2 citations · 2 across the 16 of their papers we have counts for
17 papers
ChipMEM: Verification-Grounded Memory for EDA Agents
Abdulrahman AlRabah, Joshua Mabry, Dilek Hakkani-Tür +4
Large language model (LLM)-based agents use Electronic Design Automation (EDA) tools to generate and revise register-transfer-level (RTL) designs under synthesis and verification f…
Popular Knowledge Propagates More Errors in LLM Knowledge Updating
Yuji Zhang, Weibing Wang, Cheng Qian +5
Updating a language model's knowledge through fine-tuning is essential for keeping its outputs current, yet can also induce factual forgetting and new hallucinations. Prior work sh…
ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback
Tarik Can Ozden, Sachidanand VS, Furkan Horoz +4
Automatic academic paper-to-slide generation is inherently iterative, because creating an effective presentation requires repeated cycles of generation, critique, and revision. Rec…
Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
Nimet Beyza Bozdag, Emre Can Acikgoz, Gokhan Tur +1
Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increas…
PredActBench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise
Abdulrahman AlRabah, Xiaocheng Yang, Dilek Hakkani-Tür +1
Large language model (LLM) agents are increasingly used to support decisions by calling external tools. Existing work on LLM tool-calling assumes these tools are perfectly reliable…
Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation
Amruta Parulekar, Jinu Lee, Dilek Hakkani-Tür +1
Large Language Models (LLMs) reason in free-form chain-of-thought (CoT) without revealing which steps were well supported and which alternatives were rejected. In high-stakes domai…
Measuring, Localizing, and Reducing the AI-Like Writing Style of Post-Trained LLMs
Aniket Anand, Janvijay Singh, Zhewei Sun +2
Post-trained language models often exhibit a recognizable AI-like writing style, yet its connection to post-training and internal representations remains poorly understood. In this…
AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions
Ishika Agarwal, Sofia Stoica, Emre Can Acikgoz +4
Data quality remains a critical bottleneck in developing capable, competitive models. Researchers have explored many ways to generate top quality samples. Some works rely on reject…
Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors
Shuhaib Mehri, Philippe Laban, Sumuk Shashidhar +4
As user simulators are increasingly used for interactive training and evaluation of AI assistants, it is essential that they represent the diverse behaviors of real users. While ex…
Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
Vardhan Dongre, Dilek Hakkani-Tür
Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the w…
PSI-Bench: Interpretable and Clinically Meaningful Evaluation of Depression Patient Simulators
Nguyen Khoi Hoang, Shuhaib Mehri, Tse-An Hsu +4
Patient simulators are gaining traction in mental health training by providing scalable exposure to complex and sensitive patient interactions. Simulating depressed patients is cha…
User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction
Yuren Hao, Shuhaib Mehri, ChengXiang Zhai +1
Large language models are increasingly used as personal assistants, yet most lack a persistent user model, forcing users to repeatedly restate preferences across sessions. We propo…
A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality
Ishika Agarwal, Zhenlin He, Dhruva Patil +1
Non-compositional expressions (e.g., idioms, proverbs, and metaphors) pose significant challenges for neural machine translation systems because their meanings cannot be derived fr…
Do LLMs Encode Functional Importance of Reasoning Tokens?
Janvijay Singh, Dilek Hakkani-Tür
Large language models solve complex tasks by generating long reasoning chains, achieving higher accuracy at the cost of increased computational cost and reduced ability to isolate…
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…
Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis
Shuhaib Mehri, Xiusi Chen, Heng Ji +1
High-quality instruction-tuning data is crucial for developing Large Language Models (LLMs) that can effectively navigate real-world tasks and follow human instructions. While synt…
TEACh: Task-driven Embodied Agents that Chat
Aishwarya Padmakumar, Jesse Thomason, Ayush Shrivastava +6
Robots operating in human spaces must be able to engage in natural language interaction with people, both understanding and executing instructions, and using conversation to resolv…