Deep learning technologies have demonstrated remarkable performance in vulnerability detection. Existing works primarily adopt a uniform and consistent feature learning pattern across the entire target set. While designed for general-purpose detection tasks, they lack sensitivity towards target code comprising multiple functional modules or diverse vulnerability subtypes. In this paper, we present a knowledge fusion-based vulnerability detection method (KF-GVD) that integrates specific vulnerability knowledge into the Graph Neural Network feature learning process. KF-GVD achieves accurate vulnerability detection across different functional modules of the Linux kernel and vulnerability subtypes without compromising general task performance. Extensive experiments demonstrate that KF-GVD outperforms SOTAs on function-level and statement-level vulnerability detection across various target tasks, with an average increase of 40.9% in precision and 26.1% in recall. Notably, KF-GVD discovered 9 undisclosed vulnerabilities when employing on C/C++ open-source projects without ground truth.

We investigate the extent to which contemporary Large Language Models (LLMs) can engage in exploration, a core capability in reinforcement learning and decision making. We focus on native performance of existing LLMs, without training interventions. We deploy LLMs as agents in simple multi-armed bandit environments, specifying the environment description and interaction history entirely in-context, i.e., within the LLM prompt. We experiment with GPT-3.5, GPT-4, and Llama2, using a variety of prompt designs, and find that the models do not robustly engage in exploration without substantial interventions: i) Only one configuration resulted in satisfactory exploratory behavior: GPT-4 with chain-of-thought reasoning and an externally summarized interaction history; ii) All other configurations did not result in robust exploratory behavior, including those with chain-of-thought reasoning but unsummarized history. While these findings can be interpreted positively, they suggest that external summarization--which may not be possible in more complex settings--is essential for desirable LLM behavior. We conclude that non-trivial algorithmic interventions, such as fine-tuning or dataset curation, may be required to empower LLM-based decision making agents in complex settings.

Planning is a crucial element of both human intelligence and contemporary large language models (LLMs). In this paper, we initiate a theoretical investigation into the emergence of planning capabilities in Transformer-based LLMs via their next-word prediction mechanisms. We model planning as a network path-finding task, where the objective is to generate a valid path from a specified source node to a designated target node. Our mathematical characterization shows that Transformer architectures can execute path-finding by embedding the adjacency and reachability matrices within their weights. Furthermore, our theoretical analysis of gradient-based learning dynamics reveals that LLMs can learn both the adjacency and a limited form of the reachability matrices. These theoretical insights are then validated through experiments, which demonstrate that Transformer architectures indeed learn the adjacency and an incomplete reachability matrices, consistent with our theoretical predictions. When applying our methodology to the real-world planning benchmark Blocksworld, our observations remain consistent. Additionally, our analyses uncover a fundamental limitation of current Transformer architectures in path-finding: these architectures cannot identify reachability relationships through transitivity, which leads to failures in generating paths when concatenation is required. These findings provide new insights into how the internal mechanisms of autoregressive learning facilitate intelligent planning and deepen our understanding of how future LLMs might achieve more advanced and general planning-and-reasoning capabilities across diverse applications.

Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks. Existing methods work by emulating the human preference at the single decision (turn) level, limiting their capabilities in settings that require planning or multi-turn interactions to achieve a long-term goal. In this paper, we address this issue by developing novel methods for Reinforcement Learning (RL) from preference feedback between two full multi-turn conversations. In the tabular setting, we present a novel mirror-descent-based policy optimization algorithm for the general multi-turn preference-based RL problem, and prove its convergence to Nash equilibrium. To evaluate performance, we create a new environment, Education Dialogue, where a teacher agent guides a student in learning a random topic, and show that a deep RL variant of our algorithm outperforms RLHF baselines. Finally, we show that in an environment with explicit rewards, our algorithm recovers the same performance as a reward-based RL baseline, despite relying solely on a weaker preference signal.

Public LLMs such as the Llama 2-Chat underwent alignment training and were considered safe. Recently Qi et al. (2024) reported that even benign fine-tuning on seemingly safe datasets can give rise to unsafe behaviors in the models. The current paper is about methods and best practices to mitigate such loss of alignment. We focus on the setting where a public model is fine-tuned before serving users for specific usage, where the model should improve on the downstream task while maintaining alignment. Through extensive experiments on several chat models (Meta's Llama 2-Chat, Mistral AI's Mistral 7B Instruct v0.2, and OpenAI's GPT-3.5 Turbo), this paper uncovers that the prompt templates used during fine-tuning and inference play a crucial role in preserving safety alignment, and proposes the "Pure Tuning, Safe Testing" (PTST) strategy --- fine-tune models without a safety prompt, but include it at test time. This seemingly counterintuitive strategy incorporates an intended distribution shift to encourage alignment preservation. Fine-tuning experiments on GSM8K, ChatDoctor, and OpenOrca show that PTST significantly reduces the rise of unsafe behaviors.

Large language models based on decoder-only transformers have demonstrated superior text understanding capabilities compared to CLIP and T5-series models.However, the paradigm for utilizing current advanced LLMs in text-to-image diffusion models remains to be explored.We observed an unusual phenomenon: directly using a large language model as the prompt encoder significantly degrades the prompt-following ability in image generation.We identified two main obstacles behind this issue.One is the misalignment between the next token prediction training in LLM and the requirement for discriminative prompt features in diffusion models.The other is the intrinsic positional bias introduced by the decoder-only architecture.To deal with this issue, we propose a novel framework to fully harness the capabilities of LLMs.Through the carefully designed usage guidance, we effectively enhance the text representation capability of the LLM for prompt encoding and eliminate its inherent positional bias.This allows us to flexibly integrate state-of-the-art LLMs into the text-to-image generation model.Furthermore, we also provide an effective manner to fuse multiple LLMs into our framework.Considering the excellent performance and scaling capabilities demonstrated by the transformer architecture, we further design an LLM-Infused Diffusion Transformer (LI-DIT)based on the framework.We conduct extensive experiments to validate LI-DIT across model size and data size.Benefiting from the inherent ability of the LLMs and our innovative designs, the prompt understanding performance of LI-DIT easily surpasses state-of-the-art open-source models as well as mainstream closed-source commercial models including Stable Diffusion 3, DALL-E 3, and Midjourney V6.

Deep learning has achieved tremendous success. However, unlike SVMs, which provide direct decision criteria and can be trained with a small dataset, it still has significant weaknesses due to its requirement for massive datasets during training and the black-box characteristics on decision criteria.

Deep neural networks, including Convolutional Neural Networks (CNNs) and Visual Transformers (ViT), have achieved stunning success in the medical image domain. We study thorax disease classification in this paper. Effective extraction of features for the disease areas is crucial for disease classification on radiographic images. While various neural architectures and training techniques, such as self-supervised learning with contrastive/restorative learning, have been employed for disease classification on radiographic images, there are no principled methods that can effectively reduce the adverse effect of noise and background or non-disease areas on the radiographic images for disease classification. To address this challenge, we propose a novel Low-Rank Feature Learning (LRFL) method in this paper, which is universally applicable to the training of all neural networks. The LRFL method is both empirically motivated by a Low Frequency Property (LFP) and theoretically motivated by our sharp generalization bound for neural networks with low-rank features. LFP not only widely exists in deep neural networks for generic machine learning but also exists in all the thorax medical datasets studied in this paper. In the empirical study, using a neural network such as a ViT or a CNN pre-trained on unlabeled chest X-rays by Masked Autoencoders (MAE), our novel LRFL method is applied on the pre-trained neural network and demonstrates better classification results in terms of both multi-class area under the receiver operating curve (mAUC) and classification accuracy than the current state-of-the-art.

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning.Nevertheless, it is unclear how improved representation learning can benefit reinforcement learning from human feedback on language models.In this work, we propose training reward models (RMs) in a contrastive, $\textit{goal-conditioned}$ fashion by increasing the representation similarity of future states along sampled preferred trajectories and decreasing the similarity along randomly sampled dispreferred trajectories.This objective significantly improves reward model performance by up to 0.09 AUROC across challenging benchmarks, such as MATH and GSM8k. These findings extend to general alignment as well -- on the Helpful-Harmless dataset, we observe 2.3\% increase in accuracy.Beyond improving reward model performance, we show this way of training RM representations enables improved steerability because it allows us to evaluate the likelihood of an action achieving a particular goal-state (e.g.

Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks. In this work we develop an iterative approach that optimizes the preference between competing generated Chain-of-Thought (CoT) candidates by optimizing for winning vs. losing reasoning steps. We train using a modified DPO loss with an additional negative log-likelihood term, which we find to be crucial. We show reasoning improves across repeated iterations of this scheme. While only relying on examples in the training set, our approach results in increasing accuracy on GSM8K, MATH, and ARC-Challenge for Llama-2-70B-Chat, outperforming other Llama-2-based models not relying on additionally sourced datasets. For example, we see a large improvement from 55.6% to 81.6% on GSM8K and an accuracy of 88.7% with majority voting out of 32 samples.