Sentiment analysis plays a crucial role in various domains, such as business intelligence and financial forecasting. Large language models (LLMs) have become a popular paradigm for sentiment analysis, leveraging multi-task learning to address specific tasks concurrently. However, LLMs with fine-tuning for sentiment analysis often underperforms due to the inherent challenges in managing diverse task complexities. Moreover, constant-weight approaches in multi-task learning struggle to adapt to variations in data characteristics, further complicating model effectiveness. To address these issues, we propose a novel multi-task learning framework with a dynamic adaptive optimization (DAO) module. This module is designed as a plug-and-play component that can be seamlessly integrated into existing models, providing an effective and flexible solution for multi-task learning. The key component of the DAO module is dynamic adaptive loss, which dynamically adjusts the weights assigned to different tasks based on their relative importance and data characteristics during training. Sentiment analyses on a standard and customized financial text dataset demonstrate that the proposed framework achieves superior performance. Specifically, this work improves the Mean Squared Error (MSE) and Accuracy (ACC) by 15.58% and 1.24% respectively, compared with previous work.

Large language models are typically trained on a wide and diverse distribution of text. For example, a "base" or "foundation" model may simultaneously be trained to write news articles, 1990s-era DHTML, and impassioned forum discourse on fictional character romances. While such wide-ranging modeling capabilities are fascinating, they often prove difficult to control for the average user. The release of ChatGPT (and its myriad later offspring) has popularized the "chat" paradigm for interacting with large language models, which imbues a base model with steerability by training it to adopt the persona of a helpful assistant - the "chatbot". A more general version of the chat-tuned model is the instruct-tuned model [24, 33], where the base model is trained to respond to imperative statements, e.g. What are some interesting places to visit in San Francisco?

Due to the growing complexity of modern Integrated Circuits (ICs), automating hardware design can prevent a significant amount of human error from the engineering process and result in less errors. Verilog is a popular hardware description language for designing and modeling digital systems; thus, Verilog generation is one of the emerging areas of research to facilitate the design process. In this work, we propose VerilogCoder, a system of multiple Artificial Intelligence (AI) agents for Verilog code generation, to autonomously write Verilog code and fix syntax and functional errors using collaborative Verilog tools (i.e., syntax checker, simulator, and waveform tracer). Firstly, we propose a task planner that utilizes a novel Task and Circuit Relation Graph retrieval method to construct a holistic plan based on module descriptions. To debug and fix functional errors, we develop a novel and efficient abstract syntax tree (AST)-based waveform tracing tool, which is integrated within the autonomous Verilog completion flow. The proposed methodology successfully generates 94.2% syntactically and functionally correct Verilog code, surpassing the state-of-the-art methods by 33.9% on the VerilogEval-Human v2 benchmark.

Despite their widespread adoption, large language models (LLMs) remain prohibitive to use under resource constraints, with their ever growing sizes only increasing the barrier for use. One noted issue is the high latency associated with auto-regressive generation, rendering large LLMs use dependent on advanced computing infrastructure. Assisted decoding, where a smaller draft model guides a larger target model's generation, has helped alleviate this, but remains dependent on alignment between the two models. Thus if the draft model is insufficiently capable on some domain relative to the target model, performance can degrade. Alternatively, one can leverage multiple draft models to better cover the expertise of the target, but when multiple black-box draft models are available, selecting an assistant without details about its construction can be difficult. To better understand this decision making problem, we observe it as a contextual bandit, where a policy must choose a draft model based on a context. We show that even without prior knowledge of the draft models, creating an offline dataset from only outputs of independent draft/target models and training a policy over the alignment of these outputs can accelerate performance on multiple domains provided the candidates are effective. Further results show this to hold on various settings with multiple assisted decoding candidates, highlighting its flexibility and the advantageous role that such decision making can play.

In the field of psychology, traditional assessment methods, such as standardized scales, are frequently critiqued for their static nature, lack of personalization, and reduced participant engagement, while comprehensive counseling evaluations are often inaccessible. The complexity of quantifying psychological traits further limits these methods. Despite advances with large language models (LLMs), many still depend on single-round Question-and-Answer interactions. To bridge this gap, we introduce PsyDI, a personalized and progressively in-depth chatbot designed for psychological measurements, exemplified by its application in the Myers-Briggs Type Indicator (MBTI) framework. PsyDI leverages user-related multi-modal information and engages in customized, multi-turn interactions to provide personalized, easily accessible measurements, while ensuring precise MBTI type determination. To address the challenge of unquantifiable psychological traits, we introduce a novel training paradigm that involves learning the ranking of proxy variables associated with these traits, culminating in a robust score model for MBTI measurements. The score model enables PsyDI to conduct comprehensive and precise measurements through multi-turn interactions within a unified estimation context. Through various experiments, we validate the efficacy of both the score model and the PsyDI pipeline, demonstrating its potential to serve as a general framework for psychological measurements. Furthermore, the online deployment of PsyDI has garnered substantial user engagement, with over 3,000 visits, resulting in the collection of numerous multi-turn dialogues annotated with MBTI types, which facilitates further research. The source code for the training and web service components is publicly available as a part of OpenDILab at: https://github.com/opendilab/PsyDI

Logs are a first-hand source of information for software maintenance and failure diagnosis. Log parsing, which converts semi-structured log messages into structured templates, is a prerequisite for automated log analysis tasks such as anomaly detection, troubleshooting, and root cause analysis. However, existing log parsers fail in real-world systems for three main reasons. First, traditional heuristics-based parsers require handcrafted features and domain knowledge, which are difficult to generalize at scale. Second, existing large language model-based parsers rely on periodic offline processing, limiting their effectiveness in real-time use cases. Third, existing online parsing algorithms are susceptible to log drift, where slight log changes create false positives that drown out real anomalies. To address these challenges, we propose HELP, a Hierarchical Embeddings-based Log Parser. HELP is the first online semantic-based parser to leverage LLMs for performant and cost-effective log parsing. We achieve this through a novel hierarchical embeddings module, which fine-tunes a text embedding model to cluster logs before parsing, reducing querying costs by multiple orders of magnitude. To combat log drift, we also develop an iterative rebalancing module, which periodically updates existing log groupings. We evaluate HELP extensively on 14 public large-scale datasets, showing that HELP achieves significantly higher F1-weighted grouping and parsing accuracy than current state-of-the-art online log parsers. We also implement HELP into Iudex's production observability platform, confirming HELP's practicality in a production environment. Our results show that HELP is effective and efficient for high-throughput real-world log parsing.

Despite the impressive capabilities of Large Language Models (LLMs) in general medical domains, questions remain about their performance in diagnosing rare diseases. To answer this question, we aim to assess the diagnostic performance of LLMs in rare diseases, and explore methods to enhance their effectiveness in this area. In this work, we introduce a rare disease question-answering (ReDis-QA) dataset to evaluate the performance of LLMs in diagnosing rare diseases. Specifically, we collected 1360 high-quality question-answer pairs within the ReDis-QA dataset, covering 205 rare diseases. Additionally, we annotated meta-data for each question, facilitating the extraction of subsets specific to any given disease and its property. Based on the ReDis-QA dataset, we benchmarked several open-source LLMs, revealing that diagnosing rare diseases remains a significant challenge for these models. To facilitate retrieval augmentation generation for rare disease diagnosis, we collect the first rare diseases corpus (ReCOP), sourced from the National Organization for Rare Disorders (NORD) database. Specifically, we split the report of each rare disease into multiple chunks, each representing a different property of the disease, including their overview, symptoms, causes, effects, related disorders, diagnosis, and standard therapies. This structure ensures that the information within each chunk aligns consistently with a question. Experiment results demonstrate that ReCOP can effectively improve the accuracy of LLMs on the ReDis-QA dataset by an average of 8%. Moreover, it significantly guides LLMs to generate trustworthy answers and explanations that can be traced back to existing literature.

We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM, PLaMo-100B, pre-trained from scratch using datasets dominated by Japanese and English texts as the decoder. We adopt a pre-trained Whisper encoder as an audio encoder, and the audio embeddings from the audio encoder are projected to the text embedding space by an adapter layer and concatenated with text embeddings converted from text prompts to form inputs to the decoder. By providing keywords as prior information in the text prompts, we can contextualize our LLM-based ASR system without modifying the model architecture to transcribe ambiguous words in the input audio accurately. Experimental results demonstrate that providing keywords to the decoder can significantly improve the recognition performance of rare and ambiguous words.

Large Language Models (LLMs), especially following the release of OpenAI's GPT series, have significantly disrupted textual human-machine interaction. They have enabled the development of chat assistants--also known as chatbots--that engage in more natural conversations and better understand users' needs. When combined with Retrieval-Augmented Generation (RAG) [1] techniques, these models can interact with other software systems and expand the information encoded in their parameters with data retrieved from external sources. Some examples described in the literature include FACTS [2], NVIDIA's framework for building assistants that leverage enterprise data for enhancing employee productivity and Abbasian et al. [3] health agents, focused on assisting users with healthcare-related tasks. Another possible domain for such systems is online shopping and delivery services. With estimated global retail e-commerce sales surpassing 6.3 trillion US dollars in 2024 [4], developing alternatives to enhance the customer experience in online purchases holds significant commercial value. In this context, this work describes Retail-GPT, an original open-source RAG-based chatbot designed to guide users through product recommendations and assist with cart operations, aiming to enhance user engagement with retail e-commerce and serve as a virtual sales agent. The goal of this system is to test the viability of such an assistant and provide an adaptable approach for implementing sales chatbots across different retail businesses.

Unit tests represent the most basic level of testing within the software testing lifecycle and are crucial to ensuring software correctness. Designing and creating unit tests is a costly and labor-intensive process that is ripe for automation. Recently, Large Language Models (LLMs) have been applied to various aspects of software development, including unit test generation. Although several empirical studies evaluating LLMs' capabilities in test code generation exist, they primarily focus on simple scenarios, such as the straightforward generation of unit tests for individual methods. These evaluations often involve independent and small-scale test units, providing a limited view of LLMs' performance in real-world software development scenarios. Moreover, previous studies do not approach the problem at a suitable scale for real-life applications. Generated unit tests are often evaluated via manual integration into the original projects, a process that limits the number of tests executed and reduces overall efficiency. To address these gaps, we have developed an approach for generating and evaluating more real-life complexity test suites. Our approach focuses on class-level test code generation and automates the entire process from test generation to test assessment. In this work, we present AgoneTest: an automated system for generating test suites for Java projects and a comprehensive and principled methodology for evaluating the generated test suites. Starting from a state-of-the-art dataset (i.e., Methods2Test), we built a new dataset for comparing human-written tests with those generated by LLMs. Our key contributions include a scalable automated software system, a new dataset, and a detailed methodology for evaluating test quality.