The method of training language models based on domain datasets has obtained significant achievements in the task of generating scientific paper abstracts. However, such models face problems of generalization and expensive training costs. The use of large language models (LLMs) to solve the task of generating paper abstracts saves the cost of model training. However, due to the hallucination problem of LLM, it is often necessary to improve the reliability of the results through multi-round query prompt approach such as Graph of Thoughts (GoT), which also brings additional reasoning costs. In this paper, we propose a Dynamic Graph of Thought (DGoT). It not only inherits the advantages of the existing GoT prompt approach, but also dynamically adjust the graph structure according to data characteristics while reducing model reasoning cost. Experimental results show that our method's cost-effectiveness in abstract generation tasks is only 43.7% to 56.4% of other multi-round query prompt approaches. Our code is available at https://github.com/JayceNing/DGoT.

LLM-as-a-Judge is a novel solution that can assess textual information with large language models (LLMs). Based on existing research studies, LLMs demonstrate remarkable performance in providing a compelling alternative to traditional human assessment. However, the robustness of these systems against prompt injection attacks remains an open question. In this work, we introduce JudgeDeceiver, a novel optimization-based prompt injection attack tailored to LLM-as-a-Judge. Our method formulates a precise optimization objective for attacking the decision-making process of LLM-as-a-Judge and utilizes an optimization algorithm to efficiently automate the generation of adversarial sequences, achieving targeted and effective manipulation of model evaluations. Compared to handcraft prompt injection attacks, our method demonstrates superior efficacy, posing a significant challenge to the current security paradigms of LLM-based judgment systems. Through extensive experiments, we showcase the capability of JudgeDeceiver in altering decision outcomes across various cases, highlighting the vulnerability of LLM-as-a-Judge systems to the optimization-based prompt injection attack.

Quickly understanding lengthy lecture videos is essential for learners with limited time and interest in various topics to improve their learning efficiency. To this end, video summarization has been actively researched to enable users to view only important scenes from a video. However, these studies focus on either the visual or audio information of a video and extract important segments in the video. Therefore, there is a risk of missing important information when both the teacher's speech and visual information on the blackboard or slides are important, such as in a lecture video. To tackle this issue, we propose FastPerson, a video summarization approach that considers both the visual and auditory information in lecture videos. FastPerson creates summary videos by utilizing audio transcriptions along with on-screen images and text, minimizing the risk of overlooking crucial information for learners. Further, it provides a feature that allows learners to switch between the summary and original videos for each chapter of the video, enabling them to adjust the pace of learning based on their interests and level of understanding. We conducted an evaluation with 40 participants to assess the effectiveness of our method and confirmed that it reduced viewing time by 53\% at the same level of comprehension as that when using traditional video playback methods.

Recent advances in interactive large language models like ChatGPT have revolutionized various domains; however, their behavior in natural and role-play conversation settings remains underexplored. In our study, we address this gap by deeply investigating how ChatGPT behaves during conversations in different settings by analyzing its interactions in both a normal way and a role-play setting. We introduce a novel dataset of broad range of human-AI conversations annotated with user motives and model naturalness to examine (i) how humans engage with the conversational AI model, and (ii) how natural are AI model responses. Our study highlights the diversity of user motives when interacting with ChatGPT and variable AI naturalness, showing not only the nuanced dynamics of natural conversations between humans and AI, but also providing new avenues for improving the effectiveness of human-AI communication.

Traditional continual event detection relies on abundant labeled data for training, which is often impractical to obtain in real-world applications. In this paper, we introduce continual few-shot event detection (CFED), a more commonly encountered scenario when a substantial number of labeled samples are not accessible. The CFED task is challenging as it involves memorizing previous event types and learning new event types with few-shot samples. To mitigate these challenges, we propose a memory-based framework: Hierarchical Augmentation Networks (HANet). To memorize previous event types with limited memory, we incorporate prototypical augmentation into the memory set. For the issue of learning new event types in few-shot scenarios, we propose a contrastive augmentation module for token representations. Despite comparing with previous state-of-the-art methods, we also conduct comparisons with ChatGPT. Experiment results demonstrate that our method significantly outperforms all of these methods in multiple continual few-shot event detection tasks.

We acknowledge and thank Michael Howell, MD MPH, Bakul Patel, MSEE MBA, Matthew Thompson, DPhil MPH, Joseph Dooley, MPA, and David Steiner, MD PhD for reviewing and providing helpful feedback on this manuscript. LLMs MENTAL HEALTH 2 Abstract Global rates of mental health concerns are rising and there is increasing realization that existing models of mental healthcare will not adequately expand to meet the demand. With the emergence of large language models (LLMs) has come great optimism regarding their promise to create novel, large-scale solutions to support mental health. Despite their nascence, LLMs have already been applied to mental health-related tasks. In this review, we summarize the extant literature on efforts to use LLMs to provide mental health education, assessment, and intervention and highlight key opportunities for positive impact in each area. We then highlight risks associated with LLMs' application to mental health and encourage adoption of strategies to mitigate these risks. The urgent need for mental health support must be balanced with responsible development, testing, and deployment of mental health LLMs. Especially critical is ensuring that mental health LLMs are fine-tuned for mental health, enhance mental health equity, adhere to ethical standards, and that people, including those with lived experience with mental health concerns, are involved in all stages from development through deployment. Prioritizing these efforts will minimize potential harms to mental health and maximize the likelihood that LLMs will positively impact mental health globally. To overcome inadequate access to effective and equitable mental healthcare, large-scale solutions are needed.

Large Language Models (LLMs) have demonstrated surprising performance on many tasks, including writing supportive messages that display empathy. Here, we had these models generate empathic messages in response to posts describing common life experiences, such as workplace situations, parenting, relationships, and other anxiety- and anger-eliciting situations. Across two studies (N=192, 202), we showed human raters a variety of responses written by several models (GPT4 Turbo, Llama2, and Mistral), and had people rate these responses on how empathic they seemed to be. We found that LLM-generated responses were consistently rated as more empathic than human-written responses. Linguistic analyses also show that these models write in distinct, predictable ``styles", in terms of their use of punctuation, emojis, and certain words. These results highlight the potential of using LLMs to enhance human peer support in contexts where empathy is important.

In this paper, we address the significant gap in Arabic natural language processing (NLP) resources by introducing ArabicaQA, the first large-scale dataset for machine reading comprehension and open-domain question answering in Arabic. This comprehensive dataset, consisting of 89,095 answerable and 3,701 unanswerable questions created by crowdworkers to look similar to answerable ones, along with additional labels of open-domain questions marks a crucial advancement in Arabic NLP resources. We also present AraDPR, the first dense passage retrieval model trained on the Arabic Wikipedia corpus, specifically designed to tackle the unique challenges of Arabic text retrieval. Furthermore, our study includes extensive benchmarking of large language models (LLMs) for Arabic question answering, critically evaluating their performance in the Arabic language context. In conclusion, ArabicaQA, AraDPR, and the benchmarking of LLMs in Arabic question answering offer significant advancements in the field of Arabic NLP. The dataset and code are publicly accessible for further research https://github.com/DataScienceUIBK/ArabicaQA.

The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation. We set out to simplify this process by grounding it in an end-to-end mechanistic architecture design (MAD) pipeline, encompassing small-scale capability unit tests predictive of scaling laws. Through a suite of synthetic token manipulation tasks such as compression and recall, designed to probe capabilities, we identify and test new hybrid architectures constructed from a variety of computational primitives. We experimentally validate the resulting architectures via an extensive compute-optimal and a new state-optimal scaling law analysis, training over 500 language models between 70M to 7B parameters. Surprisingly, we find MAD synthetics to correlate with compute-optimal perplexity, enabling accurate evaluation of new architectures via isolated proxy tasks. The new architectures found via MAD, based on simple ideas such as hybridization and sparsity, outperform state-of-the-art Transformer, convolutional, and recurrent architectures (Transformer++, Hyena, Mamba) in scaling, both at compute-optimal budgets and in overtrained regimes. Overall, these results provide evidence that performance on curated synthetic tasks can be predictive of scaling laws, and that an optimal architecture should leverage specialized layers via a hybrid topology.

Many recent language model (LM) interpretability studies have adopted the circuits framework, which aims to find the minimal computational subgraph, or circuit, that explains LM behavior on a given task. Most studies determine which edges belong in a LM's circuit by performing causal interventions on each edge independently, but this scales poorly with model size. Edge attribution patching (EAP), gradient-based approximation to interventions, has emerged as a scalable but imperfect solution to this problem. In this paper, we introduce a new method - EAP with integrated gradients (EAP-IG) - that aims to better maintain a core property of circuits: faithfulness. A circuit is faithful if all model edges outside the circuit can be ablated without changing the model's performance on the task; faithfulness is what justifies studying circuits, rather than the full model. Our experiments demonstrate that circuits found using EAP are less faithful than those found using EAP-IG, even though both have high node overlap with circuits found previously using causal interventions. We conclude more generally that when using circuits to compare the mechanisms models use to solve tasks, faithfulness, not overlap, is what should be measured.