Predicting case criticality helps legal professionals in the court system manage large volumes of case law. This paper introduces the Criticality Prediction dataset, a new resource for evaluating the potential influence of Swiss Federal Supreme Court decisions on future jurisprudence. Unlike existing approaches that rely on resource-intensive manual annotations, we semi-automatically derive labels leading to a much larger dataset than otherwise possible. Our dataset features a two-tier labeling system: (1) the LD-Label, which identifies cases published as Leading Decisions (LD), and (2) the Citation-Label, which ranks cases by their citation frequency and recency. This allows for a more nuanced evaluation of case importance. We evaluate several multilingual models, including fine-tuned variants and large language models, and find that fine-tuned models consistently outperform zero-shot baselines, demonstrating the need for task-specific adaptation. Our contributions include the introduction of this task and the release of a multilingual dataset to the research community.

Large language models (LLMs) serve as giant information stores, often including personal or copyrighted data, and retraining them from scratch is not a viable option. This has led to the development of various fast, approximate unlearning techniques to selectively remove knowledge from LLMs. Prior research has largely focused on minimizing the probabilities of specific token sequences by reversing the language modeling objective. However, these methods still leave LLMs vulnerable to adversarial attacks that exploit indirect references. In this work, we examine the limitations of current unlearning techniques in effectively erasing a particular type of indirect prompt: multi-hop queries. Our findings reveal that existing methods fail to completely remove multi-hop knowledge when one of the intermediate hops is unlearned. To address this issue, we propose MUNCH, a simple uncertainty-based approach that breaks down multi-hop queries into subquestions and leverages the uncertainty of the unlearned model in final decision-making. Empirical results demonstrate the effectiveness of our framework, and MUNCH can be easily integrated with existing unlearning techniques, making it a flexible and useful solution for enhancing unlearning processes.

We present Legal Argument Reasoning (LAR), a novel task designed to evaluate the legal reasoning capabilities of Large Language Models (LLMs). The task requires selecting the correct next statement (from multiple choice options) in a chain of legal arguments from court proceedings, given the facts of the case. We constructed a dataset (LAR-ECHR) for this task using cases from the European Court of Human Rights (ECHR). We evaluated seven general-purpose LLMs on LAR-ECHR and found that (a) the ranking of the models is aligned with that of LegalBench, an established US-based legal reasoning benchmark, even though LAR-ECHR is based on EU law, (b) LAR-ECHR distinguishes top models more clearly, compared to LegalBench, (c) even the best model (GPT-4o) obtains 75.8% accuracy on LAR-ECHR, indicating significant potential for further model improvement. The process followed to construct LAR-ECHR can be replicated with cases from other legal systems.

As the capabilities of Multimodal Large Language Models (MLLMs) continue to improve, the need for higher-order capability evaluation of MLLMs is increasing. However, there is a lack of work evaluating MLLM for higher-order perception and understanding of Chinese visual content. To fill the gap, we introduce the **C**hinese **I**mage **I**mplication understanding **Bench**mark, **CII-Bench**, which aims to assess the higher-order perception and understanding capabilities of MLLMs for Chinese images. CII-Bench stands out in several ways compared to existing benchmarks. Firstly, to ensure the authenticity of the Chinese context, images in CII-Bench are sourced from the Chinese Internet and manually reviewed, with corresponding answers also manually crafted. Additionally, CII-Bench incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, which can deeply reflect the model's understanding of Chinese traditional culture. Through extensive experiments on CII-Bench across multiple MLLMs, we have made significant findings. Initially, a substantial gap is observed between the performance of MLLMs and humans on CII-Bench. The highest accuracy of MLLMs attains 64.4%, where as human accuracy averages 78.2%, peaking at an impressive 81.0%. Subsequently, MLLMs perform worse on Chinese traditional culture images, suggesting limitations in their ability to understand high-level semantics and lack a deep knowledge base of Chinese traditional culture. Finally, it is observed that most models exhibit enhanced accuracy when image emotion hints are incorporated into the prompts. We believe that CII-Bench will enable MLLMs to gain a better understanding of Chinese semantics and Chinese-specific images, advancing the journey towards expert artificial general intelligence (AGI). Our project is publicly available at https://cii-bench.github.io/.

LLM self-evaluation relies on the LLM's own ability to estimate response correctness, which can greatly improve its deployment reliability. In this research track, we propose the Chain-of-Embedding (CoE) in the latent space to enable LLMs to perform output-free self-evaluation. CoE consists of all progressive hidden states produced during the inference time, which can be treated as the latent thinking path of LLMs. We find that when LLMs respond correctly and incorrectly, their CoE features differ, these discrepancies assist us in estimating LLM response correctness. Experiments in four diverse domains and seven LLMs fully demonstrate the effectiveness of our method. Meanwhile, its label-free design intent without any training and millisecond-level computational cost ensure real-time feedback in large-scale scenarios. More importantly, we provide interesting insights into LLM response correctness from the perspective of hidden state changes inside LLMs. Large Language Models (LLMs) have significantly enhanced their ability to generalize across diverse scenarios (Brown et al., 2020; Achiam et al., 2023; GLM et al., 2024). However, their outputs can sometimes be unstable, leading to incorrect responses that may threaten social safety. Therefore, labelfree LLM self-evaluation -- estimating the correctness of LLM responses fully through LLMs' own capabilities -- has emerged as a crucial research area. It can provide real-time response monitoring and feedback in large-scale employments, enhancing the reliability of LLMs (Sun et al., 2024). Popular self-evaluation research in the era of LLMs focuses more on output-based forms (Zhang et al., 2023). Two typical paradigms that do not assess the internal states of LLMs involve directly asking LLMs to express confidence in their responses through well-designed prompts (Lin et al., 2022a; Tian et al., 2023), and generating multiple responses by perturbing prompts (Gao et al., 2024) or decoding sampling (Wang et al., 2023) to calculating the response consistency (Xiong et al., 2024). Besides the two types, other methods basically draw on uncertainty estimation concepts from the era of deep neural networks, leveraging output logits or probability distributions to gauge the confidence of model responses (Malinin & Gales, 2020; Si et al., 2022; Huang et al., 2023; Kuhn et al., 2023). Recently, some research has revealed that the latent space of LLMs contains a substantial amount of untapped hidden state information, they can largely reflect response correctness (Azaria & Mitchell, 2023; Liu et al., 2023; Duan et al., 2024), and are usually more interpretable than LLM output (Li et al., 2024a). However, these output-free research often require correctness labels 0/1 for training probing classifiers to extract features from hidden states (Burns et al., 2022; Sky et al., 2024; Su et al., 2024). This contradicts our goal of being "label-free" and limits the generalization capabilities on unseen data.

This paper presents the IETF Insights project, an automated system that streamlines the generation of comprehensive reports on the activities of the Internet Engineering Task Force (IETF) Working Groups. The system collects, consolidates, and analyzes data from various IETF sources, including meeting minutes, participant lists, drafts and agendas. The core components of the system include data preprocessing code and a report generation module that produces high-quality documents in LaTeX or Markdown. By integrating large Language Models (LLMs) for summaries based on the data as ground truth, the IETF Insights project enhances the accessibility and utility of IETF records, providing a valuable overview of the IETF's activities and contributions to the community.

Legal research is a time-consuming task that most lawyers face on a daily basis. A large part of legal research entails looking up relevant caselaw and bringing it in relation to the case at hand. Lawyers heavily rely on summaries (also called headnotes) to find the right cases quickly. However, not all decisions are annotated with headnotes and writing them is time-consuming. Automated headnote creation has the potential to make hundreds of thousands of decisions more accessible for legal research in Switzerland alone. To kickstart this, we introduce the Swiss Leading Decision Summarization ( SLDS) dataset, a novel cross-lingual resource featuring 18K court rulings from the Swiss Federal Supreme Court (SFSC), in German, French, and Italian, along with German headnotes. We fine-tune and evaluate three mT5 variants, along with proprietary models. Our analysis highlights that while proprietary models perform well in zero-shot and one-shot settings, fine-tuned smaller models still provide a strong competitive edge. We publicly release the dataset to facilitate further research in multilingual legal summarization and the development of assistive technologies for legal professionals

This study investigates how personal differences (digital self-efficacy, technical knowledge, belief in equality, political ideology) and demographic factors (age, education, and income) are associated with perceptions of artificial intelligence (AI) outcomes exhibiting gender and racial bias and with general attitudes towards AI. Analyses of a large-scale experiment dataset (N = 1,206) indicate that digital self-efficacy and technical knowledge are positively associated with attitudes toward AI, while liberal ideologies are negatively associated with outcome trust, higher negative emotion, and greater skepticism. Furthermore, age and income are closely connected to cognitive gaps in understanding discriminatory AI outcomes. These findings highlight the importance of promoting digital literacy skills and enhancing digital self-efficacy to maintain trust in AI and beliefs in AI usefulness and safety. The findings also suggest that the disparities in understanding problematic AI outcomes may be aligned with economic inequalities and generational gaps in society. Overall, this study sheds light on the socio-technological system in which complex interactions occur between social hierarchies, divisions, and machines that reflect and exacerbate the disparities.

Detecting offensive memes is crucial, yet standard deep neural network systems often remain opaque. Various input attribution-based methods attempt to interpret their behavior, but they face challenges with implicitly offensive memes and non-causal attributions. To address these issues, we propose a framework based on a Structural Causal Model (SCM). In this framework, VisualBERT is trained to predict the class of an input meme based on both meme input and causal concepts, allowing for transparent interpretation. Our qualitative evaluation demonstrates the framework's effectiveness in understanding model behavior, particularly in determining whether the model was right due to the right reason, and in identifying reasons behind misclassification. Additionally, quantitative analysis assesses the significance of proposed modelling choices, such as de-confounding, adversarial learning, and dynamic routing, and compares them with input attribution methods. Surprisingly, we find that input attribution methods do not guarantee causality within our framework, raising questions about their reliability in safety-critical applications. The project page is at: https://newcodevelop.github.io/causality_adventure/

Alignment of large language models (LLMs) involves training models on preference-contrastive output pairs to adjust their responses according to human preferences. To obtain such contrastive pairs, traditional methods like RLHF and RLAIF rely on limited contrasting patterns, such as varying model variants or decoding temperatures. This singularity leads to two issues: (1) alignment is not comprehensive; and thereby (2) models are susceptible to jailbreaking attacks. To address these issues, we investigate how to construct more comprehensive and diversified contrasting patterns to enhance preference data (RQ1) and verify the impact of the diversification of contrasting patterns on model alignment (RQ2). For RQ1, we propose PopAlign, a framework that integrates diversified contrasting patterns across the prompt, model, and pipeline levels, introducing six contrasting strategies that do not require additional feedback labeling procedures. Regarding RQ2, we conduct thorough experiments demonstrating that PopAlign significantly outperforms existing methods, leading to more comprehensive alignment.