Entropy-Based Decoding for Retrieval-Augmented Large Language Models

Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue, where the generated responses are negatively influenced by noise from both external and internal knowledge sources. In this paper, we introduce a novel, training-free decoding method guided by entropy considerations to mitigate this issue. Our approach utilizes entropy-based document-parallel ensemble decoding to prioritize low-entropy distributions from retrieved documents, thereby enhancing the extraction of relevant information of context. Additionally, it incorporates a contrastive decoding mechanism that contrasts the obtained low-entropy ensemble distribution with the high-entropy distribution derived from the model's internal knowledge across layers, which ensures a greater emphasis on reliable external information. Extensive experiments on open-domain question answering datasets demonstrate the superiority of our method.

Generative Artificial Intelligence-Guided User Studies: An Application for Air Taxi Services

User studies are crucial for meeting user needs. In user studies, real experimental scenarios and participants are constructed and recruited. However, emerging and unfamiliar studies face limitations, including safety concerns and iterative efficiency. To address these challenges, this study utilizes a large language model (LLM) to create generative AI virtual scenarios for user experience. By recruiting real users to evaluate this experience, we can collect feedback that enables rapid iteration in the early design phase. The air taxi is particularly representative of these challenges and has been chosen as the case study for this research. The key contribution was designing a virtual ATJ using OpenAI's GPT-4 model and AI image and video generators. Based on the LLM-generated scripts, key visuals were created for the air taxi, and the ATJ was evaluated by 72 participants. Furthermore, the LLM demonstrated the ability to identify and suggest environments that significantly improve participants' attitudes toward air taxis. Education level and gender significantly influenced participants' attitudes and their satisfaction with the ATJ. Our study confirms the capability of generative AI to support user studies, providing a feasible approach and valuable insights for designing air taxi user experiences in the early design phase.

Enhancing Biomedical Knowledge Retrieval-Augmented Generation with Self-Rewarding Tree Search and Proximal Policy Optimization

Large Language Models (LLMs) have shown great potential in the biomedical domain with the advancement of retrieval-augmented generation (RAG). However, existing retrieval-augmented approaches face challenges in addressing diverse queries and documents, particularly for medical knowledge queries, resulting in sub-optimal performance. To address these limitations, we propose a novel plug-and-play LLM-based retrieval method called Self-Rewarding Tree Search (SeRTS) based on Monte Carlo Tree Search (MCTS) and a self-rewarding paradigm. By combining the reasoning capabilities of LLMs with the effectiveness of tree search, SeRTS boosts the zero-shot performance of retrieving high-quality and informative results for RAG. We further enhance retrieval performance by fine-tuning LLMs with Proximal Policy Optimization (PPO) objectives using the trajectories collected by SeRTS as feedback. Controlled experiments using the BioASQ-QA dataset with GPT-3.5-Turbo and LLama2-7b demonstrate that our method significantly improves the performance of the BM25 retriever and surpasses the strong baseline of self-reflection in both efficiency and scalability. Moreover, SeRTS generates higher-quality feedback for PPO training than self-reflection. Our proposed method effectively adapts LLMs to document retrieval tasks, enhancing their ability to retrieve highly relevant documents for RAG in the context of medical knowledge queries. This work presents a significant step forward in leveraging LLMs for accurate and comprehensive biomedical question answering.

How Well Can LLMs Echo Us? Evaluating AI Chatbots' Role-Play Ability with ECHO

The role-play ability of Large Language Models (LLMs) has emerged as a popular research direction. However, existing studies focus on imitating well-known public figures or fictional characters, overlooking the potential for simulating ordinary individuals. Such an oversight limits the potential for advancements in digital human clones and non-player characters in video games. To bridge this gap, we introduce ECHO, an evaluative framework inspired by the Turing test. This framework engages the acquaintances of the target individuals to distinguish between human and machine-generated responses. Notably, our framework focuses on emulating average individuals rather than historical or fictional figures, presenting a unique advantage to apply the Turing Test. We evaluated three role-playing LLMs using ECHO, with GPT-3.5 and GPT-4 serving as foundational models, alongside the online application GPTs from OpenAI. Our results demonstrate that GPT-4 more effectively deceives human evaluators, and GPTs achieves a leading success rate of 48.3%. Furthermore, we investigated whether LLMs could discern between human-generated and machine-generated texts. While GPT-4 can identify differences, it could not determine which texts were human-produced. Our code and results of reproducing the role-playing LLMs are made publicly available via https://github.com/CUHK-ARISE/ECHO.

An Entropy-based Text Watermarking Detection Method

Currently, text watermarking algorithms for large language models (LLMs) can embed hidden features to texts generated by LLMs to facilitate subsequent detection, thus alleviating the problem of misuse of LLMs. Although the current text watermarking algorithms perform well in most high-entropy scenarios, its performance in low-entropy scenarios still needs to be improved. In this work, we proposed that the influence of token entropy should be fully considered in the watermark detection process, that is, the weight of each token should be adjusted according to its entropy during watermark detection, rather than setting the weight of all tokens to the same value as in previous methods. Specifically, we proposed an Entropy-based Watermark Detection (EWD) that gives higher-entropy tokens higher weights during watermark detection, so as to better reflect the degree of watermarking. Furthermore, the proposed detection process is training-free and fully automated. %In actual detection, we use a proxy-LLM to calculate the entropy of each token, without the need to use the original LLM. In the experiment, we found that our method can achieve better detection performance in low-entropy scenarios, and our method is also general and can be applied to texts with different entropy distributions. Our code and data will be available online.

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation

Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet, most transfer approaches for VLMs focus on either the language or visual branches, overlooking the nuanced interplay between both modalities. In this work, we introduce a Unified Modality Separation (UniMoS) framework for unsupervised domain adaptation. Leveraging insights from modality gap studies, we craft a nimble modality separation network that distinctly disentangles CLIP's features into language-associated and vision-associated components. Our proposed Modality-Ensemble Training (MET) method fosters the exchange of modality-agnostic information while maintaining modality-specific nuances. We align features across domains using a modality discriminator. Comprehensive evaluations on three benchmarks reveal our approach sets a new state-of-the-art with minimal computational costs. Code: https://github.com/TL-UESTC/UniMoS

Agile Multi-Source-Free Domain Adaptation

Efficiently utilizing rich knowledge in pretrained models has become a critical topic in the era of large models. This work focuses on adaptively utilizing knowledge from multiple source-pretrained models to an unlabeled target domain without accessing the source data. Despite being a practically useful setting, existing methods require extensive parameter tuning over each source model, which is computationally expensive when facing abundant source domains or larger source models. To address this challenge, we propose a novel approach which is free of the parameter tuning over source backbones. Our technical contribution lies in the Bi-level ATtention ENsemble (Bi-ATEN) module, which learns both intra-domain weights and inter-domain ensemble weights to achieve a fine balance between instance specificity and domain consistency. By slightly tuning source bottlenecks, we achieve comparable or even superior performance on a challenging benchmark DomainNet with less than 3% trained parameters and 8 times of throughput compared with SOTA method. Furthermore, with minor modifications, the proposed module can be easily equipped to existing methods and gain more than 4% performance boost. Code is available at https://github.com/TL-UESTC/Bi-ATEN.

CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models

Developing Large Language Models (LLMs) with robust long-context capabilities has been the recent research focus, resulting in the emergence of long-context LLMs proficient in Chinese. However, the evaluation of these models remains underdeveloped due to a lack of benchmarks. To address this gap, we present CLongEval, a comprehensive Chinese benchmark for evaluating long-context LLMs. CLongEval is characterized by three key features: (1) Sufficient data volume, comprising 7 distinct tasks and 7,267 examples; (2) Broad applicability, accommodating to models with context windows size from 1K to 100K; (3) High quality, with over 2,000 manually annotated question-answer pairs in addition to the automatically constructed labels. With CLongEval, we undertake a comprehensive assessment of 6 open-source long-context LLMs and 2 leading commercial counterparts that feature both long-context abilities and proficiency in Chinese. We also provide in-depth analysis based on the empirical results, trying to shed light on the critical capabilities that present challenges in long-context settings. The dataset, evaluation scripts, and model outputs will be released.

Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation

Conventional Unsupervised Domain Adaptation (UDA) strives to minimize distribution discrepancy between domains, which neglects to harness rich semantics from data and struggles to handle complex domain shifts. A promising technique is to leverage the knowledge of large-scale pre-trained vision-language models for more guided adaptation. Despite some endeavors, current methods often learn textual prompts to embed domain semantics for source and target domains separately and perform classification within each domain, limiting cross-domain knowledge transfer. Moreover, prompting only the language branch lacks flexibility to adapt both modalities dynamically. To bridge this gap, we propose Domain-Agnostic Mutual Prompting (DAMP) to exploit domain-invariant semantics by mutually aligning visual and textual embeddings. Specifically, the image contextual information is utilized to prompt the language branch in a domain-agnostic and instance-conditioned way. Meanwhile, visual prompts are imposed based on the domain-agnostic textual prompt to elicit domain-invariant visual embeddings. These two branches of prompts are learned mutually with a cross-attention module and regularized with a semantic-consistency loss and an instance-discrimination contrastive loss. Experiments on three UDA benchmarks demonstrate the superiority of DAMP over state-of-the-art approaches.

TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Models

Driven by the proliferation of real-world application scenarios and scales, time series anomaly detection (TSAD) has attracted considerable scholarly and industrial interest. However, existing algorithms exhibit a gap in terms of training paradigm, online detection paradigm, and evaluation criteria when compared to the actual needs of real-world industrial systems. Firstly, current algorithms typically train a specific model for each individual time series. In a large-scale online system with tens of thousands of curves, maintaining such a multitude of models is impractical. The performance of using merely one single unified model to detect anomalies remains unknown. Secondly, most TSAD models are trained on the historical part of a time series and are tested on its future segment. In distributed systems, however, there are frequent system deployments and upgrades, with new, previously unseen time series emerging daily. The performance of testing newly incoming unseen time series on current TSAD algorithms remains unknown. Lastly, although some papers have conducted detailed surveys, the absence of an online evaluation platform prevents answering questions like "Who is the best at anomaly detection at the current stage?" In this paper, we propose TimeSeriesBench, an industrial-grade benchmark that we continuously maintain as a leaderboard. On this leaderboard, we assess the performance of existing algorithms across more than 168 evaluation settings combining different training and testing paradigms, evaluation metrics and datasets. Through our comprehensive analysis of the results, we provide recommendations for the future design of anomaly detection algorithms. To address known issues with existing public datasets, we release an industrial dataset to the public together with TimeSeriesBench. All code, data, and the online leaderboard have been made publicly available.