Related papers: LatentRefusal: Latent-Signal Refusal for Unanswera…
Large language models (LLMs) have emerged as a new paradigm for Text-to-SQL task. However, the absence of a systematical benchmark inhibits the development of designing effective, efficient and economic LLM-based Text-to-SQL solutions. To…
Text-to-SQL generation aims to translate natural language questions into SQL statements. In Text-to-SQL based on large language models, schema linking is a widely adopted strategy to streamline the input for LLMs by selecting only relevant…
Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…
Despite the success of large language models (LLMs) in Text-to-SQL tasks, open-source LLMs encounter challenges in contextual understanding and response coherence. To tackle these issues, we present \ours, a systematic methodology tailored…
Previous text-to-SQL datasets and systems have primarily focused on user questions with clear intentions that can be answered. However, real user questions can often be ambiguous with multiple interpretations or unanswerable due to a lack…
Safety alignment in large language models (LLMs) is primarily evaluated under open-ended generation, where models can mitigate risk by refusing to respond. In contrast, many real-world applications place LLMs in structured decision-making…
Large language models (LLMs) with in-context learning have significantly improved the performance of text-to-SQL task. Previous works generally focus on using exclusive SQL generation prompt to improve the LLMs' reasoning ability. However,…
Retrieval-Augmented Generation (RAG) has emerged as the predominant paradigm for grounding Large Language Model outputs in factual knowledge, effectively mitigating hallucinations. However, conventional RAG systems operate under a…
Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This paper investigates refusal behavior across six LLMs from…
Large language models (LLMs) have revolutionized Text-to-SQL generation, allowing users to query structured data using natural language with growing ease. Yet, real-world deployment remains challenging, especially in complex or unseen…
Text-to-SQL enables users to interact with databases through natural language, simplifying the retrieval and synthesis of information. Despite the success of large language models (LLMs) in converting natural language questions into SQL…
In the multi-turn interaction schema, large language models (LLMs) can leverage user feedback to enhance the quality and relevance of their responses. However, evaluating an LLM's ability to incorporate user refutation feedback is crucial…
Refusals - instances where large language models (LLMs) decline or fail to fully execute user instructions - are crucial for both AI safety and AI capabilities and the reduction of hallucinations in particular. These behaviors are learned…
Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. We present RAID (Refusal-Aware and Integrated Decoding), a framework that…
Text-to-SQL is a challenging task involving multiple reasoning-intensive subtasks, including natural language understanding, database schema comprehension, and precise SQL query formulation. Existing approaches often rely on handcrafted…
Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly…
Large Language Models (LLMs) often struggle with the precise logic and schema alignment required for complex Text-to-SQL tasks. While current methods rely heavily on static prompting, they lack the ability to dynamically adapt and…
Text-to-SQL systems empower users to interact with databases using natural language, automatically translating queries into executable SQL code. However, their reliance on database schema information for SQL generation exposes them to…
Large Audio-Language Models (LALMs) are becoming essential as a powerful multimodal backbone for real-world applications. However, recent studies show that audio inputs can more easily elicit harmful responses than text, exposing new risks…
To access data stored in relational databases, users need to understand the database schema and write a query using a query language such as SQL. To simplify this task, text-to-SQL models attempt to translate a user's natural language…