In ad-hoc retrieval, evaluation relies heavily on user actions, including implicit feedback. In a conversational setting such signals are usually unavailable due to the nature of the interactions, and, instead, the evaluation often relies on crowdsourced evaluation labels. The role of user feedback in annotators' assessment of turns in a conversational perception has been little studied. We focus on how the evaluation of task-oriented dialogue systems (TDSs), is affected by considering user feedback, explicit or implicit, as provided through the follow-up utterance of a turn being evaluated. We explore and compare two methodologies for assessing TDSs: one includes the user's follow-up utterance and one without. We use both crowdworkers and large language models (LLMs) as annotators to assess system responses across four aspects: relevance, usefulness, interestingness, and explanation quality. Our findings indicate that there is a distinct difference in ratings assigned by both annotator groups in the two setups, indicating user feedback does influence system evaluation. Workers are more susceptible to user feedback on usefulness and interestingness compared to LLMs on interestingness and relevance. User feedback leads to a more personalized assessment of usefulness by workers, aligning closely with the user's explicit feedback. Additionally, in cases of ambiguous or complex user requests, user feedback improves agreement among crowdworkers. These findings emphasize the significance of user feedback in refining system evaluations and suggest the potential for automated feedback integration in future research. We publicly release the annotated data to foster research in this area.
相關內容
Human-like Agents with diverse and dynamic personality could serve as an important design probe in the process of user-centered design, thereby enabling designers to enhance the user experience of interactive application.In this article, we introduce Evolving Agents, a novel agent architecture that consists of two systems: Personality and Behavior. The Personality system includes three modules: Cognition, Emotion and Character Growth. The Behavior system comprises two modules: Planning and Action. We also build a simulation platform that enables agents to interact with the environment and other agents. Evolving Agents can simulate the human personality evolution process. Compared to its initial state, agents' personality and behavior patterns undergo believable development after several days of simulation. Agents reflect on their behavior to reason and develop new personality traits. These traits, in turn, generate new behavior patterns, forming a feedback loop-like personality evolution.In our experiment, we utilized simulation platform with 10 agents for evaluation. During the evaluation, these agents experienced believable and inspirational personality evolution. Through ablation and control experiments, we demonstrated the outstanding effectiveness of agent personality evolution and all modules of our agent architecture contribute to creating believable human-like agents with diverse and dynamic personalities. We also demonstrated through workshops how Evolving Agents could inspire designers.
Large language models (LLMs) demonstrate exceptional instruct-following ability to complete various downstream tasks. Although this impressive ability makes LLMs flexible task solvers, their performance in solving tasks also heavily relies on instructions. In this paper, we reveal that LLMs are over-sensitive to lexical variations in task instructions, even when the variations are imperceptible to humans. By providing models with neighborhood instructions, which are closely situated in the latent representation space and differ by only one semantically similar word, the performance on downstream tasks can be vastly different. Following this property, we propose a black-box Combinatorial Optimization framework for Prompt Lexical Enhancement (COPLE). COPLE performs iterative lexical optimization according to the feedback from a batch of proxy tasks, using a search strategy related to word influence. Experiments show that even widely-used human-crafted prompts for current benchmarks suffer from the lexical sensitivity of models, and COPLE recovers the declined model ability in both instruct-following and solving downstream tasks.
While subword tokenizers such as BPE and WordPiece are typically used to build vocabularies for NLP models, the method of decoding text into a sequence of tokens from these vocabularies is often left unspecified, or ill-suited to the method in which they were constructed. We provide a controlled analysis of seven tokenizer inference methods across four different algorithms and three vocabulary sizes, performed on a novel intrinsic evaluation suite we curated for English, combining measures rooted in morphology, cognition, and information theory. We show that for the most commonly used tokenizers, greedy inference performs surprisingly well; and that SaGe, a recently-introduced contextually-informed tokenizer, outperforms all others on morphological alignment.
Credential theft and remote attacks are the most serious threats to user authentication mechanisms. The crux of these problems is that we cannot control such behaviors. However, if a password does not contain user secrets, stealing it is useless. If unauthorized inputs are invalidated, remote attacks can be disabled. Thus, credential secrets and account input fields can be controlled. Rather than encrypting passwords, we design a dual-password login-authentication mechanism, where a user-selected secret-free login password is converted into an untypable authentication password. Subsequently, the authenticatable functionality of the login password and the typable functionality of the authentication password can be disabled or invalidated to prevent credential theft and remote attacks. Thus, the usability-security tradeoff and password reuse issues are resolved; local authentication password storage is no longer necessary. More importantly, the password converter acts as an open hashing algorithm, meaning that its intermediate elements can be used to define a truly unique identity for the login process to implement a novel dual-identity authentication scheme. In particular, the system-managed elements are concealed, inaccessible, and independent of any personal information and therefore can be used to define a perfect unforgeable process identifier to identify unauthorized inputs.
Network function (NF) offloading on SmartNICs has been widely used in modern data centers, offering benefits in host resource saving and programmability. Co-running NFs on the same SmartNICs can cause performance interference due to onboard resource contention. Therefore, to meet performance SLAs while ensuring efficient resource management, operators need mechanisms to predict NF performance under such contention. However, existing solutions lack SmartNIC-specific knowledge and exhibit limited traffic awareness, leading to poor accuracy for on-NIC NFs. This paper proposes Tomur, a novel performance predictive system for on-NIC NFs. Tomur builds upon the key observation that co-located NFs contend for multiple resources, including onboard accelerators and the memory subsystem. It also facilitates traffic awareness according to the behaviors of individual resources to maintain accuracy as the external traffic attributes vary. Evaluation using BlueField-2 SmartNIC shows that Tomur improves the prediction accuracy by 78.8% and reduces SLA violations by 92.2% compared to state-of-the-art approaches, and enables new practical usecases.
Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and PaLI-3. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored, making it challenging to understand what factors account for model performance $-$ a challenge further complicated by the lack of objective, consistent evaluations. To address these gaps, we first compile a suite of standardized evaluations spanning visual question answering, object localization, and challenge sets that probe properties such as hallucination; evaluations that provide fine-grained insight VLM capabilities. Second, we rigorously investigate VLMs along key design axes, including pretrained visual representations and training from base vs. instruct-tuned language models, amongst others. We couple our analysis with three resource contributions: (1) a unified framework for evaluating VLMs, (2) optimized, flexible training code, and (3) checkpoints for all models, including a family of VLMs at the 7-13B scale that strictly outperform InstructBLIP and LLaVa v1.5, the state-of-the-art in open VLMs.
Phishing attacks pose a significant threat to Internet users, with cybercriminals elaborately replicating the visual appearance of legitimate websites to deceive victims. Visual similarity-based detection systems have emerged as an effective countermeasure, but their effectiveness and robustness in real-world scenarios have been unexplored. In this paper, we comprehensively scrutinize and evaluate state-of-the-art visual similarity-based anti-phishing models using a large-scale dataset of 450K real-world phishing websites. Our analysis reveals that while certain models maintain high accuracy, others exhibit notably lower performance than results on curated datasets, highlighting the importance of real-world evaluation. In addition, we observe the real-world tactic of manipulating visual components that phishing attackers employ to circumvent the detection systems. To assess the resilience of existing models against adversarial attacks and robustness, we apply visible and perturbation-based manipulations to website logos, which adversaries typically target. We then evaluate the models' robustness in handling these adversarial samples. Our findings reveal vulnerabilities in several models, emphasizing the need for more robust visual similarity techniques capable of withstanding sophisticated evasion attempts. We provide actionable insights for enhancing the security of phishing defense systems, encouraging proactive actions. To the best of our knowledge, this work represents the first large-scale, systematic evaluation of visual similarity-based models for phishing detection in real-world settings, necessitating the development of more effective and robust defenses.
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this paper, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.
The advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of large language models has been dramatically improved, leading to human-like performances in understanding, language synthesizing, and common-sense reasoning, etc. Such a major leap-forward in general AI capacity will change the pattern of how personalization is conducted. For one thing, it will reform the way of interaction between humans and personalization systems. Instead of being a passive medium of information filtering, large language models present the foundation for active user engagement. On top of such a new foundation, user requests can be proactively explored, and user's required information can be delivered in a natural and explainable way. For another thing, it will also considerably expand the scope of personalization, making it grow from the sole function of collecting personalized information to the compound function of providing personalized services. By leveraging large language models as general-purpose interface, the personalization systems may compile user requests into plans, calls the functions of external tools to execute the plans, and integrate the tools' outputs to complete the end-to-end personalization tasks. Today, large language models are still being developed, whereas the application in personalization is largely unexplored. Therefore, we consider it to be the right time to review the challenges in personalization and the opportunities to address them with LLMs. In particular, we dedicate this perspective paper to the discussion of the following aspects: the development and challenges for the existing personalization system, the newly emerged capabilities of large language models, and the potential ways of making use of large language models for personalization.
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.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191