Recently, Large Language Models (LLMs) make remarkable evolutions in language understanding and generation. Following this, various benchmarks for measuring all kinds of capabilities of LLMs have sprung up. In this paper, we challenge the reasoning and understanding abilities of LLMs by proposing a FaLlacy Understanding Benchmark (FLUB) containing cunning texts that are easy for humans to understand but difficult for models to grasp. Specifically, the cunning texts that FLUB focuses on mainly consist of the tricky, humorous, and misleading texts collected from the real internet environment. And we design three tasks with increasing difficulty in the FLUB benchmark to evaluate the fallacy understanding ability of LLMs. Based on FLUB, we investigate the performance of multiple representative and advanced LLMs, reflecting our FLUB is challenging and worthy of more future study. Interesting discoveries and valuable insights are achieved in our extensive experiments and detailed analyses. We hope that our benchmark can encourage the community to improve LLMs' ability to understand fallacies. Our data and codes are available at https://github.com/THUKElab/FLUB.

Generative Artificial Intelligence (GenAI), specifically large language models like ChatGPT, has swiftly entered organizations without adequate governance, posing both opportunities and risks. Despite extensive debates on GenAI's transformative nature and regulatory measures, limited research addresses organizational governance, encompassing technical and business perspectives. Our review paper fills this gap by surveying recent works with the purpose of developing a framework for GenAI governance within companies. This framework outlines the scope, objectives, and governance mechanisms tailored to harness business opportunities as well as mitigate risks associated with GenAI integration. Our research contributes a focused approach to GenAI governance, offering practical insights for companies navigating the challenges of GenAI adoption and highlighting research gaps.

Language models (LMs) are trained on web text originating from many points in time and, in general, without any explicit temporal grounding. This work investigates the temporal chaos of pretrained LMs and explores various methods to align their internal knowledge to a target time, which we call "temporal alignment." To do this, we first automatically construct a dataset containing 20K time-sensitive questions and their answers for each year from 2000 to 2023. Based on this dataset, we empirically show that pretrained LMs (e.g., LLaMa2), despite having a recent pretraining cutoff (e.g., 2022), mostly answer questions using earlier knowledge (e.g., in 2019). We then develop several methods, from prompting to finetuning, to align LMs to use their most recent knowledge when answering questions, and investigate various factors in this alignment. Our experiments demonstrate that aligning LLaMa2 to the year 2022 can enhance its performance by up to 62% according to that year's answers. This improvement occurs even without explicitly mentioning time information, indicating the possibility of aligning models' internal sense of time after pretraining. Finally, we find that alignment to a historical time is also possible, with up to 2.8$\times$ the performance of the unaligned LM in 2010 if finetuning models to that year. These findings hint at the sophistication of LMs' internal knowledge organization and the necessity of tuning them properly.

Although Large Language Models (LLMs) exhibit remarkable adaptability across domains, these models often fall short in structured knowledge extraction tasks such as named entity recognition (NER). This paper explores an innovative, cost-efficient strategy to harness LLMs with modest NER capabilities for producing superior NER datasets. Our approach diverges from the basic class-conditional prompts by instructing LLMs to self-reflect on the specific domain, thereby generating domain-relevant attributes (such as category and emotions for movie reviews), which are utilized for creating attribute-rich training data. Furthermore, we preemptively generate entity terms and then develop NER context data around these entities, effectively bypassing the LLMs' challenges with complex structures. Our experiments across both general and niche domains reveal significant performance enhancements over conventional data generation methods while being more cost-effective than existing alternatives.

Embedding as a Service (EaaS) has become a widely adopted solution, which offers feature extraction capabilities for addressing various downstream tasks in Natural Language Processing (NLP). Prior studies have shown that EaaS can be prone to model extraction attacks; nevertheless, this concern could be mitigated by adding backdoor watermarks to the text embeddings and subsequently verifying the attack models post-publication. Through the analysis of the recent watermarking strategy for EaaS, EmbMarker, we design a novel CSE (Clustering, Selection, Elimination) attack that removes the backdoor watermark while maintaining the high utility of embeddings, indicating that the previous watermarking approach can be breached. In response to this new threat, we propose a new protocol to make the removal of watermarks more challenging by incorporating multiple possible watermark directions. Our defense approach, WARDEN, notably increases the stealthiness of watermarks and has been empirically shown to be effective against CSE attack.

Large Language Models (LLMs) have achieved unparalleled success across diverse language modeling tasks in recent years. However, this progress has also intensified ethical concerns, impacting the deployment of LLMs in everyday contexts. This paper provides a comprehensive survey of ethical challenges associated with LLMs, from longstanding issues such as copyright infringement, systematic bias, and data privacy, to emerging problems like truthfulness and social norms. We critically analyze existing research aimed at understanding, examining, and mitigating these ethical risks. Our survey underscores integrating ethical standards and societal values into the development of LLMs, thereby guiding the development of responsible and ethically aligned language models.

It has been shown that many generative models inherit and amplify societal biases. To date, there is no uniform/systematic agreed standard to control/adjust for these biases. This study examines the presence and manipulation of societal biases in leading text-to-image models: Stable Diffusion, DALL-E 3, and Adobe Firefly. Through a comprehensive analysis combining base prompts with modifiers and their sequencing, we uncover the nuanced ways these AI technologies encode biases across gender, race, geography, and region/culture. Our findings reveal the challenges and potential of prompt engineering in controlling biases, highlighting the critical need for ethical AI development promoting diversity and inclusivity. This work advances AI ethics by not only revealing the nuanced dynamics of bias in text-to-image generation models but also by offering a novel framework for future research in controlling bias. Our contributions-panning comparative analyses, the strategic use of prompt modifiers, the exploration of prompt sequencing effects, and the introduction of a bias sensitivity taxonomy-lay the groundwork for the development of common metrics and standard analyses for evaluating whether and how future AI models exhibit and respond to requests to adjust for inherent biases.

Detecting subjectivity in news sentences is crucial for identifying media bias, enhancing credibility, and combating misinformation by flagging opinion-based content. It provides insights into public sentiment, empowers readers to make informed decisions, and encourages critical thinking. While research has developed methods and systems for this purpose, most efforts have focused on English and other high-resourced languages. In this study, we present the first large dataset for subjectivity detection in Arabic, consisting of ~3.6K manually annotated sentences, and GPT-4o based explanation. In addition, we included instructions (both in English and Arabic) to facilitate LLM based fine-tuning. We provide an in-depth analysis of the dataset, annotation process, and extensive benchmark results, including PLMs and LLMs. Our analysis of the annotation process highlights that annotators were strongly influenced by their political, cultural, and religious backgrounds, especially at the beginning of the annotation process. The experimental results suggest that LLMs with in-context learning provide better performance. We aim to release the dataset and resources for the community.

Machine learning (ML) has revolutionized the digital transformation of technology valuation by predicting the value of patents with high accuracy. However, the lack of validation regarding the reliability of these models hinders experts from fully trusting the confidence of model predictions. To address this issue, we propose an analytical framework for reliable technology valuation using calibrated ML models, which provide robust confidence levels in model predictions. We extract quantitative patent indicators that represent various technology characteristics as input data, using the patent maintenance period as a proxy for technology values. Multiple ML models are developed to capture the nonlinear relationship between patent indicators and technology value. The reliability and accuracy of these models are evaluated, presenting a Pareto-front map where the expected calibration error, Matthews correlation coefficient and F1-scores are compared. After identifying the best-performing model, we apply SHapley Additive exPlanation (SHAP) analysis to pinpoint the most significant input features by confidence bin. Through a case study, we confirmed that the proposed approach offers a practical guideline for developing reliable and accurate ML-based technology valuation models, with significant implications for both academia and industry.

The rapid development and reduced barriers to entry for Text-to-Image (T2I) models have raised concerns about the biases in their outputs, but existing research lacks a holistic definition and evaluation framework of biases, limiting the enhancement of debiasing techniques. To address this issue, we introduce FAIntbench, a holistic and precise benchmark for biases in T2I models. In contrast to existing benchmarks that evaluate bias in limited aspects, FAIntbench evaluate biases from four dimensions: manifestation of bias, visibility of bias, acquired attributes, and protected attributes. We applied FAIntbench to evaluate seven recent large-scale T2I models and conducted human evaluation, whose results demonstrated the effectiveness of FAIntbench in identifying various biases. Our study also revealed new research questions about biases, including the side-effect of distillation. The findings presented here are preliminary, highlighting the potential of FAIntbench to advance future research aimed at mitigating the biases in T2I models. Our benchmark is publicly available to ensure the reproducibility.