133 citations · 316 across the 39 of their papers we have counts for
43 papers
Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness
Pardis Sadat Zahraei, Janvijay Singh, Gokhan Tur +1
Large language models are characterized by three key properties: capability, alignment, and faithfulness. Prior work studies the tradeoffs between capability and alignment, and bet…
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
Xiaocheng Yang, Abdulrahman Alrabah, Dilek Hakkani-Tür +1
Multi-agent systems (MAS) built on large language models (LLMs) provide a promising framework for solving complex tasks through role specialization and structured interaction. Howe…
ReIn: Conversational Error Recovery with Reasoning Inception
Takyoung Kim, Jinseok Nam, Chandrayee Basu +5
Conversational agents powered by large language models (LLMs) with tool integration achieve strong performance on fixed task-oriented dialogue datasets but remain vulnerable to una…
ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems
Yifei Zhang, Hooshang Nayyeri, Rinat Khaziev +5
Agentic task-oriented dialogue (TOD) requires systems to track concurrent goals, dependencies, and long-horizon state. We examine goal-lifecycle recovery from fixed dialogue trajec…
Current Agents Fail to Leverage World Model as Tool for Foresight
Cheng Qian, Emre Can Acikgoz, Bingxuan Li +8
Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer…
SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
Emre Can Acikgoz, Jinoh Oh, Jie Hao +7
Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providi…
MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations
Emre Can Acikgoz, Jinoh Oh, Joo Hyuk Jeon +7
Conversational agents often encounter ambiguous user requests, requiring an effective clarification to successfully complete tasks. While recent advancements in real-world applicat…
Self-Improving LLM Agents at Test-Time
Emre Can Acikgoz, Cheng Qian, Heng Ji +2
One paradigm of language model (LM) fine-tuning relies on creating large training datasets, under the assumption that high quantity and diversity will enable models to generalize t…
The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs
Pardis Sadat Zahraei, Gokhan Tur, Dilek Hakkani-Tür +1
What happens inside a language model when alignment training conflicts with a cultural value it encodes? Across 16 MENA countries, 26 models, and 1.53M human survey responses, we s…
Plan Verification for LLM-Based Embodied Task Completion Agents
Ananth Hariharan, Vardhan Dongre, Dilek Hakkani-Tür +1
Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors…
Goal Alignment in LLM-Based User Simulators for Conversational AI
Shuhaib Mehri, Xiaocheng Yang, Takyoung Kim +3
User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. While current Large Language Models (LLMs) ha…
MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations
Vardhan Dongre, Chi Gui, Shubham Garg +4
We introduce MIRAGE, a new benchmark for multimodal expert-level reasoning and decision-making in consultative interaction settings. Designed for the agriculture domain, MIRAGE cap…
Must Read: A Comprehensive Survey of Computational Persuasion
Nimet Beyza Bozdag, Shuhaib Mehri, Xiaocheng Yang +7
Persuasion is a fundamental aspect of communication, influencing decision-making across diverse contexts, from everyday conversations to high-stakes scenarios such as politics, mar…
AURA: A Diagnostic Framework for Tracking User Satisfaction of Interactive Planning Agents
Takyoung Kim, Janvijay Singh, Shuhaib Mehri +6
The growing capabilities of large language models (LLMs) in instruction-following and context-understanding lead to the era of agents with numerous applications. Among these, task…
ToolRL: Reward is All Tool Learning Needs
Cheng Qian, Emre Can Acikgoz, Qi He +5
Current Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities. However, SFT struggles to generalize to unfamiliar or complex tool…
A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions
Emre Can Acikgoz, Cheng Qian, Hongru Wang +5
Recent advances in Large Language Models (LLMs) have propelled conversational AI from traditional dialogue systems into sophisticated agents capable of autonomous actions, contextu…
YourBench: Easy Custom Evaluation Sets for Everyone
Sumuk Shashidhar, Clémentine Fourrier, Alina Lozovskia +3
Evaluating large language models (LLMs) effectively remains a critical bottleneck, as traditional static benchmarks suffer from saturation and contamination, while human evaluation…
TD-EVAL: Revisiting Task-Oriented Dialogue Evaluation by Combining Turn-Level Precision with Dialogue-Level Comparisons
Emre Can Acikgoz, Carl Guo, Suvodip Dey +4
Task-oriented dialogue (TOD) systems are experiencing a revolution driven by Large Language Models (LLMs), yet the evaluation methodologies for these systems remain insufficient fo…
Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models
Nimet Beyza Bozdag, Shuhaib Mehri, Gokhan Tur +1
Large Language Models (LLMs) demonstrate persuasive capabilities that rival human-level persuasion. While these capabilities can be used for social good, they also present risks of…
Can a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language Model
Emre Can Acikgoz, Jeremiah Greer, Akul Datta +6
Large Language Models (LLMs) with API-calling capabilities enabled building effective Language Agents (LA), while also revolutionizing the conventional task-oriented dialogue (TOD)…
SMART: Self-Aware Agent for Tool Overuse Mitigation
Cheng Qian, Emre Can Acikgoz, Hongru Wang +5
Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness, failing to balance these approaches effectively. Th…
Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems
Mert İnan, Anthony Sicilia, Suvodip Dey +6
While theories of discourse and cognitive science have long recognized the value of unhurried pacing, recent dialogue research tends to minimize friction in conversational systems.…
Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling
Suvodip Dey, Yi-Jyun Sun, Gokhan Tur +1
Recent LLMs have enabled significant advancements for conversational agents. However, they are also well known to hallucinate, producing responses that seem plausible but are factu…
Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems
Taaha Kazi, Ruiliang Lyu, Sizhe Zhou +2
Traditionally, offline datasets have been used to evaluate task-oriented dialogue (TOD) models. These datasets lack context awareness, making them suboptimal benchmarks for convers…