565 citations · 1.1k across the 33 of their papers we have counts for
35 papers
Voxtral TTS
Mistral-AI, :, Alexander H. Liu +186
We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid…
Voxtral Realtime
Mistral-AI, :, Alexander H. Liu +166
We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adap…
Ministral 3
Alexander H. Liu, Kartik Khandelwal, Sandeep Subramanian +116
We introduce the Ministral 3 series, a family of parameter-efficient dense language models designed for compute and memory constrained applications, available in three model sizes:…
Devstral: Fine-tuning Language Models for Coding Agent Applications
Abhinav Rastogi, Adam Yang, Albert Q. Jiang +100
We introduce Devstral-Small, a lightweight open source model for code agents with the best performance among models below 100B size. In this technical report, we give an overview o…
Voxtral
Alexander H. Liu, Andy Ehrenberg, Andy Lo +103
We present Voxtral Mini and Voxtral Small, two multimodal audio chat models. Voxtral is trained to comprehend both spoken audio and text documents, achieving state-of-the-art perfo…
Robust Multi-Objective Preference Alignment with Online DPO
Raghav Gupta, Ryan Sullivan, Yunxuan Li +2
Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, o…
MoDE: Effective Multi-task Parameter Efficient Fine-Tuning with a Mixture of Dyadic Experts
Lin Ning, Harsh Lara, Meiqi Guo +1
Parameter-efficient fine-tuning techniques like Low-Rank Adaptation (LoRA) have revolutionized the adaptation of large language models (LLMs) to diverse tasks. Recent efforts have…
Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance
Kaitlyn Zhou, Jena D. Hwang, Xiang Ren +3
The ability to communicate uncertainty, risk, and limitation is crucial for the safety of large language models. However, current evaluations of these abilities rely on simple cali…
Improve Mathematical Reasoning in Language Models by Automated Process Supervision
Liangchen Luo, Yinxiao Liu, Rosanne Liu +9
Complex multi-step reasoning tasks, such as solving mathematical problems or generating code, remain a significant hurdle for even the most advanced large language models (LLMs). V…
Granular Change Accuracy: A More Accurate Performance Metric for Dialogue State Tracking
Taha Aksu, Nancy F. Chen
Current metrics for evaluating Dialogue State Tracking (DST) systems exhibit three primary limitations. They: i) erroneously presume a uniform distribution of slots throughout the…
Parameter Efficient Reinforcement Learning from Human Feedback
Hakim Sidahmed, Samrat Phatale, Alex Hutcheson +16
While Reinforcement Learning from Human Feedback (RLHF) effectively aligns pretrained Large Language and Vision-Language Models (LLMs, and VLMs) with human preferences, its computa…
RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Harrison Lee, Samrat Phatale, Hassan Mansoor +8
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but gathering high-quality preference labels…
Conversational Recommendation as Retrieval: A Simple, Strong Baseline
Raghav Gupta, Renat Aksitov, Samrat Phatale +3
Conversational recommendation systems (CRS) aim to recommend suitable items to users through natural language conversation. However, most CRS approaches do not effectively utilize…
Speech Aware Dialog System Technology Challenge (DSTC11)
Hagen Soltau, Izhak Shafran, Mingqiu Wang +6
Most research on task oriented dialog modeling is based on written text input. However, users interact with practical dialog systems often using speech as input. Typically, systems…
AnyTOD: A Programmable Task-Oriented Dialog System
Jeffrey Zhao, Yuan Cao, Raghav Gupta +6
We propose AnyTOD, an end-to-end, zero-shot task-oriented dialog (TOD) system capable of handling unseen tasks without task-specific training. We view TOD as a program executed by…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue
Raghav Gupta, Harrison Lee, Jeffrey Zhao +3
Building universal dialogue systems that operate across multiple domains/APIs and generalize to new ones with minimal overhead is a critical challenge. Recent works have leveraged…
Description-Driven Task-Oriented Dialog Modeling
Jeffrey Zhao, Raghav Gupta, Yuan Cao +6
Task-oriented dialogue (TOD) systems are required to identify key information from conversations for the completion of given tasks. Such information is conventionally specified in…
A Unified Approach to Entity-Centric Context Tracking in Social Conversations
Ulrich Rückert, Srinivas Sunkara, Abhinav Rastogi +2
In human-human conversations, Context Tracking deals with identifying important entities and keeping track of their properties and relationships. This is a challenging problem that…
SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems
Harrison Lee, Raghav Gupta, Abhinav Rastogi +3
Zero/few-shot transfer to unseen services is a critical challenge in task-oriented dialogue research. The Schema-Guided Dialogue (SGD) dataset introduced a paradigm for enabling mo…
UIBert: Learning Generic Multimodal Representations for UI Understanding
Chongyang Bai, Xiaoxue Zang, Ying Xu +4
To improve the accessibility of smart devices and to simplify their usage, building models which understand user interfaces (UIs) and assist users to complete their tasks is critic…
Overview of the Ninth Dialog System Technology Challenge: DSTC9
Chulaka Gunasekara, Seokhwan Kim, Luis Fernando D'Haro +36
This paper introduces the Ninth Dialog System Technology Challenge (DSTC-9). This edition of the DSTC focuses on applying end-to-end dialog technologies for four distinct tasks in…
MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines
Xiaoxue Zang, Abhinav Rastogi, Srinivas Sunkara +3
MultiWOZ is a well-known task-oriented dialogue dataset containing over 10,000 annotated dialogues spanning 8 domains. It is extensively used as a benchmark for dialogue state trac…
Text-to-Text Pre-Training for Data-to-Text Tasks
Mihir Kale, Abhinav Rastogi
We study the pre-train + fine-tune strategy for data-to-text tasks. Our experiments indicate that text-to-text pre-training in the form of T5, enables simple, end-to-end transforme…