Last summer, AdamYedidia, a user on a Web forum called LessWrong, published a post titled "Chess as a Case Study in Hidden Capabilities in ChatGPT." He started by noting that the Internet is filled with funny videos of ChatGPT playing bad chess: in one popular clip, the A.I. confidently and illegally moves a pawn backward. But many of these videos were made using the original version of OpenAI's chatbot, which was released to the public in late November, 2022, and was based on the GPT-3.5 large language model. Last March, OpenAI introduced an enhanced version of ChatGPT based on the more powerful GPT-4. As the post demonstrated, this new model, if prompted correctly, could play a surprisingly decent game of chess, achieving something like an Elo rating of 1000--better than roughly fifty per cent of ranked players.

AI caught everyone's attention in 2023 with Large Language Models (LLMs) that can be instructed to perform general tasks, such as translation or coding, just by prompting. This naturally led to an intense focus on models as the primary ingredient in AI application development, with everyone wondering what capabilities new LLMs will bring. As more developers begin to build using LLMs, however, we believe that this focus is rapidly changing: state-of-the-art AI results are increasingly obtained by compound systems with multiple components, not just monolithic models. For example, Google's AlphaCode 2 set state-of-the-art results in programming through a carefully engineered system that uses LLMs to generate up to 1 million possible solutions for a task and then filter down the set. AlphaGeometry, likewise, combines an LLM with a traditional symbolic solver to tackle olympiad problems.

Alzheimer's Disease (AD) is the most common form of dementia in the United States. Sleep is one of the lifestyle-related factors that has been shown critical for optimal cognitive function in old age. However, there is a lack of research studying the association between sleep and AD incidence. A major bottleneck for conducting such research is that the traditional way to acquire sleep information is time-consuming, inefficient, non-scalable, and limited to patients' subjective experience. A gold standard dataset is created from manual annotation of 570 randomly sampled clinical note documents from the adSLEEP, a corpus of 192,000 de-identified clinical notes of 7,266 AD patients retrieved from the University of Pittsburgh Medical Center (UPMC). We developed a rule-based Natural Language Processing (NLP) algorithm, machine learning models, and Large Language Model(LLM)-based NLP algorithms to automate the extraction of sleep-related concepts, including snoring, napping, sleep problem, bad sleep quality, daytime sleepiness, night wakings, and sleep duration, from the gold standard dataset. Rule-based NLP algorithm achieved the best performance of F1 across all sleep-related concepts. In terms of Positive Predictive Value (PPV), rule-based NLP algorithm achieved 1.00 for daytime sleepiness and sleep duration, machine learning models: 0.95 and for napping, 0.86 for bad sleep quality and 0.90 for snoring; and LLAMA2 with finetuning achieved PPV of 0.93 for Night Wakings, 0.89 for sleep problem, and 1.00 for sleep duration. The results show that the rule-based NLP algorithm consistently achieved the best performance for all sleep concepts. This study focused on the clinical notes of patients with AD, but could be extended to general sleep information extraction for other diseases.

Recently, Large Langauge Models (LLMs) have gained a lot of attention in the Software Engineering (SE) community. LLMs or their variants pre-trained on code are used for many SE tasks. A main approach for adapting LLMs to the downstream task is to fine-tune the models. However, with having billions-parameters-LLMs, fine-tuning the models is not practical. An alternative approach is using Parameter Efficient Fine Tuning (PEFT), in which the model parameters are frozen and only a few added parameters are trained. Though the LLMs are used for programming languages such as Python and Java widely, their capability for low-resource languages is limited. In this work, we empirically study PEFT methods, LoRA and Compacter, on CodeT5 and CodeLlama. We will assess their performance compared to fully fine-tuned models, whether they can be used for knowledge transfer from natural language models to code (using T5 and Llama models), and their ability to adapt the learned knowledge to an unseen language. For the unseen language, we aim to study R, as it has a wide community. The adaptability with less computational costs makes LLMs accessible in scenarios where heavy computational resources are not available. Moreover, studying R opens new opportunities for using LLMs for other languages. We anticipate our findings to showcase the capabilities of PEFT for code LLMs for R and reveal the improvement areas.

Instruction tuning for large language models (LLMs) can drive them to produce results consistent with human goals in specific downstream tasks. However, the process of continual instruction tuning (CIT) for LLMs may bring about the catastrophic forgetting (CF) problem, where previously learned abilities are degraded. Recent methods try to alleviate the CF problem by modifying models or replaying data, which may only remember the surface-level pattern of instructions and get confused on held-out tasks. In this paper, we propose a novel continual instruction tuning method based on Key-part Information Gain (KPIG). Our method computes the information gain on masked parts to dynamically replay data and refine the training objective, which enables LLMs to capture task-aware information relevant to the correct response and alleviate overfitting to general descriptions in instructions. In addition, we propose two metrics, P-score and V-score, to measure the generalization and instruction-following abilities of LLMs. Experiments demonstrate our method achieves superior performance on both seen and held-out tasks.

While text summarization is a well-known NLP task, in this paper, we introduce a novel and useful variant of it called functionality extraction from Git README files. Though this task is a text2text generation at an abstract level, it involves its own peculiarities and challenges making existing text2text generation systems not very useful. The motivation behind this task stems from a recent surge in research and development activities around the use of large language models for code-related tasks, such as code refactoring, code summarization, etc. We also release a human-annotated dataset called FuncRead, and develop a battery of models for the task. Our exhaustive experimentation shows that small size fine-tuned models beat any baseline models that can be designed using popular black-box or white-box large language models (LLMs) such as ChatGPT and Bard. Our best fine-tuned 7 Billion CodeLlama model exhibit 70% and 20% gain on the F1 score against ChatGPT and Bard respectively.

This paper presents ExeGPT, a distributed system designed for constraint-aware LLM inference. ExeGPT finds and runs with an optimal execution schedule to maximize inference throughput while satisfying a given latency constraint. By leveraging the distribution of input and output sequences, it effectively allocates resources and determines optimal execution configurations, including batch sizes and partial tensor parallelism. We also introduce two scheduling strategies based on Round-Robin Allocation and Workload-Aware Allocation policies, suitable for different NLP workloads. We evaluate ExeGPT on six LLM instances of T5, OPT, and GPT-3 and five NLP tasks, each with four distinct latency constraints. Compared to FasterTransformer, ExeGPT achieves up to 15.2x improvements in throughput and 6x improvements in latency. Overall, ExeGPT achieves an average throughput gain of 2.9x across twenty evaluation scenarios. Moreover, when adapting to changing sequence distributions, the cost of adjusting the schedule in ExeGPT is reasonably modest. ExeGPT proves to be an effective solution for optimizing and executing LLM inference for diverse NLP workload and serving conditions.

Existing works focus on fixed-size layout pattern generation, while the more practical free-size pattern generation receives limited attention. In this paper, we propose ChatPattern, a novel Large-Language-Model (LLM) powered framework for flexible pattern customization. ChatPattern utilizes a two-part system featuring an expert LLM agent and a highly controllable layout pattern generator. The LLM agent can interpret natural language requirements and operate design tools to meet specified needs, while the generator excels in conditional layout generation, pattern modification, and memory-friendly patterns extension. Experiments on challenging pattern generation setting shows the ability of ChatPattern to synthesize high-quality large-scale patterns.

Pre-training image representations from the raw text about images enables zero-shot vision transfer to downstream tasks. Through pre-training on millions of samples collected from the internet, multimodal foundation models, such as CLIP, produce state-of-the-art zero-shot results that often reach competitiveness with fully supervised methods without the need for task-specific training. Besides the encouraging performance on classification accuracy, it is reported that these models close the robustness gap by matching the performance of supervised models trained on ImageNet under natural distribution shift. Because robustness is critical to real-world applications, especially safety-critical ones, in this paper, we present a comprehensive evaluation based on a large-scale robustness benchmark covering 7 natural, 3 synthetic distribution shifts, and 11 adversarial attacks. We use CLIP as a pilot study. We show that CLIP leads to a significant robustness drop compared to supervised ImageNet models on our benchmark, especially under synthetic distribution shift and adversarial attacks. Furthermore, data overlap analysis suggests that the observed robustness under natural distribution shifts could be attributed, at least in part, to data overlap. In summary, our evaluation shows a comprehensive evaluation of robustness is necessary; and there is a significant need to improve the robustness of zero-shot multimodal models.

Creating controlled methods to simulate neurodegeneration in artificial intelligence (AI) is crucial for applications that emulate brain function decline and cognitive disorders. We use IQ tests performed by Large Language Models (LLMs) and, more specifically, the LLaMA 2 to introduce the concept of ``neural erosion." This deliberate erosion involves ablating synapses or neurons, or adding Gaussian noise during or after training, resulting in a controlled progressive decline in the LLMs' performance. We are able to describe the neurodegeneration in the IQ tests and show that the LLM first loses its mathematical abilities and then its linguistic abilities, while further losing its ability to understand the questions. To the best of our knowledge, this is the first work that models neurodegeneration with text data, compared to other works that operate in the computer vision domain. Finally, we draw similarities between our study and cognitive decline clinical studies involving test subjects. We find that with the application of neurodegenerative methods, LLMs lose abstract thinking abilities, followed by mathematical degradation, and ultimately, a loss in linguistic ability, responding to prompts incoherently. These findings are in accordance with human studies.