works on

From the 1 of 46 linked papers with an AI index.

activity
20242026
collaborators

46 papers

cs.CL2026

Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does

Xinyi Liu, Hooshang Nayyeri, Dilek Hakkani-Tur +6

Prosodic cues can convey task-relevant information that alters the trajectory and outcome of a task-oriented dialogue, even when the words themselves remain unchanged. Yet existing…

cs.CL2026

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems

Vira Kasprova, Amruta Parulekar, Abdulrahman AlRabah +5

The paper investigates how informing language model agents about each other's tendency to agree with users (sycophancy) can reduce error cascades in multi‑agent discussions and boo…

cs.MA2026

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…

cs.SD2026

Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?

Yurii Halychanskyi, Nimet Beyza Bozdag, Mark Hasegawa-Johnson +2

Synthetic accented speech is a promising way to improve automatic speech recognition (ASR) when real accented recordings are scarce. We ask what makes such data useful for ASR fine…

cs.AI2026

PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

Jiayu Liu, Qihan Lin, Cheng Qian +8

LLM agents increasingly operate in large tool ecosystems, where real-world tasks require discovering relevant tools, inferring implicit sub-goals, and adapting to dynamic environme…

cs.CL2026

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…