WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback

As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on human or LLM annotated datasets, are limited by their resource-intensive nature, inherent subjectivity, and the risk of feedback loops that amplify model biases. To overcome these limitations, we introduce WildFeedback, a novel framework that leverages real-time, in-situ user interactions to create preference datasets that more accurately reflect authentic human values. WildFeedback operates through a three-step process: feedback signal identification, preference data construction, and user-guided evaluation. We applied this framework to a large corpus of user-LLM conversations, resulting in a rich preference dataset that reflects genuine user preferences. This dataset captures the nuances of user preferences by identifying and classifying feedback signals within natural conversations, thereby enabling the construction of more representative and context-sensitive alignment data. Our extensive experiments demonstrate that LLMs fine-tuned on WildFeedback exhibit significantly improved alignment with user preferences, as evidenced by both traditional benchmarks and our proposed user-guided evaluation. By incorporating real-time feedback from actual users, WildFeedback addresses the scalability, subjectivity, and bias challenges that plague existing approaches, marking a significant step toward developing LLMs that are more responsive to the diverse and evolving needs of their users. In summary, WildFeedback offers a robust, scalable solution for aligning LLMs with true human values, setting a new standard for the development and evaluation of user-centric language models.

Interpretable User Satisfaction Estimation for Conversational Systems with Large Language Models

Accurate and interpretable user satisfaction estimation (USE) is critical for understanding, evaluating, and continuously improving conversational systems. Users express their satisfaction or dissatisfaction with diverse conversational patterns in both general-purpose (ChatGPT and Bing Copilot) and task-oriented (customer service chatbot) conversational systems. Existing approaches based on featurized ML models or text embeddings fall short in extracting generalizable patterns and are hard to interpret. In this work, we show that LLMs can extract interpretable signals of user satisfaction from their natural language utterances more effectively than embedding-based approaches. Moreover, an LLM can be tailored for USE via an iterative prompting framework using supervision from labeled examples. The resulting method, Supervised Prompting for User satisfaction Rubrics (SPUR), not only has higher accuracy but is more interpretable as it scores user satisfaction via learned rubrics with a detailed breakdown.

Improving Generalization via Attribute Selection on Out-of-the-box Data

Zero-shot learning (ZSL) aims to recognize unseen objects (test classes) given some other seen objects (training classes), by sharing information of attributes between different objects. Attributes are artificially annotated for objects and are treated equally in recent ZSL tasks. However, some inferior attributes with poor predictability or poor discriminability may have negative impact on the ZSL system performance. This paper first derives a generalization error bound for ZSL tasks. Our theoretical analysis verifies that selecting key attributes set can improve the generalization performance of the original ZSL model which uses all the attributes. Unfortunately, previous attribute selection methods are conducted based on the seen data, their selected attributes have poor generalization capability to the unseen data, which is unavailable in training stage for ZSL tasks. Inspired by learning from pseudo relevance feedback, this paper introduces the out-of-the-box data, which is pseudo data generated by an attribute-guided generative model, to mimic the unseen data. After that, we present an iterative attribute selection (IAS) strategy which iteratively selects key attributes based on the out-of-the-box data. Since the distribution of the generated out-of-the-box data is similar to the test data, the key attributes selected by IAS can be effectively generalized to test data. Extensive experiments demonstrate that IAS can significantly improve existing attribute-based ZSL methods and achieve state-of-the-art performance.

Learning Image-Specific Attributes by Hyperbolic Neighborhood Graph Propagation

As a kind of semantic representation of visual object descriptions, attributes are widely used in various computer vision tasks. In most of existing attribute-based research, class-specific attributes (CSA), which are class-level annotations, are usually adopted due to its low annotation cost for each class instead of each individual image. However, class-specific attributes are usually noisy because of annotation errors and diversity of individual images. Therefore, it is desirable to obtain image-specific attributes (ISA), which are image-level annotations, from the original class-specific attributes. In this paper, we propose to learn image-specific attributes by graph-based attribute propagation. Considering the intrinsic property of hyperbolic geometry that its distance expands exponentially, hyperbolic neighborhood graph (HNG) is constructed to characterize the relationship between samples. Based on HNG, we define neighborhood consistency for each sample to identify inconsistent samples. Subsequently, inconsistent samples are refined based on their neighbors in HNG. Extensive experiments on five benchmark datasets demonstrate the significant superiority of the learned image-specific attributes over the original class-specific attributes in the zero-shot object classification task.

Target-Independent Active Learning via Distribution-Splitting

To reduce the label complexity in Agnostic Active Learning (A^2 algorithm), volume-splitting splits the hypothesis edges to reduce the Vapnik-Chervonenkis (VC) dimension in version space. However, the effectiveness of volume-splitting critically depends on the initial hypothesis and this problem is also known as target-dependent label complexity gap. This paper attempts to minimize this gap by introducing a novel notion of number density which provides a more natural and direct way to describe the hypothesis distribution than volume. By discovering the connections between hypothesis and input distribution, we map the volume of version space into the number density and propose a target-independent distribution-splitting strategy with the following advantages: 1) provide theoretical guarantees on reducing label complexity and error rate as volume-splitting; 2) break the curse of initial hypothesis; 3) provide model guidance for a target-independent AL algorithm in real AL tasks. With these guarantees, for AL application, we then split the input distribution into more near-optimal spheres and develop an application algorithm called Distribution-based A^2 (DA^2). Experiments further verify the effectiveness of the halving and querying abilities of DA^2. Contributions of this paper are as follows.

Zero-shot Learning with Complementary Attributes

Zero-shot learning (ZSL) aims to recognize unseen objects using disjoint seen objects via attributes to transfer semantic information from training data to testing data. The generalization performance of ZSL is governed by the attributes, which represent the relatedness between the seen classes and the unseen classes. In this paper, we propose a novel ZSL method using complementary attributes as a supplement to the original attributes. We first expand attributes with their complementary form, and then pre-train classifiers for both original attributes and complementary attributes using training data. After ranking classes for each attribute, we use rank aggregation framework to calculate the optimized rank among testing classes of which the highest order is assigned as the label of testing sample. We empirically demonstrate that complementary attributes have an effective improvement for ZSL models. Experimental results show that our approach outperforms state-of-the-art methods on standard ZSL datasets.