Weihang Su

Weihang Su, Yichen Tang, Qingyao Ai et al. · tsinghua

The emergence of Large Language Models (LLMs) has revolutionized how users access information, shifting from traditional search engines to direct question-and-answer interactions with LLMs. However, the widespread adoption of LLMs has revealed a significant challenge known as hallucination, wherein LLMs generate coherent yet factually inaccurate responses. This hallucination phenomenon has led to users' distrust in information retrieval systems based on LLMs. To tackle this challenge, this paper proposes Dynamic Retrieval Augmentation based on hallucination Detection (DRAD) as a novel method to detect and mitigate hallucinations in LLMs. DRAD improves upon traditional retrieval augmentation by dynamically adapting the retrieval process based on real-time hallucination detection. It features two main components: Real-time Hallucination Detection (RHD) for identifying potential hallucinations without external models, and Self-correction based on External Knowledge (SEK) for correcting these errors using external knowledge. Experiment results show that DRAD demonstrates superior performance in both detecting and mitigating hallucinations in LLMs. All of our code and data are open-sourced at https://github.com/oneal2000/EntityHallucination.

Weihang Su, Xiangsheng Li, Yiqun Liu et al.

Our team(THUIR2) participated in both FOSS and POSS subtasks of the NTCIR-161 Session Search (SS) Task. This paper describes our approaches and results. In the FOSS subtask, we submit five runs using learning-to-rank and fine-tuned pre-trained language models. We fine-tuned the pre-trained language model with ad-hoc data and session information and assembled them by a learning-to-rank method. The assembled model achieves the best performance among all participants in the preliminary evaluation. In the POSS subtask, we used an assembled model which also achieves the best performance in the preliminary evaluation.

Changyue Wang, Weihang Su, Hu Yiran et al.

Recent advances in Large Language Models (LLMs) have significantly shaped the applications of AI in multiple fields, including the studies of legal intelligence. Trained on extensive legal texts, including statutes and legal documents, the legal LLMs can capture important legal knowledge/concepts effectively and provide important support for downstream legal applications such as legal consultancy. Yet, the dynamic nature of legal statutes and interpretations also poses new challenges to the use of LLMs in legal applications. Particularly, how to update the legal knowledge of LLMs effectively and efficiently has become an important research problem in practice. Existing benchmarks for evaluating knowledge update methods are mostly designed for the open domain and cannot address the specific challenges of the legal domain, such as the nuanced application of new legal knowledge, the complexity and lengthiness of legal regulations, and the intricate nature of legal reasoning. To address this gap, we introduce the Legal Knowledge Update BEnchmark, i.e. LeKUBE, which evaluates knowledge update methods for legal LLMs across five dimensions. Specifically, we categorize the needs of knowledge updates in the legal domain with the help of legal professionals, and then hire annotators from law schools to create synthetic updates to the Chinese Criminal and Civil Code as well as sets of questions of which the answers would change after the updates. Through a comprehensive evaluation of state-of-the-art knowledge update methods, we reveal a notable gap between existing knowledge update methods and the unique needs of the legal domain, emphasizing the need for further research and development of knowledge update mechanisms tailored for legal LLMs.

Weihang Su, Jianming Long, Changyue Wang et al.

Large Language Models (LLMs) frequently exhibit hallucinations, generating content that appears fluent and coherent but is factually incorrect. Such errors undermine trust and hinder their adoption in real-world applications. To address this challenge, two distinct research paradigms have emerged: model-centric Hallucination Detection (HD) and text-centric Fact Verification (FV). Despite sharing the same goal, these paradigms have evolved in isolation, using distinct assumptions, datasets, and evaluation protocols. This separation has created a research schism that hinders their collective progress. In this work, we take a decisive step toward bridging this divide. We introduce UniFact, a unified evaluation framework that enables direct, instance-level comparison between FV and HD by dynamically generating model outputs and corresponding factuality labels. Through large-scale experiments across multiple LLM families and detection methods, we reveal three key findings: (1) No paradigm is universally superior; (2) HD and FV capture complementary facets of factual errors; and (3) hybrid approaches that integrate both methods consistently achieve state-of-the-art performance. Beyond benchmarking, we provide the first in-depth analysis of why FV and HD diverged, as well as empirical evidence supporting the need for their unification. The comprehensive experimental results call for a new, integrated research agenda toward unifying Hallucination Detection and Fact Verification in LLMs. We have open-sourced all the code, data, and baseline implementation at: https://github.com/oneal2000/UniFact/

Weihang Su, Yichen Tang, Qingyao Ai et al. · tsinghua

Dynamic retrieval augmented generation (RAG) paradigm actively decides when and what to retrieve during the text generation process of Large Language Models (LLMs). There are two key elements of this paradigm: identifying the optimal moment to activate the retrieval module (deciding when to retrieve) and crafting the appropriate query once retrieval is triggered (determining what to retrieve). However, current dynamic RAG methods fall short in both aspects. Firstly, the strategies for deciding when to retrieve often rely on static rules. Moreover, the strategies for deciding what to retrieve typically limit themselves to the LLM's most recent sentence or the last few tokens, while the LLM's real-time information needs may span across the entire context. To overcome these limitations, we introduce a new framework, DRAGIN, i.e., Dynamic Retrieval Augmented Generation based on the real-time Information Needs of LLMs. Our framework is specifically designed to make decisions on when and what to retrieve based on the LLM's real-time information needs during the text generation process. We evaluate DRAGIN along with existing methods comprehensively over 4 knowledge-intensive generation datasets. Experimental results show that DRAGIN achieves superior performance on all tasks, demonstrating the effectiveness of our method. We have open-sourced all the code, data, and models in GitHub: https://github.com/oneal2000/DRAGIN/tree/main

Weihang Su, Yichen Tang, Qingyao Ai et al.

Retrieval-augmented generation (RAG) techniques have emerged as a promising solution to enhance the reliability of large language models (LLMs) by addressing issues like hallucinations, outdated knowledge, and domain adaptation. In particular, existing RAG methods append relevant documents retrieved from external corpus or databases to the input of LLMs to guide their generation process, which we refer to as the in-context knowledge injection method. While this approach is simple and often effective, it has inherent limitations. Firstly, increasing the context length and number of relevant documents can lead to higher computational overhead and degraded performance, especially in complex reasoning tasks. More importantly, in-context knowledge injection operates primarily at the input level, but LLMs store their internal knowledge in their parameters. This gap fundamentally limits the capacity of in-context methods. To this end, we introduce Parametric retrieval-augmented generation (Parametric RAG), a new RAG paradigm that integrates external knowledge directly into the parameters of feed-forward networks (FFN) of an LLM through document parameterization. This approach not only saves online computational costs by eliminating the need to inject multiple documents into the LLMs' input context, but also deepens the integration of external knowledge into the parametric knowledge space of the LLM. Experimental results demonstrate that Parametric RAG substantially enhances both the effectiveness and efficiency of knowledge augmentation in LLMs. Also, it can be combined with in-context RAG methods to achieve even better performance. We have open-sourced all the code, data, and models in the following anonymized GitHub link: https://github.com/oneal2000/PRAG

Weihang Su, Baoqing Yue, Qingyao Ai et al.

This paper introduces JuDGE (Judgment Document Generation Evaluation), a novel benchmark for evaluating the performance of judgment document generation in the Chinese legal system. We define the task as generating a complete legal judgment document from the given factual description of the case. To facilitate this benchmark, we construct a comprehensive dataset consisting of factual descriptions from real legal cases, paired with their corresponding full judgment documents, which serve as the ground truth for evaluating the quality of generated documents. This dataset is further augmented by two external legal corpora that provide additional legal knowledge for the task: one comprising statutes and regulations, and the other consisting of a large collection of past judgment documents. In collaboration with legal professionals, we establish a comprehensive automated evaluation framework to assess the quality of generated judgment documents across various dimensions. We evaluate various baseline approaches, including few-shot in-context learning, fine-tuning, and a multi-source retrieval-augmented generation (RAG) approach, using both general and legal-domain LLMs. The experimental results demonstrate that, while RAG approaches can effectively improve performance in this task, there is still substantial room for further improvement. All the codes and datasets are available at: https://github.com/oneal2000/JuDGE.

Changyue Wang, Weihang Su, Qingyao Ai et al.

Large Reasoning Models (LRMs) extend large language models with explicit, multi-step reasoning traces to enhance transparency and performance on complex tasks. However, these reasoning traces can be redundant or logically inconsistent, becoming a new and hard-to-detect source of hallucination. Existing hallucination detection methods focus primarily on answer-level uncertainty and often fail to detect hallucinations or logical inconsistencies arising from the model's reasoning trace. This oversight is particularly problematic for LRMs, where the explicit thinking trace is not only an important support to the model's decision-making process but also a key source of potential hallucination. To this end, we propose RACE (Reasoning and Answer Consistency Evaluation), a novel framework specifically tailored for hallucination detection in LRMs. RACE operates by extracting essential reasoning steps and computing four diagnostic signals: inter-sample consistency of reasoning traces, entropy-based answer uncertainty, semantic alignment between reasoning and answers, and internal coherence of reasoning. The joint utilization of these signals makes RACE a more robust detector of hallucinations in LRMs. Experiments across datasets and different LLMs demonstrate that RACE outperforms existing hallucination detection baselines, offering a robust and generalizable solution for evaluating LRMs. The source code is available at https://github.com/bebr2/RACE

Changyue Wang, Weihang Su, Qingyao Ai et al.

Knowledge editing aims to efficiently update Large Language Models (LLMs) by modifying specific knowledge without retraining the entire model. Among knowledge editing approaches, in-context editing (ICE) offers a lightweight solution by injecting new knowledge directly into the input context, leaving model parameters unchanged. However, existing ICE approaches do not explicitly separate the newly injected knowledge from the model's original reasoning process. This entanglement often results in conflicts between external updates and internal parametric knowledge, undermining the consistency and accuracy of the reasoning path.In this work, we conduct preliminary experiments to examine how parametric knowledge influences reasoning path planning. We find that the model's reasoning is tightly coupled with its internal knowledge, and that naively injecting new information without adapting the reasoning path often leads to performance degradation, particularly in multi-hop tasks. To this end, we propose DecKER, a novel ICE framework that decouples reasoning from knowledge editing by generating a masked reasoning path and then resolving knowledge edits via hybrid retrieval and model-based validation. Experiments on multi-hop QA benchmarks show that DecKER significantly outperforms existing ICE methods by mitigating knowledge conflicts and preserving reasoning consistency. Our code is available at: https://github.com/bebr2/DecKER .

Weihang Su, Anzhe Xie, Qingyao Ai et al.

The rapid growth of academic literature makes the manual creation of scientific surveys increasingly infeasible. While large language models show promise for automating this process, progress in this area is hindered by the absence of standardized benchmarks and evaluation protocols. To bridge this critical gap, we introduce SurGE (Survey Generation Evaluation), a new benchmark for scientific survey generation in computer science. SurGE consists of (1) a collection of test instances, each including a topic description, an expert-written survey, and its full set of cited references, and (2) a large-scale academic corpus of over one million papers. In addition, we propose an automated evaluation framework that measures the quality of generated surveys across four dimensions: comprehensiveness, citation accuracy, structural organization, and content quality. Our evaluation of diverse LLM-based methods demonstrates a significant performance gap, revealing that even advanced agentic frameworks struggle with the complexities of survey generation and highlighting the need for future research in this area. We have open-sourced all the code, data, and models at: https://github.com/oneal2000/SurGE

Weihang Su, Yiran Hu, Anzhe Xie et al.

Statute retrieval aims to find relevant statutory articles for specific queries. This process is the basis of a wide range of legal applications such as legal advice, automated judicial decisions, legal document drafting, etc. Existing statute retrieval benchmarks focus on formal and professional queries from sources like bar exams and legal case documents, thereby neglecting non-professional queries from the general public, which often lack precise legal terminology and references. To address this gap, we introduce the STAtute Retrieval Dataset (STARD), a Chinese dataset comprising 1,543 query cases collected from real-world legal consultations and 55,348 candidate statutory articles. Unlike existing statute retrieval datasets, which primarily focus on professional legal queries, STARD captures the complexity and diversity of real queries from the general public. Through a comprehensive evaluation of various retrieval baselines, we reveal that existing retrieval approaches all fall short of these real queries issued by non-professional users. The best method only achieves a Recall@100 of 0.907, suggesting the necessity for further exploration and additional research in this area. All the codes and datasets are available at: https://github.com/oneal2000/STARD/tree/main

Haitao Li, Changyue Wang, Weihang Su et al.

This paper describes the approach of the THUIR team at the COLIEE 2023 Legal Case Entailment task. This task requires the participant to identify a specific paragraph from a given supporting case that entails the decision for the query case. We try traditional lexical matching methods and pre-trained language models with different sizes. Furthermore, learning-to-rank methods are employed to further improve performance. However, learning-to-rank is not very robust on this task. which suggests that answer passages cannot simply be determined with information retrieval techniques. Experimental results show that more parameters and legal knowledge contribute to the legal case entailment task. Finally, we get the third place in COLIEE 2023. The implementation of our method can be found at https://github.com/CSHaitao/THUIR-COLIEE2023.

Haitao Li, Weihang Su, Changyue Wang et al.

Legal case retrieval techniques play an essential role in modern intelligent legal systems. As an annually well-known international competition, COLIEE is aiming to achieve the state-of-the-art retrieval model for legal texts. This paper summarizes the approach of the championship team THUIR in COLIEE 2023. To be specific, we design structure-aware pre-trained language models to enhance the understanding of legal cases. Furthermore, we propose heuristic pre-processing and post-processing approaches to reduce the influence of irrelevant messages. In the end, learning-to-rank methods are employed to merge features with different dimensions. Experimental results demonstrate the superiority of our proposal. Official results show that our run has the best performance among all submissions. The implementation of our method can be found at https://github.com/CSHaitao/THUIR-COLIEE2023.

Weihang Su, Changyue Wang, Qingyao Ai et al. · tsinghua

Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs producing responses that are coherent yet factually inaccurate. This issue undermines the effectiveness of LLMs in practical applications, necessitating research into detecting and mitigating hallucinations of LLMs. Previous studies have mainly concentrated on post-processing techniques for hallucination detection, which tend to be computationally intensive and limited in effectiveness due to their separation from the LLM's inference process. To overcome these limitations, we introduce MIND, an unsupervised training framework that leverages the internal states of LLMs for real-time hallucination detection without requiring manual annotations. Additionally, we present HELM, a new benchmark for evaluating hallucination detection across multiple LLMs, featuring diverse LLM outputs and the internal states of LLMs during their inference process. Our experiments demonstrate that MIND outperforms existing state-of-the-art methods in hallucination detection.

Yan Fang, Jingtao Zhan, Qingyao Ai et al. · tsinghua

Scaling up neural models has yielded significant advancements in a wide array of tasks, particularly in language generation. Previous studies have found that the performance of neural models frequently adheres to predictable scaling laws, correlated with factors such as training set size and model size. This insight is invaluable, especially as large-scale experiments grow increasingly resource-intensive. Yet, such scaling law has not been fully explored in dense retrieval due to the discrete nature of retrieval metrics and complex relationships between training data and model sizes in retrieval tasks. In this study, we investigate whether the performance of dense retrieval models follows the scaling law as other neural models. We propose to use contrastive log-likelihood as the evaluation metric and conduct extensive experiments with dense retrieval models implemented with different numbers of parameters and trained with different amounts of annotated data. Results indicate that, under our settings, the performance of dense retrieval models follows a precise power-law scaling related to the model size and the number of annotations. Additionally, we examine scaling with prevalent data augmentation methods to assess the impact of annotation quality, and apply the scaling law to find the best resource allocation strategy under a budget constraint. We believe that these insights will significantly contribute to understanding the scaling effect of dense retrieval models and offer meaningful guidance for future research endeavors.

Weihang Su, Qingyao Ai, Xiangsheng Li et al.

With the development of deep learning and natural language processing techniques, pre-trained language models have been widely used to solve information retrieval (IR) problems. Benefiting from the pre-training and fine-tuning paradigm, these models achieve state-of-the-art performance. In previous works, plain texts in Wikipedia have been widely used in the pre-training stage. However, the rich structured information in Wikipedia, such as the titles, abstracts, hierarchical heading (multi-level title) structure, relationship between articles, references, hyperlink structures, and the writing organizations, has not been fully explored. In this paper, we devise four pre-training objectives tailored for IR tasks based on the structured knowledge of Wikipedia. Compared to existing pre-training methods, our approach can better capture the semantic knowledge in the training corpus by leveraging the human-edited structured data from Wikipedia. Experimental results on multiple IR benchmark datasets show the superior performance of our model in both zero-shot and fine-tuning settings compared to existing strong retrieval baselines. Besides, experimental results in biomedical and legal domains demonstrate that our approach achieves better performance in vertical domains compared to previous models, especially in scenarios where long text similarity matching is needed.

Ziyi Ye, Xiaohui Xie, Qingyao Ai et al.

The Relevance Feedback (RF) process relies on accurate and real-time relevance estimation of feedback documents to improve retrieval performance. Since collecting explicit relevance annotations imposes an extra burden on the user, extensive studies have explored using pseudo-relevance signals and implicit feedback signals as substitutes. However, such signals are indirect indicators of relevance and suffer from complex search scenarios where user interactions are absent or biased. Recently, the advances in portable and high-precision brain-computer interface (BCI) devices have shown the possibility to monitor user's brain activities during search process. Brain signals can directly reflect user's psychological responses to search results and thus it can act as additional and unbiased RF signals. To explore the effectiveness of brain signals in the context of RF, we propose a novel RF framework that combines BCI-based relevance feedback with pseudo-relevance signals and implicit signals to improve the performance of document re-ranking. The experimental results on the user study dataset show that incorporating brain signals leads to significant performance improvement in our RF framework. Besides, we observe that brain signals perform particularly well in several hard search scenarios, especially when implicit signals as feedback are missing or noisy. This reveals when and how to exploit brain signals in the context of RF.

Yiteng Tu, Weihang Su, Yujia Zhou et al.

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamentally constrained by the reliability of both the retriever and the knowledge base. In real-world scenarios, imperfections in these components often lead to the retrieval of noisy, irrelevant, or misleading counterfactual information, ultimately undermining the trustworthiness of RAG systems. To address this challenge, we propose Robust Fine-Tuning (RbFT), a method designed to enhance the resilience of LLMs against retrieval defects through two targeted fine-tuning tasks. Experimental results demonstrate that RbFT significantly improves the robustness of RAG systems across diverse retrieval conditions, surpassing existing methods while maintaining high inference efficiency and compatibility with other robustness techniques.

Yichen Tang, Weihang Su, Yujia Zhou et al.

Multi-agent techniques such as role playing or multi-turn debates have been shown to be effective in improving the performance of large language models (LLMs) in downstream tasks. Despite their differences in workflows, existing multi-agent systems constructed from a single base LLM mostly use natural language for agent communication. While this is appealing for its simplicity and interpretability, it also introduces inevitable information loss as one model must down sample its continuous state vectors to discrete tokens before transferring them to the other model. Such losses are particularly significant when the information to transfer is not simple facts, but reasoning logics or abstractive thoughts. To tackle this problem, we propose a new communication protocol that transfers both natural language tokens and token-wise state transition trajectory from one agent to another. Particularly, compared to the actual state value, we find that the sequence of state changes in LLMs after generating each token can better reflect the information hidden behind the inference process. We propose a State Delta Encoding (SDE) method to represent state transition trajectories. The experimental results show that multi-agent systems with SDE achieve SOTA performance compared to other communication protocols, particularly in tasks that involve complex reasoning.

Qingyao Ai, Yichen Tang, Changyue Wang et al.

Scaling up data, parameters, and test-time computation has been the mainstream methods to improve LLM systems (LLMsys), but their upper bounds are almost reached due to the gradual depletion of high-quality data and marginal gains obtained from larger computational resource consumption. Inspired by the abilities of human and traditional AI systems in learning from practice, constructing memory and continual learning frameworks for LLMsys has become an important and popular research direction in recent literature. Yet, existing benchmarks for LLM memory often focus on evaluating the system on homogeneous reading comprehension tasks with long-form inputs rather than testing their abilities to learn from accumulated user feedback in service time. Therefore, we propose a user feedback simulation framework and a comprehensive benchmark covering multiple domains, languages, and types of tasks to evaluate the continual learning abilities of LLMsys. Experiments show that the effectiveness and efficiency of state-of-the-art baselines are far from satisfying, and we hope this benchmark could pave the way for future studies on LLM memory and optimization algorithms.

Junjie Chen, Weihang Su, Zhumin Chu et al.

The rapid development of large language models (LLMs) has highlighted the need for efficient and reliable methods to evaluate their performance. Traditional evaluation methods often face challenges like high costs, limited task formats, dependence on human references, and systematic biases. To address these limitations, we propose Auto-PRE, an automatic LLM evaluation framework inspired by the peer review process. Unlike previous approaches that rely on human annotations, Auto-PRE automatically selects evaluator LLMs based on three core traits: consistency, pertinence, and self-confidence, which correspond to the instruction, content, and response stages, respectively, and collectively cover the entire evaluation process. Experiments on three representative tasks, including summarization, non-factoid QA, and dialogue generation, demonstrate that Auto-PRE achieves state-of-the-art performance while significantly reducing evaluation costs. Furthermore, the structured and scalable design of our automatic qualification exam framework provides valuable insights into automating the evaluation of LLMs-as-judges, paving the way for more advanced LLM-based evaluation frameworks.

Yixiao Ma, Yueyue Wu, Weihang Su et al.

Legal case retrieval is a critical process for modern legal information systems. While recent studies have utilized pre-trained language models (PLMs) based on the general domain self-supervised pre-training paradigm to build models for legal case retrieval, there are limitations in using general domain PLMs as backbones. Specifically, these models may not fully capture the underlying legal features in legal case documents. To address this issue, we propose CaseEncoder, a legal document encoder that leverages fine-grained legal knowledge in both the data sampling and pre-training phases. In the data sampling phase, we enhance the quality of the training data by utilizing fine-grained law article information to guide the selection of positive and negative examples. In the pre-training phase, we design legal-specific pre-training tasks that align with the judging criteria of relevant legal cases. Based on these tasks, we introduce an innovative loss function called Biased Circle Loss to enhance the model's ability to recognize case relevance in fine grains. Experimental results on multiple benchmarks demonstrate that CaseEncoder significantly outperforms both existing general pre-training models and legal-specific pre-training models in zero-shot legal case retrieval.

Ningyu He, Weihang Su, Zhou Yu et al.

The continuing expansion of the blockchain ecosystems has attracted much attention from the research community. However, although a large number of research studies have been proposed to understand the diverse characteristics of individual blockchain systems (e.g., Bitcoin or Ethereum), little is known at a comprehensive level on the evolution of blockchain ecosystems at scale, longitudinally, and across multiple blockchains. We argue that understanding the dynamics of blockchain ecosystems could provide unique insights that cannot be achieved through studying a single static snapshot or a single blockchain network alone. Based on billions of transaction records collected from three representative and popular blockchain systems (Bitcoin, Ethereum and EOSIO) over 10 years, we conduct the first study on the evolution of multiple blockchain ecosystems from different perspectives. Our exploration suggests that, although the overall blockchain ecosystem shows promising growth over the last decade, a number of worrying outliers exist that have disrupted its evolution.

Xuesong Chen, Ziyi Ye, Xiaohui Xie et al.

While search technologies have evolved to be robust and ubiquitous, the fundamental interaction paradigm has remained relatively stable for decades. With the maturity of the Brain-Machine Interface, we build an efficient and effective communication system between human beings and search engines based on electroencephalogram(EEG) signals, called Brain-Machine Search Interface(BMSI) system. The BMSI system provides functions including query reformulation and search result interaction. In our system, users can perform search tasks without having to use the mouse and keyboard. Therefore, it is useful for application scenarios in which hand-based interactions are infeasible, e.g, for users with severe neuromuscular disorders. Besides, based on brain signals decoding, our system can provide abundant and valuable user-side context information(e.g., real-time satisfaction feedback, extensive context information, and a clearer description of information needs) to the search engine, which is hard to capture in the previous paradigm. In our implementation, the system can decode user satisfaction from brain signals in real-time during the interaction process and re-rank the search results list based on user satisfaction feedback. The demo video is available at http://www.thuir.cn/group/YQLiu/datasets/BMSISystem.mp4.

Pengcheng Xia, Haoyu wang, Bingyu Gao et al.

The prosperity of the cryptocurrency ecosystem drives the need for digital asset trading platforms. Beyond centralized exchanges (CEXs), decentralized exchanges (DEXs) are introduced to allow users to trade cryptocurrency without transferring the custody of their digital assets to the middlemen, thus eliminating the security and privacy issues of traditional CEX. Uniswap, as the most prominent cryptocurrency DEX, is continuing to attract scammers, with fraudulent cryptocurrencies flooding in the ecosystem. In this paper, we take the first step to detect and characterize scam tokens on Uniswap. We first collect all the transactions related to Uniswap V2 exchange and investigate the landscape of cryptocurrency trading on Uniswap from different perspectives. Then, we propose an accurate approach for flagging scam tokens on Uniswap based on a guilt-by-association heuristic and a machine-learning powered technique. We have identified over 10K scam tokens listed on Uniswap, which suggests that roughly 50% of the tokens listed on Uniswap are scam tokens. All the scam tokens and liquidity pools are created specialized for the "rug pull" scams, and some scam tokens have embedded tricks and backdoors in the smart contracts. We further observe that thousands of collusion addresses help carry out the scams in league with the scam token/pool creators. The scammers have gained a profit of at least \$16 million from 39,762 potential victims. Our observations in this paper suggest the urgency to identify and stop scams in the decentralized finance ecosystem, and our approach can act as a whistleblower that identifies scam tokens at their early stages.