Safety aligned Large Language Models (LLMs) are vulnerable to harmful fine-tuning attacks \cite{qi2023fine}-- a few harmful data mixed in the fine-tuning dataset can break the LLMs's safety alignment. Existing mitigation strategies include alignment stage solutions \cite{huang2024vaccine, rosati2024representation} and fine-tuning stage solutions \cite{huang2024lazy,mukhoti2023fine}. However, our evaluation shows that both categories of defenses fail \textit{when some specific training hyper-parameters are chosen} -- a large learning rate or a large number of training epochs in the fine-tuning stage can easily invalidate the defense, which however, is necessary to guarantee finetune performance. To this end, we propose Antidote, a post-fine-tuning stage solution, which remains \textbf{\textit{agnostic to the training hyper-parameters in the fine-tuning stage}}. Antidote relies on the philosophy that by removing the harmful parameters, the harmful model can be recovered from the harmful behaviors, regardless of how those harmful parameters are formed in the fine-tuning stage. With this philosophy, we introduce a one-shot pruning stage after harmful fine-tuning to remove the harmful weights that are responsible for the generation of harmful content. Despite its embarrassing simplicity, empirical results show that Antidote can reduce harmful score while maintaining accuracy on downstream tasks.Our project page is at \url{https://huangtiansheng.github.io/Antidote_gh_page/}

As large language models (LLMs) gain traction in healthcare, concerns about their susceptibility to demographic biases are growing. We introduce {DiversityMedQA}, a novel benchmark designed to assess LLM responses to medical queries across diverse patient demographics, such as gender and ethnicity. By perturbing questions from the MedQA dataset, which comprises medical board exam questions, we created a benchmark that captures the nuanced differences in medical diagnosis across varying patient profiles. Our findings reveal notable discrepancies in model performance when tested against these demographic variations. Furthermore, to ensure the perturbations were accurate, we also propose a filtering strategy that validates each perturbation. By releasing DiversityMedQA, we provide a resource for evaluating and mitigating demographic bias in LLM medical diagnoses.

Werewolf is an incomplete information game, which has several challenges when creating a computer agent as a player given the lack of understanding of the situation and individuality of utterance (e.g., computer agents are not capable of characterful utterance or situational lying). We propose a werewolf agent that solves some of those difficulties by combining a Large Language Model (LLM) and a rule-based algorithm. In particular, our agent uses a rule-based algorithm to select an output either from an LLM or a template prepared beforehand based on the results of analyzing conversation history using an LLM. It allows the agent to refute in specific situations, identify when to end the conversation, and behave with persona. This approach mitigated conversational inconsistencies and facilitated logical utterance as a result. We also conducted a qualitative evaluation, which resulted in our agent being perceived as more human-like compared to an unmodified LLM. The agent is freely available for contributing to advance the research in the field of Werewolf game.

Recent studies have demonstrated the significant potential of Large Language Models (LLMs) in generating Register Transfer Level (RTL) code, with notable advancements showcased by commercial models such as GPT-4 and Claude3-Opus. However, these proprietary LLMs often raise concerns regarding privacy and security. While open-source LLMs offer solutions to these concerns, they typically underperform commercial models in RTL code generation tasks, primarily due to the scarcity of high-quality open-source RTL datasets. To address this challenge, we introduce OriGen , a fully open-source framework that incorporates self-reflection capabilities and a novel dataset augmentation methodology for generating high-quality, large-scale RTL code. Our approach employs a code-tocode augmentation technique to enhance the quality of open-source RTL code datasets. Furthermore, OriGen can rectify syntactic errors through a self-reflection process that leverages compiler feedback. Experimental results demonstrate that OriGen significantly outperforms other open-source alternatives in RTL code generation. It surpasses the previous best-performing open-source LLM by 12.8% and even exceeds GPT-4 Turbo in the pass@1 metric on the VerilogEval-Human benchmark. Moreover, OriGen exhibits superior capabilities in self-reflection and error correction, outperforming GPT-4 by 19.9% on a benchmark designed to evaluate self-reflection capabilities.

In the realm of NLP, BERT [2], extraction involves using a model to accurately identify GPT [3], and T5 [4] are some of the notable works that and classify the keyphrases in the document. The generation have consistently updated benchmark records in Pretrained of keyphrases is another task in which the model Language Model Keyphrase Extraction (PLM-predicts both present and absent keyphrases within the KPE) and Pre-trained Language Model Keyphrase Generation context of the document, introduced in [1]. The application (PLM-KPG) tasks [5], contributing significantly of deep learning technologies has witnessed to the development of NLP. a noticeable rise in using pre-trained language models The process of extracting keyphrases from a document (PLMs) in NLP in recent years. PLMs are trained using involves identifying and extracting significant different strategies on extensive text corpora and have phrases that represent the main topics or concepts discussed shown exceptional performance in various downstream within it. The primary objective is to extract the tasks, including Keyphrase Predation. PLMs using most essential and representative phrases using featurebased self-supervised learning differ from traditional learning [6, 7, 8, 9, 10] and linguistic techniques [11] methods, such as supervised learning, because they are like frequency analysis [12], part-of-speech tagging first trained on a large volume of unlabeled data before [13, 14], and syntactic parsing [15]. These methods fine-tuning small quantities of labeled data for specific can identify keyphrases based on their frequency, relevance, tasks.

Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these challenges by reducing the number of activated neurons during inference. Existing methods typically employ thresholding-based sparsification based on the statistics of activation tensors. However, these methods do not explicitly model the impact of activation sparsification on performance, leading to suboptimal performance degradation. To address this issue, this paper reformulates the activation sparsification problem by introducing a new objective that optimizes the sparsification decisions. Building on this reformulation, we propose CHESS, a general activation sparsification approach via CHannel-wise thrEsholding and Selective Sparsification. First, channel-wise thresholding assigns a unique threshold to each activation channel in the feed-forward network (FFN) layers. Then, selective sparsification involves applying thresholding-based activation sparsification to specific layers within the attention modules. Finally, we detail the implementation of sparse kernels to accelerate LLM inference. Experimental results demonstrate that the proposed CHESS achieves lower performance degradation over 8 downstream tasks while activating fewer parameters compared to existing methods, thus speeding up the LLM inference by up to 1.27x.

Multimodal language modeling constitutes a recent breakthrough which leverages advances in large language models to pretrain capable multimodal models. The integration of natural language during pretraining has been shown to significantly improve learned representations, particularly in computer vision. However, the efficacy of multimodal language modeling in the realm of functional brain data, specifically for advancing pathology detection, remains unexplored. This study pioneers EEG-language models trained on clinical reports and 15000 EEGs. We extend methods for multimodal alignment to this novel domain and investigate which textual information in reports is useful for training EEG-language models. Our results indicate that models learn richer representations from being exposed to a variety of report segments, including the patient's clinical history, description of the EEG, and the physician's interpretation. Compared to models exposed to narrower clinical text information, we find such models to retrieve EEGs based on clinical reports (and vice versa) with substantially higher accuracy. Yet, this is only observed when using a contrastive learning approach. Particularly in regimes with few annotations, we observe that representations of EEG-language models can significantly improve pathology detection compared to those of EEG-only models, as demonstrated by both zero-shot classification and linear probes. In sum, these results highlight the potential of integrating brain activity data with clinical text, suggesting that EEG-language models represent significant progress for clinical applications.

Categorization, a core cognitive ability in humans that organizes objects based on common features, is essential to cognitive science as well as computer vision. To evaluate the categorization ability of visual AI models, various proxy tasks on recognition from datasets to open world scenarios have been proposed. Recent development of Large Multimodal Models (LMMs) has demonstrated impressive results in high-level visual tasks, such as visual question answering, video temporal reasoning, etc., utilizing the advanced architectures and large-scale multimodal instruction tuning. Previous researchers have developed holistic benchmarks to measure the high-level visual capability of LMMs, but there is still a lack of pure and in-depth quantitative evaluation of the most fundamental categorization ability. According to the research on human cognitive process, categorization can be seen as including two parts: category learning and category use. Inspired by this, we propose a novel, challenging, and efficient benchmark based on composite blocks, called ComBo, which provides a disentangled evaluation framework and covers the entire categorization process from learning to use. By analyzing the results of multiple evaluation tasks, we find that although LMMs exhibit acceptable generalization ability in learning new categories, there are still gaps compared to humans in many ways, such as fine-grained perception of spatial relationship and abstract category understanding. Through the study of categorization, we can provide inspiration for the further development of LMMs in terms of interpretability and generalization.

The effectiveness of long-context modeling is important for Large Language Models (LLMs) in various applications. Despite their potential, LLMs' efficacy in processing long context does not consistently meet expectations, posing significant challenges for efficient management of prolonged sequences in training. This difficulty is compounded by the scarcity of comprehensive and diverse training datasets suitable for long sequences, which stems from inherent length biases across different data sources, and the logistical complexities associated with massive data management for training in extended contexts. In this work, we introduce DataSculpt, a data construction framework designed to strategically augment the data architecture for extended-context training. Our thorough evaluations demonstrate DataSculpt's remarkable capacity to boost long-context training performance, achieving improvements including an 18.09% increase in retrieval augmentation, 21.23% in summarization, 21.27% in reading comprehension, and a 3.81% rise in code completion, all while preserving the models' overall proficiency with a 4.88% improvement.

Graph Contrastive Learning (GCL) is a potent paradigm for self-supervised graph learning that has attracted attention across various application scenarios. However, GCL for learning on Text-Attributed Graphs (TAGs) has yet to be explored. Because conventional augmentation techniques like feature embedding masking cannot directly process textual attributes on TAGs. A naive strategy for applying GCL to TAGs is to encode the textual attributes into feature embeddings via a language model and then feed the embeddings into the following GCL module for processing. Such a strategy faces three key challenges: I) failure to avoid information loss, II) semantic loss during the text encoding phase, and III) implicit augmentation constraints that lead to uncontrollable and incomprehensible results. In this paper, we propose a novel GCL framework named LATEX-GCL to utilize Large Language Models (LLMs) to produce textual augmentations and LLMs' powerful natural language processing (NLP) abilities to address the three limitations aforementioned to pave the way for applying GCL to TAG tasks. Extensive experiments on four high-quality TAG datasets illustrate the superiority of the proposed LATEX-GCL method. The source codes and datasets are released to ease the reproducibility, which can be accessed via this link: https://anonymous.4open.science/r/LATEX-GCL-0712.