Reasoning Elicitation in Language Models via Counterfactual Feedback
Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first derive novel metrics that balance accuracy in factual and counterfactual questions, capturing a more complete view of the reasoning abilities of language models than traditional factual-only based metrics. Second, we propose several fine-tuning approaches that aim to elicit better reasoning mechanisms, in the sense of the proposed metrics. Finally, we evaluate the performance of the fine-tuned language models in a variety of realistic scenarios. In particular, we investigate to what extent our fine-tuning approaches systemically achieve better generalization with respect to the base models in several problems that require, among others, inductive and deductive reasoning capabilities.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualQuestion AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Counterfactual Self-Questioning for Stable Policy Optimization in Language Models
Recent work on language model self-improvement shows that models can refine their own reasoning through reflection, verification, debate, or self-generated rewards. However, most existing approaches rely on external crit…
Mathematical ReasoningCounterfactual Collaborative Reasoning
Causal reasoning and logical reasoning are two important types of reasoning abilities for human intelligence. However, their relationship has not been extensively explored under machine intelligence context. In this pape…
counterfactualCounterfactual ReasoningData AugmentationLogical Reasoning+1Investigating the Robustness of Deductive Reasoning with Large Language Models
Large Language Models (LLMs) have been shown to achieve impressive results for many reasoning-based Natural Language Processing (NLP) tasks, suggesting a degree of deductive reasoning capability. However, it remains uncl…
counterfactualRules or Weights? Comparing User Understanding of Explainable AI Techniques with the Cognitive XAI-Adaptive Model
Rules and Weights are popular XAI techniques for explaining AI decisions. Yet, it remains unclear how to choose between them, lacking a cognitive framework to compare their interpretability. In an elicitation user study …
CausalARC: Abstract Reasoning with Causal World Models
On-the-fly reasoning often requires adaptation to novel problems under limited data and distribution shift. This work introduces CausalARC: an experimental testbed for AI reasoning in low-data and out-of-distribution reg…
Logical ReasoningProgram Synthesis