Given the advancements in conversational artificial intelligence, the evaluation and assessment of Large Language Models (LLMs) play a crucial role in ensuring optimal performance across various conversational tasks. In this paper, we present a comprehensive study that thoroughly evaluates the capabilities and limitations of five prevalent LLMs: Llama, OPT, Falcon, Alpaca, and MPT. The study encompasses various conversational tasks, including reservation, empathetic response generation, mental health and legal counseling, persuasion, and negotiation. To conduct the evaluation, an extensive test setup is employed, utilizing multiple evaluation criteria that span from automatic to human evaluation. This includes using generic and task-specific metrics to gauge the LMs' performance accurately. From our evaluation, no single model emerges as universally optimal for all tasks. Instead, their performance varies significantly depending on the specific requirements of each task. While some models excel in certain tasks, they may demonstrate comparatively poorer performance in others. These findings emphasize the importance of considering task-specific requirements and characteristics when selecting the most suitable LM for conversational applications.
Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become increasingly widespread, their potential safety and robustness issues raise concerns that adversaries may evade the system and cause these models to generate toxic content through malicious attacks. Therefore, evaluating the robustness of open-source VLMs against adversarial attacks has garnered growing attention, with transfer-based attacks as a representative black-box attacking strategy. However, most existing transfer-based attacks neglect the importance of the semantic correlations between vision and text modalities, leading to sub-optimal adversarial example generation and attack performance. To address this issue, we present Chain of Attack (CoA), which iteratively enhances the generation of adversarial examples based on the multi-modal semantic update using a series of intermediate attacking steps, achieving superior adversarial transferability and efficiency. A unified attack success rate computing method is further proposed for automatic evasion evaluation. Extensive experiments conducted under the most realistic and high-stakes scenario, demonstrate that our attacking strategy can effectively mislead models to generate targeted responses using only black-box attacks without any knowledge of the victim models. The comprehensive robustness evaluation in our paper provides insight into the vulnerabilities of VLMs and offers a reference for the safety considerations of future model developments.
The Interactive Knowledge Assistant Track (iKAT) 2024 focuses on advancing conversational assistants, able to adapt their interaction and responses from personalized user knowledge. The track incorporates a Personal Textual Knowledge Base (PTKB) alongside Conversational AI tasks, such as passage ranking and response generation. Query Rewrite being an effective approach for resolving conversational context, we explore Large Language Models (LLMs), as query rewriters. Specifically, our submitted runs explore multi-aspect query generation using the MQ4CS framework, which we further enhance with Learned Sparse Retrieval via the SPLADE architecture, coupled with robust cross-encoder models. We also propose an alternative to the previous interleaving strategy, aggregating multiple aspects during the reranking phase. Our findings indicate that multi-aspect query generation is effective in enhancing performance when integrated with advanced retrieval and reranking models. Our results also lead the way for better personalization in Conversational Search, relying on LLMs to integrate personalization within query rewrite, and outperforming human rewrite performance.
Recent advances in Large Vision-Language Models (LVLMs) have showcased strong reasoning abilities across multiple modalities, achieving significant breakthroughs in various real-world applications. Despite this great success, the safety guardrail of LVLMs may not cover the unforeseen domains introduced by the visual modality. Existing studies primarily focus on eliciting LVLMs to generate harmful responses via carefully crafted image-based jailbreaks designed to bypass alignment defenses. In this study, we reveal that a safe image can be exploited to achieve the same jailbreak consequence when combined with additional safe images and prompts. This stems from two fundamental properties of LVLMs: universal reasoning capabilities and safety snowball effect. Building on these insights, we propose Safety Snowball Agent (SSA), a novel agent-based framework leveraging agents' autonomous and tool-using abilities to jailbreak LVLMs. SSA operates through two principal stages: (1) initial response generation, where tools generate or retrieve jailbreak images based on potential harmful intents, and (2) harmful snowballing, where refined subsequent prompts induce progressively harmful outputs. Our experiments demonstrate that \ours can use nearly any image to induce LVLMs to produce unsafe content, achieving high success jailbreaking rates against the latest LVLMs. Unlike prior works that exploit alignment flaws, \ours leverages the inherent properties of LVLMs, presenting a profound challenge for enforcing safety in generative multimodal systems. Our code is avaliable at \url{https://github.com/gzcch/Safety_Snowball_Agent}.
Incorporating external knowledge into dialogue generation has been proven to benefit the performance of an open-domain Dialogue System (DS), such as generating informative or stylized responses, controlling conversation topics. In this article, we study the open-domain DS that uses unstructured text as external knowledge sources (\textbf{U}nstructured \textbf{T}ext \textbf{E}nhanced \textbf{D}ialogue \textbf{S}ystem, \textbf{UTEDS}). The existence of unstructured text entails distinctions between UTEDS and traditional data-driven DS and we aim to analyze these differences. We first give the definition of the UTEDS related concepts, then summarize the recently released datasets and models. We categorize UTEDS into Retrieval and Generative models and introduce them from the perspective of model components. The retrieval models consist of Fusion, Matching, and Ranking modules, while the generative models comprise Dialogue and Knowledge Encoding, Knowledge Selection, and Response Generation modules. We further summarize the evaluation methods utilized in UTEDS and analyze the current models' performance. At last, we discuss the future development trends of UTEDS, hoping to inspire new research in this field.
Task-Oriented Dialogue (TOD) systems assist users in completing tasks through natural language interactions, often relying on a single-layered workflow structure for slot-filling in public tasks, such as hotel bookings. However, in enterprise environments, which involve rich domain-specific knowledge, TOD systems face challenges due to task complexity and the lack of standardized documentation. In this work, we introduce HierTOD, an enterprise TOD system driven by hierarchical goals and can support composite workflows. By focusing on goal-driven interactions, our system serves a more proactive role, facilitating mixed-initiative dialogue and improving task completion. Equipped with components for natural language understanding, composite goal retriever, dialogue management, and response generation, backed by a well-organized data service with domain knowledge base and retrieval engine, HierTOD delivers efficient task assistance. Furthermore, our system implementation unifies two TOD paradigms: slot-filling for information collection and step-by-step guidance for task execution. Our human study demonstrates the effectiveness and helpfulness of HierTOD in performing both paradigms.
Large Language Models (LLMs) excel in data synthesis but can be inaccurate in domain-specific tasks, which retrieval-augmented generation (RAG) systems address by leveraging user-provided data. However, RAGs require optimization in both retrieval and generation stages, which can affect output quality. In this paper, we present LLM-Ref, a writing assistant tool that aids researchers in writing articles from multiple source documents with enhanced reference synthesis and handling capabilities. Unlike traditional RAG systems that use chunking and indexing, our tool retrieves and generates content directly from text paragraphs. This method facilitates direct reference extraction from the generated outputs, a feature unique to our tool. Additionally, our tool employs iterative response generation, effectively managing lengthy contexts within the language model's constraints. Compared to baseline RAG-based systems, our approach achieves a $3.25\times$ to $6.26\times$ increase in Ragas score, a comprehensive metric that provides a holistic view of a RAG system's ability to produce accurate, relevant, and contextually appropriate responses. This improvement shows our method enhances the accuracy and contextual relevance of writing assistance tools.
Research has shown the effectiveness of reasoning (e.g., Chain-of-Thought), planning (e.g., SelfAsk), and retrieval augmented generation strategies to improve the performance of Large Language Models (LLMs) on various tasks, such as question answering. However, using a single fixed strategy to answer different kinds of questions is suboptimal in performance and inefficient in terms of generated output tokens and performed retrievals. In our work, we propose a novel technique DyPlan, to induce a dynamic strategy selection process in LLMs, to improve performance and reduce costs in question-answering. DyPlan incorporates an initial decision step to select the most suitable strategy conditioned on the input question and guides the LLM's response generation accordingly. We extend DyPlan to DyPlan-verify, adding an internal verification and correction process to further enrich the generated answer. Experiments on three prominent multi-hop question answering (MHQA) datasets reveal how DyPlan can improve model performance by 7-13% while reducing the cost by 11-32% relative to the best baseline model.
Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on single-turn RAG, leaving a significant gap in addressing the complexities of multi-turn conversations found in real-world applications. To bridge this gap, we introduce CORAL, a large-scale benchmark designed to assess RAG systems in realistic multi-turn conversational settings. CORAL includes diverse information-seeking conversations automatically derived from Wikipedia and tackles key challenges such as open-domain coverage, knowledge intensity, free-form responses, and topic shifts. It supports three core tasks of conversational RAG: passage retrieval, response generation, and citation labeling. We propose a unified framework to standardize various conversational RAG methods and conduct a comprehensive evaluation of these methods on CORAL, demonstrating substantial opportunities for improving existing approaches.
As LLMs exhibit a high degree of human-like capability, increasing attention has been paid to role-playing research areas in which responses generated by LLMs are expected to mimic human replies. This has promoted the exploration of role-playing agents in various applications, such as chatbots that can engage in natural conversations with users and virtual assistants that can provide personalized support and guidance. The crucial factor in the role-playing task is the effective utilization of character memory, which stores characters' profiles, experiences, and historical dialogues. Retrieval Augmented Generation (RAG) technology is used to access the related memory to enhance the response generation of role-playing agents. Most existing studies retrieve related information based on the semantic similarity of memory to maintain characters' personalized traits, and few attempts have been made to incorporate the emotional factor in the retrieval argument generation (RAG) of LLMs. Inspired by the Mood-Dependent Memory theory, which indicates that people recall an event better if they somehow reinstate during recall the original emotion they experienced during learning, we propose a novel emotion-aware memory retrieval framework, termed Emotional RAG, which recalls the related memory with consideration of emotional state in role-playing agents. Specifically, we design two kinds of retrieval strategies, i.e., combination strategy and sequential strategy, to incorporate both memory semantic and emotional states during the retrieval process. Extensive experiments on three representative role-playing datasets demonstrate that our Emotional RAG framework outperforms the method without considering the emotional factor in maintaining the personalities of role-playing agents. This provides evidence to further reinforce the Mood-Dependent Memory theory in psychology.
Information-seeking dialogues span a wide range of questions, from simple factoid to complex queries that require exploring multiple facets and viewpoints. When performing exploratory searches in unfamiliar domains, users may lack background knowledge and struggle to verify the system-provided information, making them vulnerable to misinformation. We investigate the limitations of response generation in conversational information-seeking systems, highlighting potential inaccuracies, pitfalls, and biases in the responses. The study addresses the problem of query answerability and the challenge of response incompleteness. Our user studies explore how these issues impact user experience, focusing on users' ability to identify biased, incorrect, or incomplete responses. We design two crowdsourcing tasks to assess user experience with different system response variants, highlighting critical issues to be addressed in future conversational information-seeking research. Our analysis reveals that it is easier for users to detect response incompleteness than query answerability and user satisfaction is mostly associated with response diversity, not factual correctness.
With the advancement of chatbots and the growing demand for automatic depression detection, identifying depression in patient conversations has gained more attention. However, prior methods often assess depression in a binary way or only a single score without diverse feedback and lack focus on enhancing dialogue responses. In this paper, we present a novel task of multi-aspect depression severity assessment via an inductive dialogue system (MaDSA), evaluating a patient's depression level on multiple criteria by incorporating an assessment-aided response generation. Further, we propose a foundational system for MaDSA, which induces psychological dialogue responses with an auxiliary emotion classification task within a hierarchical severity assessment structure. We synthesize the conversational dataset annotated with eight aspects of depression severity alongside emotion labels, proven robust via human evaluations. Experimental results show potential for our preliminary work on MaDSA.
With the resurgent interest in building open-domain dialogue systems, the dialogue generation task has attracted increasing attention over the past few years. This task is usually formulated as a conditional generation problem, which aims to generate a natural and meaningful response given dialogue contexts and specific constraints, such as persona. And maintaining a consistent persona is essential for the dialogue systems to gain trust from the users. Although tremendous advancements have been brought, traditional persona-based dialogue models are typically trained by leveraging a large number of persona-dense dialogue examples. Yet, such persona-dense training data are expensive to obtain, leading to a limited scale. This work presents a novel approach to learning from limited training examples by regarding consistency understanding as a regularization of response generation. To this end, we propose a novel stack-propagation framework for learning a generation and understanding pipeline.Specifically, the framework stacks a Transformer encoder and two Transformer decoders, where the first decoder models response generation and the second serves as a regularizer and jointly models response generation and consistency understanding. The proposed framework can benefit from the stacked encoder and decoders to learn from much smaller personalized dialogue data while maintaining competitive performance. Under different low-resource settings, subjective and objective evaluations prove that the stack-propagation framework outperforms strong baselines in response quality and persona consistency and largely overcomes the shortcomings of traditional models that rely heavily on the persona-dense dialogue data.
With the rapidly increasing complexity of modern chips, hardware engineers are required to invest more effort in tasks such as circuit design, verification, and physical implementation. These workflows often involve continuous modifications, which are labor-intensive and prone to errors. Therefore, there is an increasing need for more efficient and cost-effective Electronic Design Automation (EDA) solutions to accelerate new hardware development. Recently, large language models (LLMs) have made significant advancements in contextual understanding, logical reasoning, and response generation. Since hardware designs and intermediate scripts can be expressed in text format, it is reasonable to explore whether integrating LLMs into EDA could simplify and fully automate the entire workflow. Accordingly, this paper discusses such possibilities in several aspects, covering hardware description language (HDL) generation, code debugging, design verification, and physical implementation. Two case studies, along with their future outlook, are introduced to highlight the capabilities of LLMs in code repair and testbench generation. Finally, future directions and challenges are highlighted to further explore the potential of LLMs in shaping the next-generation EDA
Generative retrieval for search and recommendation is a promising paradigm for retrieving items, offering an alternative to traditional methods that depend on external indexes and nearest-neighbor searches. Instead, generative models directly associate inputs with item IDs. Given the breakthroughs of Large Language Models (LLMs), these generative systems can play a crucial role in centralizing a variety of Information Retrieval (IR) tasks in a single model that performs tasks such as query understanding, retrieval, recommendation, explanation, re-ranking, and response generation. Despite the growing interest in such a unified generative approach for IR systems, the advantages of using a single, multi-task model over multiple specialized models are not well established in the literature. This paper investigates whether and when such a unified approach can outperform task-specific models in the IR tasks of search and recommendation, broadly co-existing in multiple industrial online platforms, such as Spotify, YouTube, and Netflix. Previous work shows that (1) the latent representations of items learned by generative recommenders are biased towards popularity, and (2) content-based and collaborative-filtering-based information can improve an item's representations. Motivated by this, our study is guided by two hypotheses: [H1] the joint training regularizes the estimation of each item's popularity, and [H2] the joint training regularizes the item's latent representations, where search captures content-based aspects of an item and recommendation captures collaborative-filtering aspects. Our extensive experiments with both simulated and real-world data support both [H1] and [H2] as key contributors to the effectiveness improvements observed in the unified search and recommendation generative models over the single-task approaches.
Document-grounded dialogue (DGD) uses documents as external knowledge for dialogue generation. Correctly understanding the dialogue context is crucial for selecting knowledge from the document and generating proper responses. In this paper, we propose using a dialogue policy to help the dialogue understanding in DGD. Our dialogue policy consists of two kinds of guiding signals: utterance function and topic transfer intent. The utterance function reflects the purpose and style of an utterance, and the topic transfer intent reflects the topic and content of an utterance. We propose a novel framework exploiting our dialogue policy for two core tasks in DGD, namely knowledge selection (KS) and response generation (RG). The framework consists of two modules: the Policy planner leverages policy-aware dialogue representation to select knowledge and predict the policy of the response; the generator uses policy/knowledge-aware dialogue representation for response generation. Our policy-driven model gets state-of-the-art performance on three public benchmarks and we provide a detailed analysis of the experimental results. Our code/data will be released on GitHub.
As a cornerstone of modern information access, search engines have become indispensable in everyday life. With the rapid advancements in AI and natural language processing (NLP) technologies, particularly large language models (LLMs), search engines have evolved to support more intuitive and intelligent interactions between users and systems. Conversational search, an emerging paradigm for next-generation search engines, leverages natural language dialogue to facilitate complex and precise information retrieval, thus attracting significant attention. Unlike traditional keyword-based search engines, conversational search systems enhance user experience by supporting intricate queries, maintaining context over multi-turn interactions, and providing robust information integration and processing capabilities. Key components such as query reformulation, search clarification, conversational retrieval, and response generation work in unison to enable these sophisticated interactions. In this survey, we explore the recent advancements and potential future directions in conversational search, examining the critical modules that constitute a conversational search system. We highlight the integration of LLMs in enhancing these systems and discuss the challenges and opportunities that lie ahead in this dynamic field. Additionally, we provide insights into real-world applications and robust evaluations of current conversational search systems, aiming to guide future research and development in conversational search.
This paper presents an experience report on the development of Retrieval Augmented Generation (RAG) systems using PDF documents as the primary data source. The RAG architecture combines generative capabilities of Large Language Models (LLMs) with the precision of information retrieval. This approach has the potential to redefine how we interact with and augment both structured and unstructured knowledge in generative models to enhance transparency, accuracy, and contextuality of responses. The paper details the end-to-end pipeline, from data collection, preprocessing, to retrieval indexing and response generation, highlighting technical challenges and practical solutions. We aim to offer insights to researchers and practitioners developing similar systems using two distinct approaches: OpenAI's Assistant API with GPT Series and Llama's open-source models. The practical implications of this research lie in enhancing the reliability of generative AI systems in various sectors where domain-specific knowledge and real-time information retrieval is important. The Python code used in this work is also available at: https://github.com/GPT-Laboratory/RAG-LLM-Development-Guidebook-from-PDFs.
LLMs are frequently used tools for conversational generation. Without additional information LLMs can generate lower quality responses due to lacking relevant content and hallucinations, as well as the perception of poor emotional capability, and an inability to maintain a consistent character. Knowledge graphs are commonly used forms of external knowledge and may provide solutions to these challenges. This paper introduces three proposals, utilizing knowledge graphs to enhance LLM generation. Firstly, dynamic knowledge graph embeddings and recommendation could allow for the integration of new information and the selection of relevant knowledge for response generation. Secondly, storing entities with emotional values as additional features may provide knowledge that is better emotionally aligned with the user input. Thirdly, integrating character information through narrative bubbles would maintain character consistency, as well as introducing a structure that would readily incorporate new information.
Retrieval-augmented generation (RAG) has become integral to large language models (LLMs), particularly for conversational AI systems where user questions may reference knowledge beyond the LLMs' training cutoff. However, many natural user questions lack well-defined answers, either due to limited domain knowledge or because the retrieval system returns documents that are relevant in appearance but uninformative in content. In such cases, LLMs often produce hallucinated answers without flagging them. While recent work has largely focused on questions with false premises, we study out-of-scope questions, where the retrieved document appears semantically similar to the question but lacks the necessary information to answer it. In this paper, we propose a guided hallucination-based approach ELOQ to automatically generate a diverse set of out-of-scope questions from post-cutoff documents, followed by human verification to ensure quality. We use this dataset to evaluate several LLMs on their ability to detect out-of-scope questions and generate appropriate responses. Finally, we introduce an improved detection method that enhances the reliability of LLM-based question-answering systems in handling out-of-scope questions.