Despite the significant advancements in Text-to-SQL (Text2SQL) facilitated by large language models (LLMs), the latest state-of-the-art techniques are still trapped in the in-context learning of closed-source LLMs (e.g., GPT-4), which limits their applicability in open scenarios. Our approach begins with multi-task supervised fine-tuning (SFT) using various synthetic training data related to SQL generation. Unlike existing SFT-based Text2SQL methods, we introduced several additional SFT tasks, including schema linking, noise correction, and continuation writing. Engaging in a variety of SQL generation tasks enhances the model's understanding of SQL syntax and improves its ability to generate high-quality SQL queries. Additionally, inspired by the collaborative modes of LLM agents, we introduce a Multitask Collaboration Prompting (MCP) strategy. This strategy leverages collaboration across several SQL-related tasks to reduce hallucinations during SQL generation, thereby maximizing the potential of enhancing Text2SQL performance through explicit multitask capabilities. Extensive experiments and in-depth analyses have been performed on eight open-source LLMs and five widely-used benchmarks. The results demonstrate that our proposal outperforms the latest Text2SQL methods and yields promising performance. The code and data are available here. Text2SQL has emerged as a popular and practical technology for question answering based on largescale databases, serving as a crucial link between natural language and database systems (Zhang et al., 2024). Recently, Large Language Models (LLMs) have proven to be an effective solution in Text2SQL (Pourreza & Rafiei, 2024a).

This paper presents a pioneering methodology, termed StructTuning, to efficiently transform foundation Large Language Models (LLMs) into domain specialists. It significantly minimizes the training corpus requirement to a mere 0.3% while achieving an impressive 50% of traditional knowledge injection performance. Our method is inspired by the educational processes for human students, particularly how structured domain knowledge from textbooks is absorbed and then applied to tackle real-world challenges through specific exercises. Based on this, we propose a novel two-stage knowledge injection strategy: Structure-aware Continual Pre-Training (SCPT) and Structure-aware Supervised Fine-Tuning (SSFT). In the SCPT phase, we organize the training data into an auto-generated taxonomy of domain knowledge, enabling LLMs to effectively memorize textual segments linked to specific expertise within the taxonomy's architecture. Subsequently, in the SSFT phase, we explicitly prompt models to reveal the underlying knowledge structure in their outputs, leveraging this structured domain insight to address practical problems adeptly. Our ultimate method has undergone extensive evaluations across model architectures and scales, using closed-book question-answering tasks on LongBench and MMedBench datasets. Remarkably, our method matches 50% of the improvement displayed by the state-of-the-art MMedLM2 on MMedBench, but with only 0.3% quantity of the training corpus. This breakthrough showcases the potential to scale up our StructTuning for stronger domain-specific LLMs. Code will be made public soon.

Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing significant risks for future model deployment. In this paper, we introduce CARES and aim to Comprehensively evAluate the tRustworthinESs of Med-LVLMs across the medical domain. We assess the trustworthiness of Med-LVLMs across five dimensions, including trustfulness, fairness, safety, privacy, and robustness. CARES comprises about 41K question-answer pairs in both closed and open-ended formats, covering 16 medical image modalities and 27 anatomical regions. Our analysis reveals that the models consistently exhibit concerns regarding trustworthiness, often displaying factual inaccuracies and failing to maintain fairness across different demographic groups. Furthermore, they are vulnerable to attacks and demonstrate a lack of privacy awareness.

Model Weight Averaging (MWA) is a technique that seeks to enhance model's performance by averaging the weights of multiple trained models. This paper first empirically finds that 1) the vanilla MWA can benefit the class-imbalanced learning, and 2) performing model averaging in the early epochs of training yields a greater performance improvement than doing that in later epochs. Inspired by these two observations, in this paper we propose a novel MWA technique for class-imbalanced learning tasks named Iterative Model Weight Averaging (IMWA). Specifically, IMWA divides the entire training stage into multiple episodes. Within each episode, multiple models are concurrently trained from the same initialized model weight, and subsequently averaged into a singular model. Then, the weight of this average model serves as a fresh initialization for the ensuing episode, thus establishing an iterative learning paradigm. Compared to vanilla MWA, IMWA achieves higher performance improvements with the same computational cost. Moreover, IMWA can further enhance the performance of those methods employing EMA strategy, demonstrating that IMWA and EMA can complement each other. Extensive experiments on various class-imbalanced learning tasks, i.e., class-imbalanced image classification, semi-supervised class-imbalanced image classification and semi-supervised object detection tasks showcase the effectiveness of our IMWA.

This paper mainly describes a unified system for hallucination detection of LLMs, which wins the second prize in the model-agnostic track of the SemEval-2024 Task 6, and also achieves considerable results in the model-aware track. This task aims to detect hallucination with LLMs for three different text-generation tasks without labeled training data. We utilize prompt engineering and few-shot learning to verify the performance of different LLMs on the validation data. Then we select the LLMs with better performance to generate high-quality weakly supervised training data, which not only satisfies the consistency of different LLMs, but also satisfies the consistency of the optimal LLM with different sampling parameters. Furthermore, we finetune different LLMs by using the constructed training data, and finding that a relatively small LLM can achieve a competitive level of performance in hallucination detection, when compared to the large LLMs and the prompt-based approaches using GPT-4.

Knowledge hallucination have raised widespread concerns for the security and reliability of deployed LLMs. Previous efforts in detecting hallucinations have been employed at logit-level uncertainty estimation or language-level self-consistency evaluation, where the semantic information is inevitably lost during the tokendecoding procedure. Thus, we propose to explore the dense semantic information retained within LLMs' INternal States for hallucInation DEtection (INSIDE). In particular, a simple yet effective EigenScore metric is proposed to better evaluate responses' self-consistency, which exploits the eigenvalues of responses' covariance matrix to measure the semantic consistency/diversity in the dense embedding space. Furthermore, from the perspective of self-consistent hallucination detection, a test time feature clipping approach is explored to truncate extreme activations in the internal states, which reduces overconfident generations and potentially benefits the detection of overconfident hallucinations. Extensive experiments and ablation studies are performed on several popular LLMs and questionanswering (QA) benchmarks, showing the effectiveness of our proposal. Large Language Models (LLMs) have recently achieved a milestone breakthrough and demonstrated impressive abilities in various applications (Ouyang et al., 2022; OpenAI, 2023). However, it has been widely observed that even the state-of-the-art LLMs often make factually incorrect or nonsense generations (Cohen et al., 2023; Ren et al., 2022; Kuhn et al., 2022), which is also known as knowledge hallucination (Ji et al., 2023). The potentially unreliable generations make it risky to deploy LLMs in practical scenarios.

For a machine learning model deployed in real world scenarios, the ability of detecting out-of-distribution (OOD) samples is indispensable and challenging. Most existing OOD detection methods focused on exploring advanced training skills or training-free tricks to prevent the model from yielding overconfident confidence score for unknown samples. The training-based methods require expensive training cost and rely on OOD samples which are not always available, while most training-free methods can not efficiently utilize the prior information from the training data. In this work, we propose an \textbf{O}ptimal \textbf{P}arameter and \textbf{N}euron \textbf{P}runing (\textbf{OPNP}) approach, which aims to identify and remove those parameters and neurons that lead to over-fitting. The main method is divided into two steps. In the first step, we evaluate the sensitivity of the model parameters and neurons by averaging gradients over all training samples. In the second step, the parameters and neurons with exceptionally large or close to zero sensitivities are removed for prediction. Our proposal is training-free, compatible with other post-hoc methods, and exploring the information from all training data. Extensive experiments are performed on multiple OOD detection tasks and model architectures, showing that our proposed OPNP consistently outperforms the existing methods by a large margin.

Sentence-level relation extraction aims to identify the relation between two entities for a given sentence. The existing works mostly focus on obtaining a better entity representation and adopting a multi-label classifier for relation extraction. A major limitation of these works is that they ignore background relational knowledge and the interrelation between entity types and candidate relations. In this work, we propose a new paradigm, Contrastive Learning with Descriptive Relation Prompts(CTL-DRP), to jointly consider entity information, relational knowledge and entity type restrictions. In particular, we introduce an improved entity marker and descriptive relation prompts when generating contextual embedding, and utilize contrastive learning to rank the restricted candidate relations. The CTL-DRP obtains a competitive F1-score of 76.7% on TACRED. Furthermore, the new presented paradigm achieves F1-scores of 85.8% and 91.6% on TACREV and Re-TACRED respectively, which are both the state-of-the-art performance.

In this paper, we present our solution to the Multilingual Information Retrieval Across a Continuum of Languages (MIRACL) challenge of WSDM CUP 2023\footnote{https://project-miracl.github.io/}. Our solution focuses on enhancing the ranking stage, where we fine-tune pre-trained multilingual transformer-based models with MIRACL dataset. Our model improvement is mainly achieved through diverse data engineering techniques, including the collection of additional relevant training data, data augmentation, and negative sampling. Our fine-tuned model effectively determines the semantic relevance between queries and documents, resulting in a significant improvement in the efficiency of the multilingual information retrieval process. Finally, Our team is pleased to achieve remarkable results in this challenging competition, securing 2nd place in the Surprise-Languages track with a score of 0.835 and 3rd place in the Known-Languages track with an average nDCG@10 score of 0.716 across the 16 known languages on the final leaderboard.

In this paper, we present an ensemble approach for the NL4Opt competition subtask 1(NER task). For this task, we first fine tune the pretrained language models based on the competition dataset. Then we adopt differential learning rates and adversarial training strategies to enhance the model generalization and robustness. Additionally, we use a model ensemble method for the final prediction, which achieves a micro-averaged F1 score of 93.3% and attains the second prize in the NER task.