Search Results for author: Dilek Hakkani-Tür

Found 20 papers, 4 papers with code

Can a Single Model Master Both Multi-turn Conversations and Tool Use? CALM: A Unified Conversational Agentic Language Model

no code implementations12 Feb 2025 Emre Can Acikgoz, Jeremiah Greer, Akul Datta, Ze Yang, William Zeng, Oussama Elachqar, Emmanouil Koukoumidis, Dilek Hakkani-Tür, Gokhan Tur

Large Language Models (LLMs) with API-calling capabilities enabled building effective Language Agents (LA), while also revolutionizing the conventional task-oriented dialogue (TOD) paradigm.

Language Modeling Language Modelling +1

Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis

1 code implementation6 Feb 2025 Shuhaib Mehri, Xiusi Chen, Heng Ji, Dilek Hakkani-Tür

LLMs demonstrate remarkable capabilities in following natural language instructions, largely due to instruction-tuning on high-quality datasets.

Synthetic Data Generation

Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems

no code implementations28 Jan 2025 Mert İnan, Anthony Sicilia, Suvodip Dey, Vardhan Dongre, Tejas Srinivasan, Jesse Thomason, Gökhan Tür, Dilek Hakkani-Tür, Malihe Alikhani

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.

Decision Making Friction

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language

no code implementations23 Jan 2025 Yubin Ge, Neeraja Kirtane, Hao Peng, Dilek Hakkani-Tür

Various jailbreaking techniques have been developed to expose the vulnerabilities of these models and improve their safety.

Persuasiveness

ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents

no code implementations1 Nov 2024 Vardhan Dongre, Xiaocheng Yang, Emre Can Acikgoz, Suvodip Dey, Gokhan Tur, Dilek Hakkani-Tür

However, current frameworks do not enable these agents to work with users and interact with them to align on the details of their tasks and reach user-defined goals; instead, in ambiguous situations, these agents may make decisions based on assumptions.

Decision Making Language Modeling +2

Simulating User Agents for Embodied Conversational-AI

no code implementations31 Oct 2024 Daniel Philipov, Vardhan Dongre, Gokhan Tur, Dilek Hakkani-Tür

Such a user agent assists in improving the scalability and efficiency of embodied dialogues dataset generation and is critical for enhancing and evaluating the robot's interaction and task completion ability, as well as for research in reinforcement learning using AI feedback.

Dataset Generation Large Language Model

Unsupervised Human Preference Learning

no code implementations30 Sep 2024 Sumuk Shashidhar, Abhinav Chinta, Vaibhav Sahai, Dilek Hakkani-Tür

By allowing foundation models to adapt to individual preferences in a data and compute-efficient manner, our approach paves the way for highly personalized language model applications.

In-Context Learning Language Modeling +2

KILM: Knowledge Injection into Encoder-Decoder Language Models

1 code implementation17 Feb 2023 Yan Xu, Mahdi Namazifar, Devamanyu Hazarika, Aishwarya Padmakumar, Yang Liu, Dilek Hakkani-Tür

Large pre-trained language models (PLMs) have been shown to retain implicit knowledge within their parameters.

Decoder Entity Disambiguation

Using In-Context Learning to Improve Dialogue Safety

no code implementations2 Feb 2023 Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Hakkani-Tür

For instance, using automatic evaluation, we find our best fine-tuned baseline only generates safe responses to unsafe dialogue contexts from DiaSafety 4. 04% more than our approach.

In-Context Learning Re-Ranking +1

Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems

no code implementations CL (ACL) 2022 Manaal Faruqui, Dilek Hakkani-Tür

As more users across the world are interacting with dialog agents in their daily life, there is a need for better speech understanding that calls for renewed attention to the dynamics between research in automatic speech recognition (ASR) and natural language understanding (NLU).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Zero-Shot Controlled Generation with Encoder-Decoder Transformers

no code implementations11 Jun 2021 Devamanyu Hazarika, Mahdi Namazifar, Dilek Hakkani-Tür

In this work, we propose novel approaches for controlling encoder-decoder transformer-based NLG models in zero-shot.

Decoder Document Summarization +2

VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator

1 code implementation Findings (ACL) 2022 Ayush Shrivastava, Karthik Gopalakrishnan, Yang Liu, Robinson Piramuthu, Gokhan Tür, Devi Parikh, Dilek Hakkani-Tür

Interactive robots navigating photo-realistic environments need to be trained to effectively leverage and handle the dynamic nature of dialogue in addition to the challenges underlying vision-and-language navigation (VLN).

Binary Classification Imitation Learning +3

Learning Question-Guided Video Representation for Multi-Turn Video Question Answering

no code implementations WS 2019 Guan-Lin Chao, Abhinav Rastogi, Semih Yavuz, Dilek Hakkani-Tür, Jindong Chen, Ian Lane

Understanding and conversing about dynamic scenes is one of the key capabilities of AI agents that navigate the environment and convey useful information to humans.

Navigate Question Answering +2

Towards Universal Dialogue Act Tagging for Task-Oriented Dialogues

no code implementations5 Jul 2019 Shachi Paul, Rahul Goel, Dilek Hakkani-Tür

In unsupervised learning experiments we achieve an F1 score of 54. 1% on system turns in human-human dialogues.

Task-Oriented Dialogue Systems

HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking

no code implementations1 Jul 2019 Rahul Goel, Shachi Paul, Dilek Hakkani-Tür

In this work, we analyze the performance of these two alternative dialogue state tracking methods, and present a hybrid approach (HyST) which learns the appropriate method for each slot type.

Dialogue State Tracking Multi-domain Dialogue State Tracking

Building a Conversational Agent Overnight with Dialogue Self-Play

3 code implementations15 Jan 2018 Pararth Shah, Dilek Hakkani-Tür, Gokhan Tür, Abhinav Rastogi, Ankur Bapna, Neha Nayak, Larry Heck

We propose Machines Talking To Machines (M2M), a framework combining automation and crowdsourcing to rapidly bootstrap end-to-end dialogue agents for goal-oriented dialogues in arbitrary domains.

Diversity

Cannot find the paper you are looking for? You can Submit a new open access paper.