ChinaTravel: A Real-World Benchmark for Language Agents in Chinese Travel Planning

Recent advances in LLMs, particularly in language reasoning and tool integration, have rapidly sparked the real-world development of Language Agents. Among these, travel planning represents a prominent domain, combining academic challenges with practical value due to its complexity and market demand. However, existing benchmarks fail to reflect the diverse, real-world requirements crucial for deployment. To address this gap, we introduce ChinaTravel, a benchmark specifically designed for authentic Chinese travel planning scenarios. We collect the travel requirements from questionnaires and propose a compositionally generalizable domain-specific language that enables a scalable evaluation process, covering feasibility, constraint satisfaction, and preference comparison. Empirical studies reveal the potential of neuro-symbolic agents in travel planning, achieving a constraint satisfaction rate of 27.9%, significantly surpassing purely neural models at 2.6%. Moreover, we identify key challenges in real-world travel planning deployments, including open language reasoning and unseen concept composition. These findings highlight the significance of ChinaTravel as a pivotal milestone for advancing language agents in complex, real-world planning scenarios.

You Only Submit One Image to Find the Most Suitable Generative Model

Deep generative models have achieved promising results in image generation, and various generative model hubs, e.g., Hugging Face and Civitai, have been developed that enable model developers to upload models and users to download models. However, these model hubs lack advanced model management and identification mechanisms, resulting in users only searching for models through text matching, download sorting, etc., making it difficult to efficiently find the model that best meets user requirements. In this paper, we propose a novel setting called Generative Model Identification (GMI), which aims to enable the user to identify the most appropriate generative model(s) for the user's requirements from a large number of candidate models efficiently. To our best knowledge, it has not been studied yet. In this paper, we introduce a comprehensive solution consisting of three pivotal modules: a weighted Reduced Kernel Mean Embedding (RKME) framework for capturing the generated image distribution and the relationship between images and prompts, a pre-trained vision-language model aimed at addressing dimensionality challenges, and an image interrogator designed to tackle cross-modality issues. Extensive empirical results demonstrate the proposal is both efficient and effective. For example, users only need to submit a single example image to describe their requirements, and the model platform can achieve an average top-4 identification accuracy of more than 80%.

Fully Test-time Adaptation for Tabular Data

Tabular data plays a vital role in various real-world scenarios and finds extensive applications. Although recent deep tabular models have shown remarkable success, they still struggle to handle data distribution shifts, leading to performance degradation when testing distributions change. To remedy this, a robust tabular model must adapt to generalize to unknown distributions during testing. In this paper, we investigate the problem of fully test-time adaptation (FTTA) for tabular data, where the model is adapted using only the testing data. We identify three key challenges: the existence of label and covariate distribution shifts, the lack of effective data augmentation, and the sensitivity of adaptation, which render existing FTTA methods ineffective for tabular data. To this end, we propose the Fully Test-time Adaptation for Tabular data, namely FTAT, which enables FTTA methods to robustly optimize the label distribution of predictions, adapt to shifted covariate distributions, and suit a variety of tasks and models effectively. We conduct comprehensive experiments on six benchmark datasets, which are evaluated using three metrics. The experimental results demonstrate that FTAT outperforms state-of-the-art methods by a margin.

Enabling Small Models for Zero-Shot Classification through Model Label Learning

Vision-language models (VLMs) like CLIP have demonstrated impressive zero-shot ability in image classification tasks by aligning text and images but suffer inferior performance compared with task-specific expert models. On the contrary, expert models excel in their specialized domains but lack zero-shot ability for new tasks. How to obtain both the high performance of expert models and zero-shot ability is an important research direction. In this paper, we attempt to demonstrate that by constructing a model hub and aligning models with their functionalities using model labels, new tasks can be solved in a zero-shot manner by effectively selecting and reusing models in the hub. We introduce a novel paradigm, Model Label Learning (MLL), which bridges the gap between models and their functionalities through a Semantic Directed Acyclic Graph (SDAG) and leverages an algorithm, Classification Head Combination Optimization (CHCO), to select capable models for new tasks. Compared with the foundation model paradigm, it is less costly and more scalable, i.e., the zero-shot ability grows with the sizes of the model hub. Experiments on seven real-world datasets validate the effectiveness and efficiency of MLL, demonstrating that expert models can be effectively reused for zero-shot tasks. Our code will be released publicly.

Offline Imitation Learning with Model-based Reverse Augmentation

In offline Imitation Learning (IL), one of the main challenges is the \textit{covariate shift} between the expert observations and the actual distribution encountered by the agent, because it is difficult to determine what action an agent should take when outside the state distribution of the expert demonstrations. Recently, the model-free solutions introduce the supplementary data and identify the latent expert-similar samples to augment the reliable samples during learning. Model-based solutions build forward dynamic models with conservatism quantification and then generate additional trajectories in the neighborhood of expert demonstrations. However, without reward supervision, these methods are often over-conservative in the out-of-expert-support regions, because only in states close to expert-observed states can there be a preferred action enabling policy optimization. To encourage more exploration on expert-unobserved states, we propose a novel model-based framework, called offline Imitation Learning with Self-paced Reverse Augmentation (SRA). Specifically, we build a reverse dynamic model from the offline demonstrations, which can efficiently generate trajectories leading to the expert-observed states in a self-paced style. Then, we use the subsequent reinforcement learning method to learn from the augmented trajectories and transit from expert-unobserved states to expert-observed states. This framework not only explores the expert-unobserved states but also guides maximizing long-term returns on these states, ultimately enabling generalization beyond the expert data. Empirical results show that our proposal could effectively mitigate the covariate shift and achieve the state-of-the-art performance on the offline imitation learning benchmarks. Project website: \url{https://www.lamda.nju.edu.cn/shaojj/KDD24_SRA/}.

LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model

Large language models (LLMs), including both proprietary and open-source models, have showcased remarkable capabilities in addressing a wide range of downstream tasks. Nonetheless, when it comes to practical Chinese legal tasks, these models fail to meet the actual requirements. Proprietary models do not ensure data privacy for sensitive legal cases, while open-source models demonstrate unsatisfactory performance due to their lack of legal knowledge. To address this problem, we introduce LawGPT, the first open-source model specifically designed for Chinese legal applications. LawGPT comprises two key components: legal-oriented pre-training and legal supervised fine-tuning. Specifically, we employ large-scale Chinese legal documents for legal-oriented pre-training to incorporate legal domain knowledge. To further improve the model's performance on downstream legal tasks, we create a knowledge-driven instruction dataset for legal supervised fine-tuning. Our experimental results demonstrate that LawGPT outperforms the open-source LLaMA 7B model. Our code and resources are publicly available at https://github.com/pengxiao-song/LaWGPT and have received 5.7K stars on GitHub.

Robustness Assessment of Mathematical Reasoning in the Presence of Missing and Contradictory Conditions

Large language models (LLMs) have demonstrated impressive performance on reasoning tasks, which can be further improved through few-shot prompting techniques. However, the current evaluation primarily focuses on carefully constructed benchmarks and neglects the consideration of real-world reasoning problems that present missing and contradictory conditions, known as ill-defined problems. Our observations suggest that existing few-shot prompting techniques are ineffective in such scenarios, often providing overconfident answers or hallucination. To further study this problem, we develop a benchmark called Problems with Missing and Contradictory conditions (PMC) and introduce two novel metrics to evaluate the performance of few-shot prompting methods in these scenarios. Our analysis using the PMC benchmark reveals a trade-off dilemma between the performance of mathematical reasoning for well-defined problems and the ability to recognize ill-defined problems. To address the challenges posed by PMC, we propose a novel few-shot prompting method called SMT-LIB Prompting (SLP), which utilizes the SMT-LIB language to model the problems instead of solving them directly. Subsequently, a double-check solving strategy checks the satisfiability and uniqueness of the solution and provides final feedback. Extensive experiments demonstrate the superiority of our SLP approach compared to existing few-shot prompting methods when dealing with problems with missing and contradictory conditions. We will open-source our benchmark and code to facilitate future research.

DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection

Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few-shot prompt tuning methods. However, current studies evaluate the performance of learned prompts separately on base and new classes. This evaluation lacks practicality for real-world applications since downstream tasks cannot determine whether the data belongs to base or new classes in advance. In this paper, we explore a problem setting called Open-world Prompt Tuning (OPT), which involves tuning prompts on base classes and evaluating on a combination of base and new classes. By introducing Decomposed Prompt Tuning framework (DePT), we theoretically demonstrate that OPT can be solved by incorporating out-of-distribution detection into prompt tuning, thereby enhancing the base-to-new discriminability. Based on DePT, we present a novel prompt tuning approach, namely, Decomposed Context Optimization (DeCoOp), which introduces new-class detectors and sub-classifiers to further enhance the base-class and new-class discriminability. Experimental results on 11 benchmark datasets validate the effectiveness of DePT and demonstrate that DeCoOp outperforms current state-of-the-art methods, providing a significant 2% average accuracy improvement.

Investigating the Limitation of CLIP Models: The Worst-Performing Categories

Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts, enabling zero-shot recognition on downstream tasks. It is usually expected that satisfactory overall accuracy can be achieved across numerous domains through well-designed textual prompts. However, we found that their performance in the worst categories is significantly inferior to the overall performance. For example, on ImageNet, there are a total of 10 categories with class-wise accuracy as low as 0\%, even though the overall performance has achieved 64.1\%. This phenomenon reveals the potential risks associated with using CLIP models, particularly in risk-sensitive applications where specific categories hold significant importance. To address this issue, we investigate the alignment between the two modalities in the CLIP model and propose the Class-wise Matching Margin (\cmm) to measure the inference confusion. \cmm\ can effectively identify the worst-performing categories and estimate the potential performance of the candidate prompts. We further query large language models to enrich descriptions of worst-performing categories and build a weighted ensemble to highlight the efficient prompts. Experimental results clearly verify the effectiveness of our proposal, where the accuracy on the worst-10 categories on ImageNet is boosted to 5.2\%, without manual prompt engineering, laborious optimization, or access to labeled validation data.

USB: A Unified Semi-supervised Learning Benchmark

Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation protocols are often constrained to computer vision (CV) tasks. In addition, previous work typically trains deep neural networks from scratch, which is time-consuming and environmentally unfriendly. To address the above issues, we construct a Unified SSL Benchmark (USB) by selecting 15 diverse, challenging, and comprehensive tasks from CV, natural language processing (NLP), and audio processing (Audio), on which we systematically evaluate dominant SSL methods, and also open-source a modular and extensible codebase for fair evaluation on these SSL methods. We further provide pre-trained versions of the state-of-the-art neural models for CV tasks to make the cost affordable for further tuning. USB enables the evaluation of a single SSL algorithm on more tasks from multiple domains but with less cost. Specifically, on a single NVIDIA V100, only 37 GPU days are required to evaluate FixMatch on 15 tasks in USB while 335 GPU days (279 GPU days on 4 CV datasets except for ImageNet) are needed on 5 CV tasks with the typical protocol.