Applying RLAIF for Code Generation with API-usage in Lightweight LLMs
This paper was accepted at the Natural Language Reasoning and Structured Explanations workshop at ACL 2024.
Reinforcement Learning from AI Feedback (RLAIF) has demonstrated...
Revisiting Non-separable Binary Classification and its Applications in Anomaly Detection
The inability to linearly classify XOR has motivated much of deep learning. We revisit this age-old problem and show that linear classification of...
How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad
Can Transformers predict new syllogisms by composing established ones? More generally, what type of targets can be learned by such models from scratch?...
MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs
We introduce MIA-Bench, a new benchmark designed to evaluate multimodal large language models (MLLMs) on their ability to strictly adhere to complex instructions....
Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages
We study the problem of private vector mean estimation in the shuffle model of privacy where nnn users each have a unit vector...
Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection
Although Large Language Models (LLMs) have shown promise for human-like conversations, they are primarily pre-trained on text data. Incorporating audio or video improves...
International ACM Conference on Research and Development in Information Retrieval (SIGIR) 2024
International ACM Conference on Research and Development in Information Retrieval (SIGIR) 2024
Source link
Server-side Rescoring of Spoken Entity-centric Knowledge Queries for Virtual Assistants
On-device Virtual Assistants powered by Automated Speech Recognition (ASR) require effective knowledge integration for the challenging entity-rich query recognition.
In this paper, we conduct...
Hypernetworks for Personalizing ASR to Atypical Speech
*Equal Contributors
Parameter-efficient fine-tuning (PEFT) for personalizing automatic speech recognition (ASR) has recently shown promise for adapting general population models to atypical speech. However,...
Synthetic Query Generation using Large Language Models for Virtual Assistants
This paper was accepted in the Industry Track at SIGIR 2024.
Virtual Assistants (VAs) are important Information Retrieval platforms that help users accomplish various...
More News
How Star Wars: Zero Company Aims To Replicate The Gritty Wartime...
After an official reveal at Star Wars Celebration Japan, new details on Star Wars: Zero Company have been revealed. One of the interesting...