Plant in Cupboard, Orange on Table, Book on Shelf. Benchmarking Practical Reasoning and Situation Modelling in a Text-Simulated Situated Environment

Large language models (LLMs) have risen to prominence as 'chatbots' for users to interact via natural language. However, their abilities to capture common-sense knowledge make them seem promising as language-based planners of situated or embodied action as well. We have implemented a simple text-based environment -- similar to others that have before been used for reinforcement-learning of agents -- that simulates, very abstractly, a household setting. We use this environment and the detailed error-tracking capabilities we implemented for targeted benchmarking of LLMs on the problem of practical reasoning: Going from goals and observations to actions. Our findings show that environmental complexity and game restrictions hamper performance, and concise action planning is demanding for current LLMs.

Exploring Emotion-Sensitive LLM-Based Conversational AI

Conversational AI chatbots have become increasingly common within the customer service industry. Despite improvements in their emotional development, they often lack the authenticity of real customer service interactions or the competence of service providers. By comparing emotion-sensitive and emotion-insensitive LLM-based chatbots across 30 participants, we aim to explore how emotional sensitivity in chatbots influences perceived competence and overall customer satisfaction in service interactions. Additionally, we employ sentiment analysis techniques to analyze and interpret the emotional content of user inputs. We highlight that perceptions of chatbot trustworthiness and competence were higher in the case of the emotion-sensitive chatbot, even if issue resolution rates were not affected. We discuss implications of improved user satisfaction from emotion-sensitive chatbots and potential applications in support services.

A Novel Dialect-Aware Framework for the Classification of Arabic Dialects and Emotions

Arabic is one of the oldest languages still in use today. As a result, several Arabic-speaking regions have developed dialects that are unique to them. Dialect and emotion recognition have various uses in Arabic text analysis, such as determining an online customer's origin based on their comments. Furthermore, intelligent chatbots that are aware of a user's emotions can respond appropriately to the user. Current research in emotion detection in the Arabic language lacks awareness of how emotions are exhibited in different dialects, which motivates the work found in this study. This research addresses the problems of dialect and emotion classification in Arabic. Specifically, this is achieved by building a novel framework that can identify and predict Arabic dialects and emotions from a given text. The framework consists of three modules: A text-preprocessing module, a classification module, and a clustering module with the novel capability of building new dialect-aware emotion lexicons. The proposed framework generated a new emotional lexicon for different dialects. It achieved an accuracy of 88.9% in classifying Arabic dialects, which outperforms the state-of-the-art results by 6.45 percentage points. Furthermore, the framework achieved 89.1-79% accuracy in detecting emotions in the Egyptian and Gulf dialects, respectively.

Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

Large Language Models (LLMs) are increasingly used as chatbots, yet their ability to personalize responses to user preferences remains limited. We introduce PrefEval, a benchmark for evaluating LLMs' ability to infer, memorize and adhere to user preferences in a long-context conversational setting. PrefEval comprises 3,000 manually curated user preference and query pairs spanning 20 topics. PrefEval contains user personalization or preference information in both explicit and implicit forms, and evaluates LLM performance using a generation and a classification task. With PrefEval, we evaluated the aforementioned preference following capabilities of 10 open-source and proprietary LLMs in multi-session conversations with varying context lengths up to 100k tokens. We benchmark with various prompting, iterative feedback, and retrieval-augmented generation methods. Our benchmarking effort reveals that state-of-the-art LLMs face significant challenges in proactively following users' preferences during conversations. In particular, in zero-shot settings, preference following accuracy falls below 10% at merely 10 turns (~3k tokens) across most evaluated models. Even with advanced prompting and retrieval methods, preference following still deteriorates in long-context conversations. Furthermore, we show that fine-tuning on PrefEval significantly improves performance. We believe PrefEval serves as a valuable resource for measuring, understanding, and enhancing LLMs' preference following abilities, paving the way for personalized conversational agents. Our code and dataset are available at https://prefeval.github.io/.

Reliable Conversational Agents under ASP Control that Understand Natural Language

Efforts have been made to make machines converse like humans in the past few decades. The recent techniques of Large Language Models (LLMs) make it possible to have human-like conversations with machines, but LLM's flaws of lacking understanding and reliability are well documented. We believe that the best way to eliminate this problem is to use LLMs only as parsers to translate text to knowledge and vice versa and carry out the conversation by reasoning over this knowledge using the answer set programming. I have been developing a framework based on LLMs and ASP to realize reliable chatbots that "understand" human conversation. This framework has been used to develop task-specific chatbots as well as socialbots. My future research is focused on making these chatbots scalable and trainable.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has not been shown to pose a serious risk to users. Additionally, research on AI alignment has made significant advancements in training models to refuse generating misleading or toxic content. As a result, LLMs generally became honest and harmless. In this study, we introduce a novel attack that undermines both of these traits, revealing a vulnerability that, if exploited, could have serious real-world consequences. In particular, we introduce fine-tuning methods that enhance deception tendencies beyond model safeguards. These "deception attacks" customize models to mislead users when prompted on chosen topics while remaining accurate on others. Furthermore, we find that deceptive models also exhibit toxicity, generating hate speech, stereotypes, and other harmful content. Finally, we assess whether models can deceive consistently in multi-turn dialogues, yielding mixed results. Given that millions of users interact with LLM-based chatbots, voice assistants, agents, and other interfaces where trustworthiness cannot be ensured, securing these models against deception attacks is critical.

Grammar Control in Dialogue Response Generation for Language Learning Chatbots

Chatbots based on large language models offer cheap conversation practice opportunities for language learners. However, they are hard to control for linguistic forms that correspond to learners' current needs, such as grammar. We control grammar in chatbot conversation practice by grounding a dialogue response generation model in a pedagogical repository of grammar skills. We also explore how this control helps learners to produce specific grammar. We comprehensively evaluate prompting, fine-tuning, and decoding strategies for grammar-controlled dialogue response generation. Strategically decoding Llama3 outperforms GPT-3.5 when tolerating minor response quality losses. Our simulation predicts grammar-controlled responses to support grammar acquisition adapted to learner proficiency. Existing language learning chatbots and research on second language acquisition benefit from these affordances. Code available on GitHub.

Enhancing Higher Education with Generative AI: A Multimodal Approach for Personalised Learning

This research explores the opportunities of Generative AI (GenAI) in the realm of higher education through the design and development of a multimodal chatbot for an undergraduate course. Leveraging the ChatGPT API for nuanced text-based interactions and Google Bard for advanced image analysis and diagram-to-code conversions, we showcase the potential of GenAI in addressing a broad spectrum of educational queries. Additionally, the chatbot presents a file-based analyser designed for educators, offering deep insights into student feedback via sentiment and emotion analysis, and summarising course evaluations with key metrics. These combinations highlight the crucial role of multimodal conversational AI in enhancing teaching and learning processes, promising significant advancements in educational adaptability, engagement, and feedback analysis. By demonstrating a practical web application, this research underlines the imperative for integrating GenAI technologies to foster more dynamic and responsive educational environments, ultimately contributing to improved educational outcomes and pedagogical strategies.

GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing

Although Large Language Models (LLMs) succeed in human-guided conversations such as instruction following and question answering, the potential of LLM-guided conversations-where LLMs direct the discourse and steer the conversation's objectives-remains under-explored. In this study, we first characterize LLM-guided conversation into three fundamental components: (i) Goal Navigation; (ii) Context Management; (iii) Empathetic Engagement, and propose GuideLLM as an installation. We then implement an interviewing environment for the evaluation of LLM-guided conversation. Specifically, various topics are involved in this environment for comprehensive interviewing evaluation, resulting in around 1.4k turns of utterances, 184k tokens, and over 200 events mentioned during the interviewing for each chatbot evaluation. We compare GuideLLM with 6 state-of-the-art LLMs such as GPT-4o and Llama-3-70b-Instruct, from the perspective of interviewing quality, and autobiography generation quality. For automatic evaluation, we derive user proxies from multiple autobiographies and employ LLM-as-a-judge to score LLM behaviors. We further conduct a human-involved experiment by employing 45 human participants to chat with GuideLLM and baselines. We then collect human feedback, preferences, and ratings regarding the qualities of conversation and autobiography. Experimental results indicate that GuideLLM significantly outperforms baseline LLMs in automatic evaluation and achieves consistent leading performances in human ratings.

Generating Privacy-Preserving Personalized Advice with Zero-Knowledge Proofs and LLMs

Large language models (LLMs) are increasingly utilized in domains such as finance, healthcare, and interpersonal relationships to provide advice tailored to user traits and contexts. However, this personalization often relies on sensitive data, raising critical privacy concerns and necessitating data minimization. To address these challenges, we propose a framework that integrates zero-knowledge proof (ZKP) technology, specifically zkVM, with LLM-based chatbots. This integration enables privacy-preserving data sharing by verifying user traits without disclosing sensitive information. Our research introduces both an architecture and a prompting strategy for this approach. Through empirical evaluation, we clarify the current constraints and performance limitations of both zkVM and the proposed prompting strategy, thereby demonstrating their practical feasibility in real-world scenarios.