Related papers: InfoQuest: Evaluating Multi-Turn Dialogue Agents f…
Simulating user interactions enables a more user-oriented evaluation of information retrieval (IR) systems. While user simulations are cost-efficient and reproducible, many approaches often lack fidelity regarding real user behavior. Most…
Most popular goal-oriented dialogue agents are capable of understanding the conversational context. However, with the surge of virtual assistants with screen, the next generation of agents are required to also understand screen context in…
Ambiguity resolution is key to effective communication. While humans effortlessly address ambiguity through conversational grounding strategies, the extent to which current language models can emulate these strategies remains unclear. In…
User queries are often underspecified and may admit multiple valid interpretations. Rather than silently making assumptions about the user's intent, a helpful assistant should surface such ambiguity by asking a clarifying question. Doing so…
Large Language Models (LLMs)-based agents have made impressive progress in reasoning and tool use, enabling them to solve complex tasks. However, their ability to proactively collaborate with users, especially when goals are vague,…
Collection of annotated dialogs for training task-oriented dialog systems have been one of the key bottlenecks in improving current models. While dialog response generation has been widely studied on the agent side, it is not evident if…
The increasing reliance on digital information necessitates advancements in conversational search systems, particularly in terms of information transparency. While prior research in conversational information-seeking has concentrated on…
Many real-world open-domain conversation applications have specific goals to achieve during open-ended chats, such as recommendation, psychotherapy, education, etc. We study the problem of imposing conversational goals on open-domain chat…
Natural language reasoning plays an increasingly important role in improving language models' ability to solve complex language understanding tasks. An interesting use case for reasoning is the resolution of context-dependent ambiguity. But…
Open domain question answering systems frequently rely on information retrieved from large collections of text (such as the Web) to answer questions. However, such collections of text often contain conflicting information, and…
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…
Understanding user intent is essential for effective planning in conversational assistants, particularly those powered by large language models (LLMs) coordinating multiple agents. However, real-world dialogues are often ambiguous,…
Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their decisions to human counterparts; however, their behavior is…
Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…
As large-scale models evolve, language instructions are increasingly utilized in multi-modal tasks. Due to human language habits, these instructions often contain ambiguities in real-world scenarios, necessitating the integration of visual…
The era of Large Language Models (LLMs) presents a new opportunity for interpretability--agentic interpretability: a multi-turn conversation with an LLM wherein the LLM proactively assists human understanding by developing and leveraging a…
Tool-calling is essential for Large Language Model (LLM) agents to complete real-world tasks. While most existing benchmarks assume simple, perfectly documented tools, real-world tools (e.g., general "search" APIs) are often opaque, lacking…
While confidence estimation is a promising direction for mitigating hallucinations in Large Language Models (LLMs), current research overwhelmingly focuses on single-turn settings. The dynamics of model confidence in multi-turn…
We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…
As one promising way to inquire about any particular information through a dialog with the bot, question answering dialog systems have gained increasing research interests recently. Designing interactive QA systems has always been a…