Improving Dialog Safety using Socially Aware Contrastive Learning
The paper discusses the potential risks of conversational AI systems generating unsafe, toxic, or unethical content. Previous…
SA-MDKIF: A Scalable and Adaptable Medical Domain Knowledge Injection Framework for Large Language Models
The article presents SA-MDKIF, a scalable and adaptable framework designed to inject medical domain knowledge into Large…
Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
The paper introduces ‘Superfiltering’, a method for data filtering in instruction tuning of Large Language Models (LLMs)….
A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains
The article presents REVEAL, a new dataset for benchmarking automatic verifiers of complex reasoning chains in language…
Actor Identification in Discourse: A Challenge for LLMs?
This research paper focuses on the identification of political actors who make claims in public debates, an…
Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases
This research focuses on Speech-to-Text Translation (S2TT), comparing traditional cascade systems with direct translation systems. The authors…
Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning
This paper presents a study on improving Weak-to-Strong Generalization (W2SG) under the framework of superalignment, a concept…
Non-Exchangeable Conformal Language Generation with Nearest Neighbors
The paper introduces a new method for text generation termed as non-exchangeable conformal nucleus sampling. This method…
Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders
This article discusses a novel model, T5VQVAE, which improves semantic control and generation in Transformer-based Variational AutoEncoders…
Transforming and Combining Rewards for Aligning Large Language Models
The study examines two problems in aligning language models to human preferences using reward models. Firstly, it…