Large Language Models (LLMs) demonstrate substantial potential in delivering legal consultation services to users without a legal background, attributed to their superior text comprehension and generation capabilities. Nonetheless, existing Chinese legal LLMs limit interaction to a single model-user dialogue, unlike the collaborative consultations typical of law firms, where multiple staff members contribute to a single consultation. This limitation prevents an authentic consultation experience. Additionally, extant Chinese legal LLMs suffer from critical limitations: (1) insufficient control over the quality of instruction fine-tuning data; (2) increased model hallucination resulting from users' ambiguous queries; and (3) a reduction in the model's ability to follow instructions over multiple dialogue turns. In response to these challenges, we propose a novel legal dialogue framework that leverages the collaborative capabilities of multiple LLM agents, termed LawLuo. This framework encompasses four agents: a receptionist, a lawyer, a secretary, and a boss, each responsible for different functionalities, collaboratively providing a comprehensive legal consultation to users. Additionally, we constructed two high-quality legal dialogue datasets, KINLED and MURLED, and fine-tuned ChatGLM-3-6b using these datasets. We propose a legal query clarification algorithm called ToLC. Experimental results demonstrate that LawLuo outperforms baseline LLMs, including GPT-4, across three dimensions: lawyer-like language style, the usefulness of legal advice, and the accuracy of legal knowledge. Our code and datasets are available at https://github.com/NEFUJing/LawLuo.

Passive data auditing, commonly referred as membership inference Auditing the use of data in training machine-learning (ML) models [7, 13, 27, 65, 83], infers if a data sample is a member of an is an increasingly pressing challenge, as myriad ML practitioners ML model's training set. However, such passive techniques have an routinely leverage the effort of content creators to train models without inherent limitation: they do not provide any quantitative guarantee their permission. In this paper, we propose a general method for the false-detection of their inference results. In contrast, proactive to audit an ML model for the use of a data-owner's data in training, data auditing techniques embed marks into data before its publication without prior knowledge of the ML task for which the data might [24, 38, 39, 59, 74, 79, 82] and can provide detection results be used.

In the pursuit of enhancing the efficacy and flexibility of interpretable, data-driven classification models, this work introduces a novel incorporation of user-defined preferences with Abstract Argumentation and Case-Based Reasoning (CBR). Specifically, we introduce Preference-Based Abstract Argumentation for Case-Based Reasoning (which we call AA-CBR-P), allowing users to define multiple approaches to compare cases with an ordering that specifies their preference over these comparison approaches. We prove that the model inherently follows these preferences when making predictions and show that previous abstract argumentation for case-based reasoning approaches are insufficient at expressing preferences over constituents of an argument. We then demonstrate how this can be applied to a real-world medical dataset sourced from a clinical trial evaluating differing assessment methods of patients with a primary brain tumour. We show empirically that our approach outperforms other interpretable machine learning models on this dataset.

First son Hunter Biden will be sentenced on Nov. 13, the week after the general election, after he was found guilty on charges in the criminal case focused on his purchase of a handgun in 2018. Judge Maryellen Noreika, in a court order Friday, set the sentencing date for Wednesday, Nov. 13, at 10:00 a.m. at the J. Caleb Boggs Federal Building in Wilmington, Delaware. President Biden's son will learn his fate 8 days after the 2020 presidential election. Hunter Biden was found guilty in June of making a false statement in the purchase of a gun, making a false statement related to information required to be kept by a federally licensed gun dealer, and possession of a gun by a person who is an unlawful user of or addicted to a controlled substance. He faces a total maximum prison time of 25 years for the three charges.

Thanks to a string of leaks and Google's own teases -- usually following said leaks -- we know we'll get the official reveal of the Pixel 9 lineup. The Pixel 9 and 9 Pro will be straight-up successors to the Pixel 8 and 8 Pro but rumors suggest Google will add a Pixel 9 Pro XL, with a larger screen. All three of the phones are expected to have a redesigned, chonky camera module and possibly even a new chipset. Alongside all those phones, we're expecting a lot more news on Gemini, Google's flavor of AI powered assistant, and Android 15. More leaks and rumors point to updated smartwatches and wireless buds too.

In May, a multibillion-dollar UK-based multinational called Informa announced in a trading update that it had signed a deal with Microsoft involving "access to advanced learning content and data, and a partnership to explore AI expert applications". Informa is the parent company of Taylor & Francis, which publishes a wide range of academic and technical books and journals, so the data in question may include the content of these books and journals. According to reports published last week, the authors of the content do not appear to have been asked or even informed about the deal. What's more, they say they had no opportunity to opt out of the deal, and will not see any money from it. Academics are only the latest of several groups of what we might call content creators to take umbrage at having their work ingested by the generative AI models currently racing to hoover up the products of human culture.

This workshop will grow and consolidate a community of interdisciplinary CSCW researchers focusing on the topic of contestable AI. As an outcome of the workshop, we will synthesize the most pressing opportunities and challenges for contestability along AI value chains in the form of a research roadmap. This roadmap will help shape and inspire imminent work in this field. Considering the length and depth of AI value chains, it will especially spur discussions around the contestability of AI systems along various sites of such chains. The workshop will serve as a platform for dialogue and demonstrations of concrete, successful, and unsuccessful examples of AI systems that (could or should) have been contested, to identify requirements, obstacles, and opportunities for designing and deploying contestable AI in various contexts. This will be held primarily as an in-person workshop, with some hybrid accommodation. The day will consist of individual presentations and group activities to stimulate ideation and inspire broad reflections on the field of contestable AI. Our aim is to facilitate interdisciplinary dialogue by bringing together researchers, practitioners, and stakeholders to foster the design and deployment of contestable AI.

Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc evaluations and do not share theoretical foundations, making it difficult to measure progress and compare the pros and cons of different techniques. Furthermore, while mechanistic understanding is frequently discussed, the basic causal units underlying these mechanisms are often not explicitly defined. In this paper, we propose a perspective on interpretability research grounded in causal mediation analysis. Specifically, we describe the history and current state of interpretability taxonomized according to the types of causal units (mediators) employed, as well as methods used to search over mediators. We discuss the pros and cons of each mediator, providing insights as to when particular kinds of mediators and search methods are most appropriate depending on the goals of a given study. We argue that this framing yields a more cohesive narrative of the field, as well as actionable insights for future work. Specifically, we recommend a focus on discovering new mediators with better trade-offs between human-interpretability and compute-efficiency, and which can uncover more sophisticated abstractions from neural networks than the primarily linear mediators employed in current work. We also argue for more standardized evaluations that enable principled comparisons across mediator types, such that we can better understand when particular causal units are better suited to particular use cases.

Learning token embeddings based on token co-occurrence statistics has proven effective for both pre-training and fine-tuning in natural language processing. However, recent studies have pointed out the distribution of learned embeddings degenerates into anisotropy, and even pre-trained language models (PLMs) suffer from a loss of semantics-related information in embeddings for low-frequency tokens. This study first analyzes fine-tuning dynamics of a PLM, BART-large, and demonstrates its robustness against degeneration. On the basis of this finding, we propose DefinitionEMB, a method that utilizes definitions to construct isotropically distributed and semantics-related token embeddings for PLMs while maintaining original robustness during fine-tuning. Our experiments demonstrate the effectiveness of leveraging definitions from Wiktionary to construct such embeddings for RoBERTa-base and BART-large. Furthermore, the constructed embeddings for low-frequency tokens improve the performance of these models across various GLUE and four text summarization datasets.

When most tech companies are challenged with a lawsuit, the expected defense is to deny wrongdoing. To give a reasonable explanation of why the business' actions were not breaking any laws. Music AI startups Udio and Suno have gone for a different approach: admit to doing exactly what you were sued for. And that's because its training data "includes essentially all music files of reasonable quality that are accessible on the open internet," which likely include millions of illegal copies of songs. But the company is taking the line that its scraping falls under the umbrella of fair use.