Membership inference attacks (MIAs) on diffusion models have emerged as potential evidence of unauthorized data usage in training pre-trained diffusion models. These attacks aim to detect the presence of specific images in training datasets of diffusion models. Our study delves into the evaluation of state-of-the-art MIAs on diffusion models and reveals critical flaws and overly optimistic performance estimates in existing MIA evaluation. We introduce CopyMark, a more realistic MIA benchmark that distinguishes itself through the support for pre-trained diffusion models, unbiased datasets, and fair evaluation pipelines. Through extensive experiments, we demonstrate that the effectiveness of current MIA methods significantly degrades under these more practical conditions. Based on our results, we alert that MIA, in its current state, is not a reliable approach for identifying unauthorized data usage in pre-trained diffusion models. To the best of our knowledge, we are the first to discover the performance overestimation of MIAs on diffusion models and present a unified benchmark for more realistic evaluation. Our code is available on GitHub: \url{https://github.com/caradryanl/CopyMark}.

Recent work in offline reinforcement learning (RL) has demonstrated the effectiveness of formulating decision-making as return-conditioned supervised learning. Notably, the decision transformer (DT) architecture has shown promise across various domains. However, despite its initial success, DTs have underperformed on several challenging datasets in goal-conditioned RL. This limitation stems from the inefficiency of return conditioning for guiding policy learning, particularly in unstructured and suboptimal datasets, resulting in DTs failing to effectively learn temporal compositionality. Moreover, this problem might be further exacerbated in long-horizon sparse-reward tasks. To address this challenge, we propose the Predictive Coding for Decision Transformer (PCDT) framework, which leverages generalized future conditioning to enhance DT methods. PCDT utilizes an architecture that extends the DT framework, conditioned on predictive codings, enabling decision-making based on both past and future factors, thereby improving generalization. Through extensive experiments on eight datasets from the AntMaze and FrankaKitchen environments, our proposed method achieves performance on par with or surpassing existing popular value-based and transformer-based methods in offline goal-conditioned RL. Furthermore, we also evaluate our method on a goal-reaching task with a physical robot.

People with disabilities (PwD) regularly encounter ableist hate and microaggressions online. While online platforms use machine learning models to moderate online harm, there is little research investigating how these models interact with ableism. In this paper, we curated a dataset of 100 social media comments targeted towards PwD, and recruited 160 participants to rate and explain how toxic and ableist these comments were. We then prompted state-of-the art toxicity classifiers (TCs) and large language models (LLMs) to rate and explain the harm. Our analysis revealed that TCs and LLMs rated toxicity significantly lower than PwD, but LLMs rated ableism generally on par with PwD. However, ableism explanations by LLMs overlooked emotional harm, and lacked specificity and acknowledgement of context, important facets of PwD explanations. Going forward, we discuss challenges in designing disability-aware toxicity classifiers, and advocate for the shift from ableism detection to ableism interpretation and explanation.

Machine Unlearning has emerged as a significant area of research, focusing on 'removing' specific subsets of data from a trained model. Fine-tuning (FT) methods have become one of the fundamental approaches for approximating unlearning, as they effectively retain model performance. However, it is consistently observed that naive FT methods struggle to forget the targeted data. In this paper, we present the first theoretical analysis of FT methods for machine unlearning within a linear regression framework, providing a deeper exploration of this phenomenon. We investigate two scenarios with distinct features and overlapping features. Our findings reveal that FT models can achieve zero remaining loss yet fail to forget the forgetting data, unlike golden models (trained from scratch without the forgetting data). This analysis reveals that naive FT methods struggle with forgetting because the pretrained model retains information about the forgetting data, and the fine-tuning process has no impact on this retained information. To address this issue, we first propose a theoretical approach to mitigate the retention of forgetting data in the pretrained model. Our analysis shows that removing the forgetting data's influence allows FT models to match the performance of the golden model. Building on this insight, we introduce a discriminative regularization term to practically reduce the unlearning loss gap between the fine-tuned model and the golden model. Our experiments on both synthetic and real-world datasets validate these theoretical insights and demonstrate the effectiveness of the proposed regularization method.

Detecting logical fallacies in texts can help users spot argument flaws, but automating this detection is not easy. Manually annotating fallacies in large-scale, real-world text data to create datasets for developing and validating detection models is costly. This paper introduces CoCoLoFa, the largest known logical fallacy dataset, containing 7,706 comments for 648 news articles, with each comment labeled for fallacy presence and type. We recruited 143 crowd workers to write comments embodying specific fallacy types (e.g., slippery slope) in response to news articles. Recognizing the complexity of this writing task, we built an LLM-powered assistant into the workers' interface to aid in drafting and refining their comments. Experts rated the writing quality and labeling validity of CoCoLoFa as high and reliable. BERT-based models fine-tuned using CoCoLoFa achieved the highest fallacy detection (F1=0.86) and classification (F1=0.87) performance on its test set, outperforming the state-of-the-art LLMs. Our work shows that combining crowdsourcing and LLMs enables us to more effectively construct datasets for complex linguistic phenomena that crowd workers find challenging to produce on their own.

A preliminary empirical evaluation indicates that this work is seen as very promising, and has the potential to become a foundation for real-world AI tools supporting professionals in the Danish legal sector.

Gender-Based Violence (GBV) is an increasing problem online, but existing datasets fail to capture the plurality of possible annotator perspectives or ensure the representation of affected groups. We revisit two important stages in the moderation pipeline for GBV: (1) manual data labelling; and (2) automated classification. For (1), we examine two datasets to investigate the relationship between annotator identities and attitudes and the responses they give to two GBV labelling tasks. To this end, we collect demographic and attitudinal information from crowd-sourced annotators using three validated surveys from Social Psychology. We find that higher Right Wing Authoritarianism scores are associated with a higher propensity to label text as sexist, while for Social Dominance Orientation and Neosexist Attitudes, higher scores are associated with a negative tendency to do so. For (2), we conduct classification experiments using Large Language Models and five prompting strategies, including infusing prompts with annotator information. We find: (i) annotator attitudes affect the ability of classifiers to predict their labels; (ii) including attitudinal information can boost performance when we use well-structured brief annotator descriptions; and (iii) models struggle to reflect the increased complexity and imbalanced classes of the new label sets.

Instruction-tuned LLMs are able to provide an explanation about their output to users by generating self-explanations that do not require gradient computations or the application of possibly complex XAI methods. In this paper, we analyse whether this ability results in a good explanation by evaluating self-explanations in the form of input rationales with respect to their plausibility to humans as well as their faithfulness to models. For this, we apply two text classification tasks: sentiment classification and forced labour detection. Next to English, we further include Danish and Italian translations of the sentiment classification task and compare self-explanations to human annotations for all samples. To allow for direct comparisons, we also compute post-hoc feature attribution, i.e., layer-wise relevance propagation (LRP) and apply this pipeline to 4 LLMs (Llama2, Llama3, Mistral and Mixtral). Our results show that self-explanations align more closely with human annotations compared to LRP, while maintaining a comparable level of faithfulness.

Data annotation refers to the labeling or tagging of textual data with relevant information. A large body of works have reported positive results on leveraging LLMs as an alternative to human annotators. However, existing studies focus on classic NLP tasks, and the extent to which LLMs as data annotators perform in domains requiring expert knowledge remains underexplored. In this work, we investigate comprehensive approaches across three highly specialized domains and discuss practical suggestions from a cost-effectiveness perspective. To the best of our knowledge, we present the first systematic evaluation of LLMs as expert-level data annotators.

Long-context models (LCMs) have made remarkable strides in recent years, offering users great convenience for handling tasks that involve long context, such as document summarization. As the community increasingly prioritizes the faithfulness of generated results, merely ensuring the accuracy of LCM outputs is insufficient, as it is quite challenging for humans to verify the results from the extremely lengthy context. Yet, although some efforts have been made to assess whether LCMs respond truly based on the context, these works either are limited to specific tasks or heavily rely on external evaluation resources like GPT4.In this work, we introduce L-CiteEval, a comprehensive multi-task benchmark for long-context understanding with citations, aiming to evaluate both the understanding capability and faithfulness of LCMs. L-CiteEval covers 11 tasks from diverse domains, spanning context lengths from 8K to 48K, and provides a fully automated evaluation suite. Through testing with 11 cutting-edge closed-source and open-source LCMs, we find that although these models show minor differences in their generated results, open-source models substantially trail behind their closed-source counterparts in terms of citation accuracy and recall. This suggests that current open-source LCMs are prone to responding based on their inherent knowledge rather than the given context, posing a significant risk to the user experience in practical applications. We also evaluate the RAG approach and observe that RAG can significantly improve the faithfulness of LCMs, albeit with a slight decrease in the generation quality. Furthermore, we discover a correlation between the attention mechanisms of LCMs and the citation generation process.