6 accepted papers
Multi-domain reinforcement learning (RL) for large language models (LLMs) involves highly intricate reward surfaces, posing significant challenges in finding parameters that excel across all domains. Recent empirical studies have further highlighted conflicts among domains, where gains in one capabi…
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, but their high computational costs limit their widespread practical application. We argue that this inefficiency arises from the tight coupling of high-level cognitive planning (devising the solution s…
Message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. For a sampled mini-batch of target nodes, the message passing process is divided into two parts: message passing between nodes within the batch (MP-IB) and message passing from nodes outsi…
The multi-domain fine-tuning of large language models (LLMs) confronts a notorious trade-off among abilities across domains. Existing studies attribute this trade-off to the conflicts between samples rooted in inherent semantics. Recent approaches attempt to mitigate these conflicts through the empi…
The prevalent noise in the preference data unavoidably poses significant challenges to the preference alignment of large language models (LLMs). Existing efforts for this problem either marginally alleviate the impact of noise without noise reduction, or rely on external LLMs that incur substantial…
The message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. However, training GNNs on large-scale graphs suffers from the well-known neighbor explosion problem, i.e., the exponentially increasing dependencies of nodes with the number of message…