Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous evaluations of LLMs' debugging ability are significantly limited by the risk of data leakage, the scale of the dataset, and the variety of tested bugs. To overcome these deficiencies, we introduce `DebugBench', an LLM debugging benchmark consisting of 4,253 instances. It covers four major bug categories and 18 minor types in C++, Java, and Python. To construct DebugBench, we collect code snippets from the LeetCode community, implant bugs into source data with GPT-4, and assure rigorous quality checks. We evaluate two commercial and three open-source models in a zero-shot scenario. We find that (1) while closed-source models like GPT-4 exhibit inferior debugging performance compared to humans, open-source models such as Code Llama fail to attain any pass rate scores; (2) the complexity of debugging notably fluctuates depending on the bug category; (3) incorporating runtime feedback has a clear impact on debugging performance which is not always helpful. As an extension, we also compare LLM debugging and code generation, revealing a strong correlation between them for closed-source models. These findings will benefit the development of LLMs in debugging.

Recent work demonstrates that, after being fine-tuned on a high-quality instruction dataset, the resulting model can obtain impressive capabilities to address a wide range of tasks. However, existing methods for instruction data generation often produce duplicate data and are not controllable enough on data quality. In this paper, we extend the generalization of instruction tuning by classifying the instruction data to 4 code-related tasks and propose a LLM-based Generator-Discriminator data process framework to generate diverse, high-quality instruction data from open source code. Hence, we introduce CodeOcean, a dataset comprising 20,000 instruction instances across 4 universal code-related tasks,which is aimed at augmenting the effectiveness of instruction tuning and improving the generalization ability of fine-tuned model. Subsequently, we present WaveCoder, a fine-tuned Code LLM with Widespread And Versatile Enhanced instruction tuning. This model is specifically designed for enhancing instruction tuning of Code Language Models (LLMs). Our experiments demonstrate that Wavecoder models outperform other open-source models in terms of generalization ability across different code-related tasks at the same level of fine-tuning scale. Moreover, Wavecoder exhibits high efficiency in previous code generation tasks. This paper thus offers a significant contribution to the field of instruction data generation and fine-tuning models, providing new insights and tools for enhancing performance in code-related tasks.

With the development of large pre-trained vision-language models, how to effectively transfer the knowledge of such foundational models to downstream tasks becomes a hot topic, especially in a data-deficient scenario. Recently, prompt tuning has become a popular solution. When adapting the vision-language models, researchers freeze the parameters in the backbone and only design and tune the prompts. On the one hand, the delicate design of prompt tuning exhibits strong performance. On the other hand, complicated structures and update rules largely increase the computation and storage cost. Motivated by the observation that the evolution pattern of the generalization capability in visual-language models aligns harmoniously with the trend of rank variations in the prompt matrix during adaptation, we design a new type of prompt, Re-parameterized Low-rank Prompt (RLP), for both efficient and effective adaptation. Our method could largely reduce the number of tunable parameters and storage space, which is quite beneficial in resource-limited scenarios. Extensive experiments further demonstrate the superiority of RLP. In particular, RLP shows comparable or even stronger performance than the latest state-of-the-art methods with an extremely small number of parameters. On a series of tasks over 11 datasets, RLP significantly increases the average downstream accuracy of classic prompt tuning by up to 5.25% using merely 0.5K parameters.

Despite the remarkable ability of large language models (LLMs) in language comprehension and generation, they often suffer from producing factually incorrect information, also known as hallucination. A promising solution to this issue is verifiable text generation, which prompts LLMs to generate content with citations for accuracy verification. However, verifiable text generation is non-trivial due to the focus-shifting phenomenon, the intricate reasoning needed to align the claim with correct citations, and the dilemma between the precision and breadth of retrieved documents. In this paper, we present VTG, an innovative framework for Verifiable Text Generation with evolving memory and self-reflection. VTG introduces evolving long short-term memory to retain both valuable documents and recent documents. A two-tier verifier equipped with an evidence finder is proposed to rethink and reflect on the relationship between the claim and citations. Furthermore, active retrieval and diverse query generation are utilized to enhance both the precision and breadth of the retrieved documents. We conduct extensive experiments on five datasets across three knowledge-intensive tasks and the results reveal that VTG significantly outperforms baselines.

We introduce EarthPT -- an Earth Observation (EO) pretrained transformer. EarthPT is a 700 million parameter decoding transformer foundation model trained in an autoregressive self-supervised manner and developed specifically with EO use-cases in mind. We demonstrate that EarthPT is an effective forecaster that can accurately predict future pixel-level surface reflectances across the 400-2300 nm range well into the future. For example, forecasts of the evolution of the Normalised Difference Vegetation Index (NDVI) have a typical error of approximately 0.05 (over a natural range of -1 -> 1) at the pixel level over a five month test set horizon, out-performing simple phase-folded models based on historical averaging. We also demonstrate that embeddings learnt by EarthPT hold semantically meaningful information and could be exploited for downstream tasks such as highly granular, dynamic land use classification. Excitingly, we note that the abundance of EO data provides us with -- in theory -- quadrillions of training tokens. Therefore, if we assume that EarthPT follows neural scaling laws akin to those derived for Large Language Models (LLMs), there is currently no data-imposed limit to scaling EarthPT and other similar `Large Observation Models.'

Both medical care and observational studies in oncology require a thorough understanding of a patient's disease progression and treatment history, often elaborately documented in clinical notes. Despite their vital role, no current oncology information representation and annotation schema fully encapsulates the diversity of information recorded within these notes. Although large language models (LLMs) have recently exhibited impressive performance on various medical natural language processing tasks, due to the current lack of comprehensively annotated oncology datasets, an extensive evaluation of LLMs in extracting and reasoning with the complex rhetoric in oncology notes remains understudied. We developed a detailed schema for annotating textual oncology information, encompassing patient characteristics, tumor characteristics, tests, treatments, and temporality. Using a corpus of 40 de-identified breast and pancreatic cancer progress notes at University of California, San Francisco, we applied this schema to assess the zero-shot abilities of three recent LLMs (GPT-4, GPT-3.5-turbo, and FLAN-UL2) to extract detailed oncological history from two narrative sections of clinical progress notes. Our team annotated 9028 entities, 9986 modifiers, and 5312 relationships. The GPT-4 model exhibited overall best performance, with an average BLEU score of 0.73, an average ROUGE score of 0.72, an exact-match F1-score of 0.51, and an average accuracy of 68% on complex tasks (expert manual evaluation on subset). Notably, it was proficient in tumor characteristic and medication extraction, and demonstrated superior performance in relational inference like adverse event detection. However, further improvements are needed before using it to reliably extract important facts from cancer progress notes needed for clinical research, complex population management, and documenting quality patient care.

Multiple-choice questions (MCQs) are ubiquitous in almost all levels of education since they are easy to administer, grade, and are a reliable form of assessment. An important aspect of MCQs is the distractors, i.e., incorrect options that are designed to target specific misconceptions or insufficient knowledge among students. To date, the task of crafting high-quality distractors has largely remained a labor-intensive process for teachers and learning content designers, which has limited scalability. In this work, we explore the task of automated distractor and corresponding feedback message generation in math MCQs using large language models. We establish a formulation of these two tasks and propose a simple, in-context learning-based solution. Moreover, we propose generative AI-based metrics for evaluating the quality of the feedback messages. We conduct extensive experiments on these tasks using a real-world MCQ dataset. Our findings suggest that there is a lot of room for improvement in automated distractor and feedback generation; based on these findings, we outline several directions for future work.

Do AI companies need to pay for the training data that powers their generative AI systems? The question is hotly contested in Silicon Valley and in a wave of lawsuits levied against tech behemoths like Meta, Google, and OpenAI. In Washington, DC, though, there seems to be a growing consensus that the tech giants need to cough up. Today, at a Senate hearing on AI's impact on journalism, lawmakers from both sides of the aisle agreed that OpenAI and others should pay media outlets for using their work in AI projects. "It's not only morally right," said Richard Blumenthal, the Democrat who chairs the Judiciary Subcommittee on Privacy, Technology, and the Law that held the hearing.

AI poses a grave threat to journalism, experts warned Congress at a hearing on Wednesday. Media executives and academic experts testified before the Senate Judiciary Subcommittee on Privacy, Technology, and the Law about how AI is contributing to the big tech-fueled decline of journalism. They also talked about intellectual property issues arising from AI models being trained on the work of journalists, and raised alarms about the increasing dangers of AI-powered misinformation. "The rise of big tech has been directly responsible for the decline in local news," said Senator Richard Blumenthal, a Connecticut Democrat and chair of the subcommittee. "First, Meta, Google and OpenAI are using the hard work of newspapers and authors to train their AI models without compensation or credit. Adding insult to injury, those models are then used to compete with newspapers and broadcasters, cannibalizing readership and revenue from the journalistic institutions that generate the content in the first place."

If you squint and tilt your head, you can see some similarities in the blurry shapes that are Harvard and OpenAI. Each is a leading institution for building minds, whether real or artificial--Harvard educates smart humans, while OpenAI engineers smart machines--and each has been forced in recent days to stare down a common allegation. Namely, that they are represented by intellectual thieves. Last month, the conservative activist Christopher Rufo and the journalist Christopher Brunet accused then–Harvard President Claudine Gay of having copied short passages without attribution in her dissertation. Gay later admitted to "instances in my academic writings where some material duplicated other scholars' language, without proper attribution," for which she requested corrections. The two cases share common ground, yet many of the responses to them could not be more different.