Dial-insight: Fine-tuning Large Language Models with High-Quality Domain-Specific Data Preventing Capability Collapse

The efficacy of large language models (LLMs) is heavily dependent on the quality of the underlying data, particularly within specialized domains. A common challenge when fine-tuning LLMs for domain-specific applications is the potential degradation of the model's generalization capabilities. To address these issues, we propose a two-stage approach for the construction of production prompts designed to yield high-quality data. This method involves the generation of a diverse array of prompts that encompass a broad spectrum of tasks and exhibit a rich variety of expressions. Furthermore, we introduce a cost-effective, multi-dimensional quality assessment framework to ensure the integrity of the generated labeling data. Utilizing a dataset comprised of service provider and customer interactions from the real estate sector, we demonstrate a positive correlation between data quality and model performance. Notably, our findings indicate that the domain-specific proficiency of general LLMs can be enhanced through fine-tuning with data produced via our proposed method, without compromising their overall generalization abilities, even when exclusively domain-specific data is employed for fine-tuning.

A Usage-centric Take on Intent Understanding in E-Commerce

Identifying and understanding user intents is a pivotal task for E-Commerce. Despite its popularity, intent understanding has not been consistently defined or accurately benchmarked. In this paper, we focus on predicative user intents as "how a customer uses a product", and pose intent understanding as a natural language reasoning task, independent of product ontologies. We identify two weaknesses of FolkScope, the SOTA E-Commerce Intent Knowledge Graph, that limit its capacity to reason about user intents and to recommend diverse useful products. Following these observations, we introduce a Product Recovery Benchmark including a novel evaluation framework and an example dataset. We further validate the above FolkScope weaknesses on this benchmark.

Understanding driver-pedestrian interactions to predict driver yielding: naturalistic open-source dataset collected in Minnesota

Many factors influence the yielding result of a driver-pedestrian interaction, including traffic volume, vehicle speed, roadway characteristics, etc. While individual aspects of these interactions have been explored, comprehensive, naturalistic studies, particularly those considering the built environment's influence on driver-yielding behavior, are lacking. To address this gap, our study introduces an extensive open-source dataset, compiled from video data at 18 unsignalized intersections across Minnesota. Documenting more than 3000 interactions, this dataset provides a detailed view of driver-pedestrian interactions and over 50 distinct contextual variables. The data, which covers individual driver-pedestrian interactions and contextual factors, is made publicly available at https://github.com/tianyi17/pedestrian_yielding_data_MN. Using logistic regression, we developed a classification model that predicts driver yielding based on the identified variables. Our analysis indicates that vehicle speed, the presence of parking lots, proximity to parks or schools, and the width of major road crossings significantly influence driver yielding at unsignalized intersections. This study contributes to one of the most comprehensive driver-pedestrian datasets in the US, offering valuable insights for traffic safety improvements. By making this information available, our study will support communities across Minnesota and the United States in their ongoing efforts to improve road safety for pedestrians.

RACER: Rational Artificial Intelligence Car-following-model Enhanced by Reality

This paper introduces RACER, the Rational Artificial Intelligence Car-following model Enhanced by Reality, a cutting-edge deep learning car-following model, that satisfies partial derivative constraints, designed to predict Adaptive Cruise Control (ACC) driving behavior while staying theoretically feasible. Unlike conventional models, RACER effectively integrates Rational Driving Constraints (RDCs), crucial tenets of actual driving, resulting in strikingly accurate and realistic predictions. Against established models like the Optimal Velocity Relative Velocity (OVRV), a car-following Neural Network (NN), and a car-following Physics-Informed Neural Network (PINN), RACER excels across key metrics, such as acceleration, velocity, and spacing. Notably, it displays a perfect adherence to the RDCs, registering zero violations, in stark contrast to other models. This study highlights the immense value of incorporating physical constraints within AI models, especially for augmenting safety measures in transportation. It also paves the way for future research to test these models against human driving data, with the potential to guide safer and more rational driving behavior. The versatility of the proposed model, including its potential to incorporate additional derivative constraints and broader architectural applications, enhances its appeal and broadens its impact within the scientific community.

Detecting stealthy cyberattacks on adaptive cruise control vehicles: A machine learning approach

With the advent of vehicles equipped with advanced driver-assistance systems, such as adaptive cruise control (ACC) and other automated driving features, the potential for cyberattacks on these automated vehicles (AVs) has emerged. While overt attacks that force vehicles to collide may be easily identified, more insidious attacks, which only slightly alter driving behavior, can result in network-wide increases in congestion, fuel consumption, and even crash risk without being easily detected. To address the detection of such attacks, we first present a traffic model framework for three types of potential cyberattacks: malicious manipulation of vehicle control commands, false data injection attacks on sensor measurements, and denial-of-service (DoS) attacks. We then investigate the impacts of these attacks at both the individual vehicle (micro) and traffic flow (macro) levels. A novel generative adversarial network (GAN)-based anomaly detection model is proposed for real-time identification of such attacks using vehicle trajectory data. We provide numerical evidence {to demonstrate} the efficacy of our machine learning approach in detecting cyberattacks on ACC-equipped vehicles. The proposed method is compared against some recently proposed neural network models and observed to have higher accuracy in identifying anomalous driving behaviors of ACC vehicles.

Synthetic Lagrangian Turbulence by Generative Diffusion Models

Lagrangian turbulence lies at the core of numerous applied and fundamental problems related to the physics of dispersion and mixing in engineering, bio-fluids, atmosphere, oceans, and astrophysics. Despite exceptional theoretical, numerical, and experimental efforts conducted over the past thirty years, no existing models are capable of faithfully reproducing statistical and topological properties exhibited by particle trajectories in turbulence. We propose a machine learning approach, based on a state-of-the-art Diffusion Model, to generate single-particle trajectories in three-dimensional turbulence at high Reynolds numbers, thereby bypassing the need for direct numerical simulations or experiments to obtain reliable Lagrangian data. Our model demonstrates the ability to quantitatively reproduce all relevant statistical benchmarks over the entire range of time scales, including the presence of fat tails distribution for the velocity increments, anomalous power law, and enhancement of intermittency around the dissipative scale. The model exhibits good generalizability for extreme events, achieving unprecedented intensity and rarity. This paves the way for producing synthetic high-quality datasets for pre-training various downstream applications of Lagrangian turbulence.

Real-time Workload Pattern Analysis for Large-scale Cloud Databases

Hosting database services on cloud systems has become a common practice. This has led to the increasing volume of database workloads, which provides the opportunity for pattern analysis. Discovering workload patterns from a business logic perspective is conducive to better understanding the trends and characteristics of the database system. However, existing workload pattern discovery systems are not suitable for large-scale cloud databases which are commonly employed by the industry. This is because the workload patterns of large-scale cloud databases are generally far more complicated than those of ordinary databases. In this paper, we propose Alibaba Workload Miner (AWM), a real-time system for discovering workload patterns in complicated large-scale workloads. AWM encodes and discovers the SQL query patterns logged from user requests and optimizes the querying processing based on the discovered patterns. First, Data Collection & Preprocessing Module collects streaming query logs and encodes them into high-dimensional feature embeddings with rich semantic contexts and execution features. Next, Online Workload Mining Module separates encoded queries by business groups and discovers the workload patterns for each group. Meanwhile, Offline Training Module collects labels and trains the classification model using the labels. Finally, Pattern-based Optimizing Module optimizes query processing in cloud databases by exploiting discovered patterns. Extensive experimental results on one synthetic dataset and two real-life datasets (extracted from Alibaba Cloud databases) show that AWM enhances the accuracy of pattern discovery by 66% and reduce the latency of online inference by 22%, compared with the state-of-the-arts.

Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility

The recent popularity of large language models (LLMs) has brought a significant impact to boundless fields, particularly through their open-ended ecosystem such as the APIs, open-sourced models, and plugins. However, with their widespread deployment, there is a general lack of research that thoroughly discusses and analyzes the potential risks concealed. In that case, we intend to conduct a preliminary but pioneering study covering the robustness, consistency, and credibility of LLMs systems. With most of the related literature in the era of LLM uncharted, we propose an automated workflow that copes with an upscaled number of queries/responses. Overall, we conduct over a million queries to the mainstream LLMs including ChatGPT, LLaMA, and OPT. Core to our workflow consists of a data primitive, followed by an automated interpreter that evaluates these LLMs under different adversarial metrical systems. As a result, we draw several, and perhaps unfortunate, conclusions that are quite uncommon from this trendy community. Briefly, they are: (i)-the minor but inevitable error occurrence in the user-generated query input may, by chance, cause the LLM to respond unexpectedly; (ii)-LLMs possess poor consistency when processing semantically similar query input. In addition, as a side finding, we find that ChatGPT is still capable to yield the correct answer even when the input is polluted at an extreme level. While this phenomenon demonstrates the powerful memorization of the LLMs, it raises serious concerns about using such data for LLM-involved evaluation in academic development. To deal with it, we propose a novel index associated with a dataset that roughly decides the feasibility of using such data for LLM-involved evaluation. Extensive empirical studies are tagged to support the aforementioned claims.

Sources of Hallucination by Large Language Models on Inference Tasks

Large Language Models (LLMs) are claimed to be capable of Natural Language Inference (NLI), necessary for applied tasks like question answering and summarization, yet this capability is under-explored. We present a series of behavioral studies on several LLM families (LLaMA, GPT-3.5, and PaLM) which probe their behavior using controlled experiments. We establish two factors which predict much of their performance, and propose that these are major sources of hallucination in generative LLM. First, the most influential factor is memorization of the training data. We show that models falsely label NLI test samples as entailing when the hypothesis is attested in the training text, regardless of the premise. We further show that named entity IDs are used as "indices" to access the memorized data. Second, we show that LLMs exploit a further corpus-based heuristic using the relative frequencies of words. We show that LLMs score significantly worse on NLI test samples which do not conform to these factors than those which do; we also discuss a tension between the two factors, and a performance trade-off.