms traditional methods regardless of the LLM's performance. Moreover, the combination of grammar rules and confidence criteria for pseudo-data selection yields the highest performance in the cross-domain constituency parsing.
We present a cost-effective method to integrate speech into a large language model (LLM), resulting in a Contextual Speech Model with Instruction-following/in-context-learning Capabilities (COSMIC) multi-modal LLM. Using GPT-3.5, we generate Speech Comprehension Test Question-Answer (SQA) pairs from speech transcriptions for supervised instruction tuning. With under 30 million trainable parameters and only 450 hours of English speech data, COSMIC demonstrates emerging capabilities in instruction-following and in-context learning. Equipped with such capabilities, COSMIC achieves a maximum 33.18 BLEU score in 0-shot EN-to-X speech to text translation (S2TT) and a significant boost in the 1-shot setting. Additionally, there is an average 25.8\% relative Word Error Rate (WER) reduction for 1-shot cross-domain adaptation. COSMIC exhibits a significant automatic speech recognition (ASR) accuracy gain in contextual biasing tasks due to its instruction-following capability.
This paper introduces Alympics (Olympics for Agents), a systematic simulation framework utilizing Large Language Model (LLM) agents for game theory research. Alympics creates a versatile platform for studying complex game theory problems, bridging the gap between theoretical game theory and empirical investigations by providing a controlled environment for simulating human-like strategic interactions with LLM agents. In our pilot case study, the "Water Allocation Challenge," we explore Alympics through a challenging strategic game focused on the multi-round auction on scarce survival resources. This study demonstrates the framework's ability to qualitatively and quantitatively analyze game determinants, strategies, and outcomes. Additionally, we conduct a comprehensive human assessment and an in-depth evaluation of LLM agents in strategic decision-making scenarios. Our findings not only expand the understanding of LLM agents' proficiency in emulating human strategic behavior but also highlight their potential in advancing game theory knowledge, thereby enriching our understanding of both game theory and empowering further research into strategic decision-making domains with LLM agents. Codes, prompts, and all related resources are available at https://github.com/microsoft/Alympics.
Recent Large Language Models (LLMs) have demonstrated remarkable capabilities in generating text that closely resembles human writing across wide range of styles and genres. However, such capabilities are prone to potential abuse, such as fake news generation, spam email creation, and misuse in academic assignments. Hence, it is essential to build automated approaches capable of distinguishing between artificially generated text and human-authored text. In this paper, we propose a simple yet efficient solution to this problem by ensembling predictions from multiple constituent LLMs. Compared to previous state-of-the-art approaches, which are perplexity-based or uses ensembles with a number of LLMs, our condensed ensembling approach uses only two constituent LLMs to achieve comparable performance. Experiments conducted on four benchmark datasets for generative text classification show performance improvements in the range of 0.5 to 100\% compared to previous state-of-the-art approaches. We also study the influence that the training data from individual LLMs have on model performance. We found that substituting commercially-restrictive Generative Pre-trained Transformer (GPT) data with data generated from other open language models such as Falcon, Large Language Model Meta AI (LLaMA2), and Mosaic Pretrained Transformers (MPT) is a feasible alternative when developing generative text detectors. Furthermore, to demonstrate zero-shot generalization, we experimented with an English essays dataset, and results suggest that our ensembling approach can handle new data effectively.
This paper presents a comprehensive evaluation of the code generation capabilities of ChatGPT, a prominent large language model, compared to human programmers. A novel dataset of 131 code-generation prompts across 5 categories was curated to enable robust analysis. Code solutions were generated by both ChatGPT and humans for all prompts, resulting in 262 code samples. A meticulous manual assessment methodology prioritized evaluating correctness, comprehensibility, and security using 14 established code quality metrics. The key findings reveal ChatGPT's strengths in crafting concise, efficient code with advanced constructs, showcasing strengths in data analysis tasks (93.1% accuracy) but limitations in visual-graphical challenges. Comparative analysis with human code highlights ChatGPT's inclination towards modular design and superior error handling. Additionally, machine learning models effectively distinguished ChatGPT from human code with up to 88% accuracy, suggesting detectable coding style disparities. By providing profound insights into ChatGPT's code generation capabilities and limitations through quantitative metrics and qualitative analysis, this study makes valuable contributions toward advancing AI-based programming assistants. The curated dataset and methodology offer a robust foundation for future research in this nascent domain. All data and codes are available on https://github.com/DSAatUSU/ChatGPT-promises-and-pitfalls.
Large language models (LLMs) have succeeded significantly in various applications but remain susceptible to adversarial jailbreaks that void their safety guardrails. Previous attempts to exploit these vulnerabilities often rely on high-cost computational extrapolations, which may not be practical or efficient. In this paper, inspired by the authority influence demonstrated in the Milgram experiment, we present a lightweight method to take advantage of the LLMs' personification capabilities to construct $\textit{a virtual, nested scene}$, allowing it to realize an adaptive way to escape the usage control in a normal scenario. Empirically, the contents induced by our approach can achieve leading harmfulness rates with previous counterparts and realize a continuous jailbreak in subsequent interactions, which reveals the critical weakness of self-losing on both open-source and closed-source LLMs, $\textit{e.g.}$, Llama-2, Llama-3, GPT-3.5, GPT-4, and GPT-4o. The code and data are available at: https://github.com/tmlr-group/DeepInception.
With the rapid development of the internet, online social media welcomes people with different backgrounds through its diverse content. The increasing usage of emoji becomes a noticeable trend thanks to emoji's rich information beyond cultural or linguistic borders. However, the current study on emojis is limited to single emoji prediction and there are limited data resources available for further study of the interesting linguistic phenomenon. To this end, we synthesize a large text-emoji parallel corpus, Text2Emoji, from a large language model. Based on the parallel corpus, we distill a sequence-to-sequence model, EmojiLM, which is specialized in the text-emoji bidirectional translation. Extensive experiments on public benchmarks and human evaluation demonstrate that our proposed model outperforms strong baselines and the parallel corpus benefits emoji-related downstream tasks.
We explore using a moderately sized large language model (GPT-J 6B parameters) to create a plan for a simulated robot to achieve 30 classes of goals in ScienceWorld, a text game simulator for elementary science experiments. Previously published empirical work claimed that large language models (LLMs) are a poor fit (Wang et al., 2022) compared to reinforcement learning. Using the Markov assumption (a single previous step), the LLM outperforms the reinforcement learning-based approach by a factor of 1.4. When we fill the LLM's input buffer with as many prior steps as possible, improvement rises to 3.5x. Even when training on only 6.5% of the training data, we observe a 2.2x improvement over the reinforcement-learning-based approach. Our experiments show that performance varies widely across the 30 classes of actions, indicating that averaging over tasks can hide significant performance issues. In work contemporaneous with ours, Lin et al. (2023) demonstrated a two-part approach (SwiftSage) that uses a small LLM (T5-large) complemented by OpenAI's massive LLMs to achieve outstanding results in ScienceWorld. Our 6-B parameter, single-stage GPT-J matches the performance of SwiftSage's two-stage architecture when it incorporates GPT-3.5 turbo which has 29-times more parameters than GPT-J.
Previous efforts to support creative problem-solving have included (a) techniques (such as brainstorming and design thinking) to stimulate creative ideas, and (b) software tools to record and share these ideas. Now, generative AI technologies can suggest new ideas that might never have occurred to the users, and users can then select from these ideas or use them to stimulate even more ideas. Here, we describe such a system, Supermind Ideator. The system uses a large language model (GPT 3.5) and adds prompting, fine tuning, and a user interface specifically designed to help people use creative problem-solving techniques. Some of these techniques can be applied to any problem; others are specifically intended to help generate innovative ideas about how to design groups of people and/or computers ("superminds"). We also describe our early experiences with using this system and suggest ways it could be extended to support additional techniques for other specific problem-solving domains.
Pre-training and fine-tuning have emerged as a promising paradigm across various natural language processing (NLP) tasks. The effectiveness of pretrained large language models (LLM) has witnessed further enhancement, holding potential for applications in the field of medicine, particularly in the context of Traditional Chinese Medicine (TCM). However, the application of these general models to specific domains often yields suboptimal results, primarily due to challenges like lack of domain knowledge, unique objectives, and computational efficiency. Furthermore, their effectiveness in specialized domains, such as Traditional Chinese Medicine, requires comprehensive evaluation. To address the above issues, we propose a novel domain specific TCMDA (TCM Domain Adaptation) approach, efficient pre-training with domain-specific corpus. Specifically, we first construct a large TCM-specific corpus, TCM-Corpus-1B, by identifying domain keywords and retreving from general corpus. Then, our TCMDA leverages the LoRA which freezes the pretrained model's weights and uses rank decomposition matrices to efficiently train specific dense layers for pre-training and fine-tuning, efficiently aligning the model with TCM-related tasks, namely TCM-GPT-7B. We further conducted extensive experiments on two TCM tasks, including TCM examination and TCM diagnosis. TCM-GPT-7B archived the best performance across both datasets, outperforming other models by relative increments of 17% and 12% in accuracy, respectively. To the best of our knowledge, our study represents the pioneering validation of domain adaptation of a large language model with 7 billion parameters in TCM domain. We will release both TCMCorpus-1B and TCM-GPT-7B model once accepted to facilitate interdisciplinary development in TCM and NLP, serving as the foundation for further study.
Recently, there has been growing interest in developing the next-generation recommender systems (RSs) based on pretrained large language models (LLMs). However, the semantic gap between natural language and recommendation tasks is still not well addressed, leading to multiple issues such as spuriously correlated user/item descriptors, ineffective language modeling on user/item data, inefficient recommendations via auto-regression, etc. In this paper, we propose CLLM4Rec, the first generative RS that tightly integrates the LLM paradigm and ID paradigm of RSs, aiming to address the above challenges simultaneously. We first extend the vocabulary of pretrained LLMs with user/item ID tokens to faithfully model user/item collaborative and content semantics. Accordingly, a novel soft+hard prompting strategy is proposed to effectively learn user/item collaborative/content token embeddings via language modeling on RS-specific corpora, where each document is split into a prompt consisting of heterogeneous soft (user/item) tokens and hard (vocab) tokens and a main text consisting of homogeneous item tokens or vocab tokens to facilitate stable and effective language modeling. In addition, a novel mutual regularization strategy is introduced to encourage CLLM4Rec to capture recommendation-related information from noisy user/item content. Finally, we propose a novel recommendation-oriented finetuning strategy for CLLM4Rec, where an item prediction head with multinomial likelihood is added to the pretrained CLLM4Rec backbone to predict hold-out items based on soft+hard prompts established from masked user-item interaction history, where recommendations of multiple items can be generated efficiently without hallucination. Codes are released at https://github.com/yaochenzhu/llm4rec.
As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation requires a synchronized update operation among each partial softmax result, leading to ~20% overheads for the attention computation in LLMs. (2) Under-utilized computation of flat GEMM. The shape of matrices performing GEMM in LLM inference is flat, leading to under-utilized computation and >50% performance loss after padding zeros in previous designs. (3) Performance loss due to static dataflow. Kernel performance in LLM depends on varied input data features, hardware configurations, etc. A single and static dataflow may lead to a 50.25% performance loss for GEMMs of different shapes in LLM inference. We present FlashDecoding++, a fast LLM inference engine supporting mainstream LLMs and hardware back-ends. To tackle the above challenges, FlashDecoding++ creatively proposes: (1) Asynchronized softmax with unified max value. FlashDecoding++ introduces a unified max value technique for different partial softmax computations to avoid synchronization. (2) Flat GEMM optimization with double buffering. FlashDecoding++ points out that flat GEMMs with different shapes face varied bottlenecks. Then, techniques like double buffering are introduced. (3) Heuristic dataflow with hardware resource adaptation. FlashDecoding++ heuristically optimizes dataflow using different hardware resource considering input dynamics. Due to the versatility of optimizations in FlashDecoding++, FlashDecoding++ can achieve up to 4.86x and 2.18x speedup on both NVIDIA and AMD GPUs compared to Hugging Face implementations. FlashDecoding++ also achieves an average speedup of 1.37x compared to state-of-the-art LLM inference engines on mainstream LLMs.
Expressive text-to-speech (TTS) aims to synthesize speeches with human-like tones, moods, or even artistic attributes. Recent advancements in expressive TTS empower users with the ability to directly control synthesis style through natural language prompts. However, these methods often require excessive training with a significant amount of style-annotated data, which can be challenging to acquire. Moreover, they may have limited adaptability due to fixed style annotations. In this work, we present FreeStyleTTS (FS-TTS), a controllable expressive TTS model with minimal human annotations. Our approach utilizes a large language model (LLM) to transform expressive TTS into a style retrieval task. The LLM selects the best-matching style references from annotated utterances based on external style prompts, which can be raw input text or natural language style descriptions. The selected reference guides the TTS pipeline to synthesize speeches with the intended style. This innovative approach provides flexible, versatile, and precise style control with minimal human workload. Experiments on a Mandarin storytelling corpus demonstrate FS-TTS's proficiency in leveraging LLM's semantic inference ability to retrieve desired styles from either input text or user-defined descriptions. This results in synthetic speeches that are closely aligned with the specified styles.
We investigate the optimization target of Contrast-Consistent Search (CCS), which aims to recover the internal representations of truth of a large language model. We present a new loss function that we call the Midpoint-Displacement (MD) loss function. We demonstrate that for a certain hyper-parameter value this MD loss function leads to a prober with very similar weights to CCS. We further show that this hyper-parameter is not optimal and that with a better hyper-parameter the MD loss function attains a higher test accuracy than CCS.
This work focuses on the novel problem setting of generating graphs conditioned on a description of the graph's functional requirements in a downstream task. We pose the problem as a text-to-text generation problem and focus on the approach of fine-tuning a pretrained large language model (LLM) to generate graphs. We propose an inductive bias which incorporates information about the structure of the graph into the LLM's generation process by incorporating message passing layers into an LLM's architecture. To evaluate our proposed method, we design a novel set of experiments using publicly available and widely studied molecule and knowledge graph data sets. Results suggest our proposed approach generates graphs which more closely meet the requested functional requirements, outperforming baselines developed on similar tasks by a statistically significant margin.