We present an automatic large language model (LLM) conversion approach that produces uncertainty-aware LLMs capable of estimating uncertainty with every prediction. Our approach is model- and data-agnostic, is computationally-efficient, and does not rely on external models or systems. We evaluate converted models on the selective question answering setting -- to answer as many questions as possible while maintaining a given accuracy, forgoing providing predictions when necessary. As part of our results, we test BERT and Llama 2 model variants on the SQuAD extractive QA task and the TruthfulQA generative QA task. We show that using the uncertainty estimates provided by our approach to selectively answer questions leads to significantly higher accuracy over directly using model probabilities.

The wide adoption and usage of generative artificial intelligence (AI) models, particularly ChatGPT, has sparked a surge in research exploring their potential applications in the educational landscape. This survey examines academic literature published between November, 2022, and July, 2023, specifically targeting high-impact research from Scopus-indexed Q1 and Q2 journals. This survey delves into the practical applications and implications of generative AI models across a diverse range of educational contexts. Through a comprehensive and rigorous evaluation of recent academic literature, this survey seeks to illuminate the evolving role of generative AI models, particularly ChatGPT, in education. By shedding light on the potential benefits, challenges, and emerging trends in this dynamic field, the survey endeavors to contribute to the understanding of the nexus between artificial intelligence and education. The findings of this review will empower educators, researchers, and policymakers to make informed decisions about the integration of AI technologies into learning environments.

Case studies commonly form the pedagogical backbone in law, ethics, and many other domains that face complex and ambiguous societal questions informed by human values. Similar complexities and ambiguities arise when we consider how AI should be aligned in practice: when faced with vast quantities of diverse (and sometimes conflicting) values from different individuals and communities, with whose values is AI to align, and how should AI do so? We propose a complementary approach to constitutional AI alignment, grounded in ideas from case-based reasoning (CBR), that focuses on the construction of policies through judgments on a set of cases. We present a process to assemble such a case repository by: 1) gathering a set of ``seed'' cases -- questions one may ask an AI system -- in a particular domain, 2) eliciting domain-specific key dimensions for cases through workshops with domain experts, 3) using LLMs to generate variations of cases not seen in the wild, and 4) engaging with the public to judge and improve cases. We then discuss how such a case repository could assist in AI alignment, both through directly acting as precedents to ground acceptable behaviors, and as a medium for individuals and communities to engage in moral reasoning around AI.

Predicting opinion trends on a range of social issues, from climate change to gay marriage, is crucial for making informed decisions, tracking social changes, and understanding the dynamics of opinion formation (Brooks and Manza, 2006; Burstein, 2003). Recently, numerous breakthroughs have been made to infer and predict people's opinions and preferences from their written records, such as books in the past (e.g., Google Ngram), internet search patterns (e.g., Google Trend), and public sentiments in social media (e.g., Twitter, Facebook, YouTube) (Beauchamp, 2017; Grimmer et al., 2022; Moore et al., 2019; O'Connor et al., 2010; Stephens-Davidowitz, 2017). However, using digital trace data for predicting public opinion presents a substantial challenge, as these "proxy" measures cannot be deemed reliable without validating them against other "ground truth" benchmarks, like surveys (Beauchamp, 2017; Ferraro and Farmer, 1999). Even if digital trace data can closely track public opinion trends, its unobtrusive and anonymous nature prompts questions about its ability to truly represent the diverse voices of the population, particularly considering the skewed representation of demographic groups in digital traces (Cesare et al., 2018). The reliance on digital trace data, despite covering a broad spectrum of opinions, makes it hard to evenly represent the real voice of the entire population.

The advent of artificial intelligence (AI) has significantly impacted the traditional judicial industry. Moreover, recently, with the development of AI-generated content (AIGC), AI and law have found applications in various domains, including image recognition, automatic text generation, and interactive chat. With the rapid emergence and growing popularity of large models, it is evident that AI will drive transformation in the traditional judicial industry. However, the application of legal large language models (LLMs) is still in its nascent stage. Several challenges need to be addressed. In this paper, we aim to provide a comprehensive survey of legal LLMs. We not only conduct an extensive survey of LLMs, but also expose their applications in the judicial system. We first provide an overview of AI technologies in the legal field and showcase the recent research in LLMs. Then, we discuss the practical implementation presented by legal LLMs, such as providing legal advice to users and assisting judges during trials. In addition, we explore the limitations of legal LLMs, including data, algorithms, and judicial practice. Finally, we summarize practical recommendations and propose future development directions to address these challenges.

In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review effort (like "technology assisted review") can create false negatives, since they are often based on active learning systems that exclude documents automatically based on user feedback. Therefore, this research proposes a more recall-oriented approach to reducing review effort. More specifically, through iteratively re-ranking the relevance rankings based on user feedback, which is also referred to as relevance feedback. In our proposed method, the relevance rankings are produced by a BERT-based dense-vector search and the relevance feedback is based on cumulatively summing the queried and selected embeddings. Our results show that this method can reduce review effort between 17.85% and 59.04%, compared to a baseline approach (of no feedback), given a fixed recall target.

High-risk domains pose unique challenges that require language models to provide accurate and safe responses. Despite the great success of large language models (LLMs), such as ChatGPT and its variants, their performance in high-risk domains remains unclear. Our study delves into an in-depth analysis of the performance of instruction-tuned LLMs, focusing on factual accuracy and safety adherence. To comprehensively assess the capabilities of LLMs, we conduct experiments on six NLP datasets including question answering and summarization tasks within two high-risk domains: legal and medical. Further qualitative analysis highlights the existing limitations inherent in current LLMs when evaluating in high-risk domains. This underscores the essential nature of not only improving LLM capabilities but also prioritizing the refinement of domain-specific metrics, and embracing a more human-centric approach to enhance safety and factual reliability. Our findings advance the field toward the concerns of properly evaluating LLMs in high-risk domains, aiming to steer the adaptability of LLMs in fulfilling societal obligations and aligning with forthcoming regulations, such as the EU AI Act.

Large language models (LLMs) have demonstrated remarkable capabilities across a broad spectrum of tasks. They have attracted significant attention and been deployed in numerous downstream applications. Nevertheless, akin to a double-edged sword, LLMs also present potential risks. They could suffer from private data leaks or yield inappropriate, harmful, or misleading content. Additionally, the rapid progress of LLMs raises concerns about the potential emergence of superintelligent systems without adequate safeguards. To effectively capitalize on LLM capacities as well as ensure their safe and beneficial development, it is critical to conduct a rigorous and comprehensive evaluation of LLMs. This survey endeavors to offer a panoramic perspective on the evaluation of LLMs. We categorize the evaluation of LLMs into three major groups: knowledge and capability evaluation, alignment evaluation and safety evaluation. In addition to the comprehensive review on the evaluation methodologies and benchmarks on these three aspects, we collate a compendium of evaluations pertaining to LLMs' performance in specialized domains, and discuss the construction of comprehensive evaluation platforms that cover LLM evaluations on capabilities, alignment, safety, and applicability. We hope that this comprehensive overview will stimulate further research interests in the evaluation of LLMs, with the ultimate goal of making evaluation serve as a cornerstone in guiding the responsible development of LLMs. We envision that this will channel their evolution into a direction that maximizes societal benefit while minimizing potential risks. A curated list of related papers has been publicly available at https://github.com/tjunlp-lab/Awesome-LLMs-Evaluation-Papers.

We don't fully understand how large language models work AI models can trick each other into disobeying their creators and providing banned instructions for making methamphetamine, building a bomb or laundering money, suggesting that the problem of preventing such AI "jailbreaks" is more difficult than it seems.

Counterfactual Explanations are becoming a de-facto standard in post-hoc interpretable machine learning. For a given classifier and an instance classified in an undesired class, its counterfactual explanation corresponds to small perturbations of that instance that allows changing the classification outcome. This work aims to leverage Counterfactual Explanations to detect the important decision boundaries of a pre-trained black-box model. This information is used to build a supervised discretization of the features in the dataset with a tunable granularity. Using the discretized dataset, an optimal Decision Tree can be trained that resembles the black-box model, but that is interpretable and compact. Numerical results on real-world datasets show the effectiveness of the approach in terms of accuracy and sparsity.