Artificial Intelligence (cs.AI)

Abstract: Despite advancements in LLMs, knowledge-based reasoning remains a longstanding issue due to the fragility of knowledge recall and inference. Existing methods primarily encourage LLMs to autonomously plan and solve problems or to extensively sample reasoning chains without addressing the conceptual and inferential fallacies. Attempting to alleviate inferential fallacies and drawing inspiration from multi-agent collaboration, we present a framework to increase faithfulness and causality for knowledge-based reasoning. Specifically, we propose to employ multiple intelligent agents (i.e., reasoner and causal evaluator) to work collaboratively in a reasoning-and-consensus paradigm for elevated reasoning faithfulness. The reasoners focus on providing solutions with human-like causality to solve open-domain problems. On the other hand, the causal evaluator agent scrutinizes if the answer in a solution is causally deducible from the question and vice versa, with a counterfactual answer replacing the original. According to the extensive and comprehensive evaluations on a variety of knowledge reasoning tasks (e.g., science question answering and commonsense reasoning), our framework outperforms all compared state-of-the-art approaches by large margins.

Abstract: Big models, exemplified by Large Language Models (LLMs), are models typically pre-trained on massive data and comprised of enormous parameters, which not only obtain significantly improved performance across diverse tasks but also present emergent capabilities absent in smaller models. However, the growing intertwining of big models with everyday human lives poses potential risks and might cause serious social harm. Therefore, many efforts have been made to align LLMs with humans to make them better follow user instructions and satisfy human preferences. Nevertheless, `what to align with' has not been fully discussed, and inappropriate alignment goals might even backfire. In this paper, we conduct a comprehensive survey of different alignment goals in existing work and trace their evolution paths to help identify the most essential goal. Particularly, we investigate related works from two perspectives: the definition of alignment goals and alignment evaluation. Our analysis encompasses three distinct levels of alignment goals and reveals a goal transformation from fundamental abilities to value orientation, indicating the potential of intrinsic human values as the alignment goal for enhanced LLMs. Based on such results, we further discuss the challenges of achieving such intrinsic value alignment and provide a collection of available resources for future research on the alignment of big models.