In practice, preference learning from human feedback depends on incomplete data with hidden context. Hidden context refers to data that affects the feedback received, but which is not represented in the data used to train a preference model. This captures common issues of data collection, such as having human annotators with varied preferences, cognitive processes that result in seemingly irrational behavior, and combining data labeled according to different criteria. We prove that standard applications of preference learning, including reinforcement learning from human feedback (RLHF), implicitly aggregate over hidden contexts according to a well-known voting rule called Borda count. We show this can produce counter-intuitive results that are very different from other methods which implicitly aggregate via expected utility. Furthermore, our analysis formalizes the way that preference learning from users with diverse values tacitly implements a social choice function. A key implication of this result is that annotators have an incentive to misreport their preferences in order to influence the learned model, leading to vulnerabilities in the deployment of RLHF. As a step towards mitigating these problems, we introduce a class of methods called distributional preference learning (DPL). DPL methods estimate a distribution of possible score values for each alternative in order to better account for hidden context. Experimental results indicate that applying DPL to RLHF for LLM chatbots identifies hidden context in the data and significantly reduces subsequent jailbreak vulnerability. Our code and data are available at //github.com/cassidylaidlaw/hidden-context
相關內容
We examine machine learning models in a setup where individuals have the choice to share optional personal information with a decision-making system, as seen in modern insurance pricing models. Some users consent to their data being used whereas others object and keep their data undisclosed. In this work, we show that the decision not to share data can be considered as information in itself that should be protected to respect users' privacy. This observation raises the overlooked problem of how to ensure that users who protect their personal data do not suffer any disadvantages as a result. To address this problem, we formalize protection requirements for models which only use the information for which active user consent was obtained. This excludes implicit information contained in the decision to share data or not. We offer the first solution to this problem by proposing the notion of Protected User Consent (PUC), which we prove to be loss-optimal under our protection requirement. We observe that privacy and performance are not fundamentally at odds with each other and that it is possible for a decision maker to benefit from additional data while respecting users' consent. To learn PUC-compliant models, we devise a model-agnostic data augmentation strategy with finite sample convergence guarantees. Finally, we analyze the implications of PUC on challenging real datasets, tasks, and models.
The advancement of large language models (LLMs) has significantly propelled the field of code generation. Previous work integrated reinforcement learning (RL) with compiler feedback for exploring the output space of LLMs to enhance code generation quality. However, the lengthy code generated by LLMs in response to complex human requirements makes RL exploration a challenge. Also, since the unit tests may not cover the complicated code, optimizing LLMs by using these unexecuted code snippets is ineffective. To tackle these challenges, we introduce StepCoder, a novel RL framework for code generation, consisting of two main components: CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks, while FGO only optimizes the model by masking the unexecuted code segments to provide Fine-Grained Optimization. In addition, we furthermore construct the APPS+ dataset for RL training, which is manually verified to ensure the correctness of unit tests. Experimental results show that our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
We introduce RACH-Space, an algorithm for labelling unlabelled data in weakly supervised learning, given incomplete, noisy information about the labels. RACH-Space offers simplicity in implementation without requiring hard assumptions on data or the sources of weak supervision, and is well suited for practical applications where fully labelled data is not available. Our method is built upon a geometrical interpretation of the space spanned by the set of weak signals. We also analyze the theoretical properties underlying the relationship between the convex hulls in this space and the accuracy of our output labels, bridging geometry with machine learning. Empirical results demonstrate that RACH-Space works well in practice and compares favorably to the best existing label models for weakly supervised learning.
Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a guidance method that provides first-principle non-linear correction for classifier-free guidance. Such correction forces the guided DDPMs to respect the Fokker-Planck (FP) equation of diffusion process, in a way that is training-free and compatible with existing sampling methods. Experiments show that characteristic guidance enhances semantic characteristics of prompts and mitigate irregularities in image generation, proving effective in diverse applications ranging from simulating magnet phase transitions to latent space sampling.
In practice, it is observed that transformer-based models can learn concepts in context in the inference stage. While existing literature, e.g., \citet{zhang2023trained,huang2023context}, provide theoretical explanations on this in-context learning ability, they assume the input $x_i$ and the output $y_i$ for each sample are embedded in the same token (i.e., structured data). However, in reality, they are presented in two tokens (i.e., unstructured data \cite{wibisono2023role}). In this case, this paper conducts experiments in linear regression tasks to study the benefits of the architecture of transformers and provides some corresponding theoretical intuitions to explain why the transformer can learn from unstructured data. We study the exact components in a transformer that facilitate the in-context learning. In particular, we observe that (1) a transformer with two layers of softmax (self-)attentions with look-ahead attention mask can learn from the prompt if $y_i$ is in the token next to $x_i$ for each example; (2) positional encoding can further improve the performance; and (3) multi-head attention with a high input embedding dimension has a better prediction performance than single-head attention.
Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length. To address this, we present LongAlign -- a recipe of the instruction data, training, and evaluation for long context alignment. First, we construct a long instruction-following dataset using Self-Instruct. To ensure the data diversity, it covers a broad range of tasks from various long context sources. Second, we adopt the packing and sorted batching strategies to speed up supervised fine-tuning on data with varied length distributions. Additionally, we develop a loss weighting method to balance the contribution to the loss across different sequences during packing training. Third, we introduce the LongBench-Chat benchmark for evaluating instruction-following capabilities on queries of 10k-100k in length. Experiments show that LongAlign outperforms existing recipes for LLMs in long context tasks by up to 30\%, while also maintaining their proficiency in handling short, generic tasks. The code, data, and long-aligned models are open-sourced at //github.com/THUDM/LongAlign.
In the realm of robot-assisted minimally invasive surgery, dynamic scene reconstruction can significantly enhance downstream tasks and improve surgical outcomes. Neural Radiance Fields (NeRF)-based methods have recently risen to prominence for their exceptional ability to reconstruct scenes. Nonetheless, these methods are hampered by slow inference, prolonged training, and substantial computational demands. Additionally, some rely on stereo depth estimation, which is often infeasible due to the high costs and logistical challenges associated with stereo cameras. Moreover, the monocular reconstruction quality for deformable scenes is currently inadequate. To overcome these obstacles, we present Endo-4DGS, an innovative, real-time endoscopic dynamic reconstruction approach that utilizes 4D Gaussian Splatting (GS) and requires no ground truth depth data. This method extends 3D GS by incorporating a temporal component and leverages a lightweight MLP to capture temporal Gaussian deformations. This effectively facilitates the reconstruction of dynamic surgical scenes with variable conditions. We also integrate Depth-Anything to generate pseudo-depth maps from monocular views, enhancing the depth-guided reconstruction process. Our approach has been validated on two surgical datasets, where it can effectively render in real-time, compute efficiently, and reconstruct with remarkable accuracy. These results underline the vast potential of Endo-4DGS to improve surgical assistance.
Existing recommender systems extract the user preference based on learning the correlation in data, such as behavioral correlation in collaborative filtering, feature-feature, or feature-behavior correlation in click-through rate prediction. However, regretfully, the real world is driven by causality rather than correlation, and correlation does not imply causation. For example, the recommender systems can recommend a battery charger to a user after buying a phone, in which the latter can serve as the cause of the former, and such a causal relation cannot be reversed. Recently, to address it, researchers in recommender systems have begun to utilize causal inference to extract causality, enhancing the recommender system. In this survey, we comprehensively review the literature on causal inference-based recommendation. At first, we present the fundamental concepts of both recommendation and causal inference as the basis of later content. We raise the typical issues that the non-causality recommendation is faced. Afterward, we comprehensively review the existing work of causal inference-based recommendation, based on a taxonomy of what kind of problem causal inference addresses. Last, we discuss the open problems in this important research area, along with interesting future works.
Autonomic computing investigates how systems can achieve (user) specified control outcomes on their own, without the intervention of a human operator. Autonomic computing fundamentals have been substantially influenced by those of control theory for closed and open-loop systems. In practice, complex systems may exhibit a number of concurrent and inter-dependent control loops. Despite research into autonomic models for managing computer resources, ranging from individual resources (e.g., web servers) to a resource ensemble (e.g., multiple resources within a data center), research into integrating Artificial Intelligence (AI) and Machine Learning (ML) to improve resource autonomy and performance at scale continues to be a fundamental challenge. The integration of AI/ML to achieve such autonomic and self-management of systems can be achieved at different levels of granularity, from full to human-in-the-loop automation. In this article, leading academics, researchers, practitioners, engineers, and scientists in the fields of cloud computing, AI/ML, and quantum computing join to discuss current research and potential future directions for these fields. Further, we discuss challenges and opportunities for leveraging AI and ML in next generation computing for emerging computing paradigms, including cloud, fog, edge, serverless and quantum computing environments.
We introduce a multi-task setup of identifying and classifying entities, relations, and coreference clusters in scientific articles. We create SciERC, a dataset that includes annotations for all three tasks and develop a unified framework called Scientific Information Extractor (SciIE) for with shared span representations. The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links. Experiments show that our multi-task model outperforms previous models in scientific information extraction without using any domain-specific features. We further show that the framework supports construction of a scientific knowledge graph, which we use to analyze information in scientific literature.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191