LLMs Struggle to Perform Counterfactual Reasoning with Parametric Knowledge

• URL: http://arxiv.org/abs/2506.15732v1
• Date: Sun, 15 Jun 2025 01:08:05 GMT
• Title: LLMs Struggle to Perform Counterfactual Reasoning with Parametric Knowledge
• Authors: Khurram Yamin, Gaurav Ghosal, Bryan Wilder,
• Abstract summary: Large Language Models contain extensive world knowledge in their parameters, enabling impressive performance on many knowledge intensive tasks.<n>However, when deployed in novel settings, LLMs often encounter situations where they must integrate parametric knowledge with new or unfamiliar information.<n>This work explores whether LLMs can combine knowledge in-context with their parametric knowledge through the lens of counterfactual reasoning.
• Score: 18.677808169753032
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models have been shown to contain extensive world knowledge in their parameters, enabling impressive performance on many knowledge intensive tasks. However, when deployed in novel settings, LLMs often encounter situations where they must integrate parametric knowledge with new or unfamiliar information. In this work, we explore whether LLMs can combine knowledge in-context with their parametric knowledge through the lens of counterfactual reasoning. Through synthetic and real experiments in multi-hop reasoning problems, we show that LLMs generally struggle with counterfactual reasoning, often resorting to exclusively using their parametric knowledge. Moreover, we show that simple post-hoc finetuning can struggle to instill counterfactual reasoning ability -- often leading to degradation in stored parametric knowledge. Ultimately, our work reveals important limitations of current LLM's abilities to re-purpose parametric knowledge in novel settings.

Related papers

• Evaluating the External and Parametric Knowledge Fusion of Large Language Models [72.40026897037814]
  We develop a systematic pipeline for data construction and knowledge infusion to simulate knowledge fusion scenarios. Our investigation reveals that enhancing parametric knowledge within LLMs can significantly bolster their capability for knowledge integration. Our findings aim to steer future explorations on harmonizing external and parametric knowledge within LLMs.
  arXiv  Detail & Related papers  (2024-05-29T11:48:27Z)
• Prompting Large Language Models with Knowledge Graphs for Question Answering Involving Long-tail Facts [50.06633829833144]
  Large Language Models (LLMs) are effective in performing various NLP tasks, but struggle to handle tasks that require extensive, real-world knowledge. We propose a benchmark that requires knowledge of long-tail facts for answering the involved questions. Our experiments show that LLMs alone struggle with answering these questions, especially when the long-tail level is high or rich knowledge is required.
  arXiv  Detail & Related papers  (2024-05-10T15:10:20Z)
• Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models [51.72963030032491]
  Knowledge documents for large language models (LLMs) may conflict with the memory of LLMs due to outdated or incorrect knowledge. We construct a new dataset, dubbed KNOT, for knowledge conflict resolution examination in the form of question answering.
  arXiv  Detail & Related papers  (2024-04-04T16:40:11Z)
• KnowTuning: Knowledge-aware Fine-tuning for Large Language Models [83.5849717262019]
  We propose a knowledge-aware fine-tuning (KnowTuning) method to improve fine-grained and coarse-grained knowledge awareness of LLMs. KnowTuning generates more facts with less factual error rate under fine-grained facts evaluation.
  arXiv  Detail & Related papers  (2024-02-17T02:54:32Z)
• A Comprehensive Study of Knowledge Editing for Large Language Models [82.65729336401027]
  Large Language Models (LLMs) have shown extraordinary capabilities in understanding and generating text that closely mirrors human communication. This paper defines the knowledge editing problem and provides a comprehensive review of cutting-edge approaches. We introduce a new benchmark, KnowEdit, for a comprehensive empirical evaluation of representative knowledge editing approaches.
  arXiv  Detail & Related papers  (2024-01-02T16:54:58Z)
• Is Knowledge All Large Language Models Needed for Causal Reasoning? [11.476877330365664]
  This paper explores the causal reasoning of large language models (LLMs) to enhance their interpretability and reliability in advancing artificial intelligence. We propose a novel causal attribution model that utilizes do-operators" for constructing counterfactual scenarios.
  arXiv  Detail & Related papers  (2023-12-30T04:51:46Z)
• Distilling Rule-based Knowledge into Large Language Models [90.7765003679106]
  We are inspired that humans can learn the new tasks or knowledge in another way by learning from rules.<n>We propose rule distillation, which first uses the strong in-context abilities of LLMs to extract the knowledge from the textual rules.<n>Our experiments show that making LLMs learn from rules by our method is much more efficient than example-based learning in both the sample size and generalization ability.
  arXiv  Detail & Related papers  (2023-11-15T11:42:41Z)
• "Merge Conflicts!" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs [15.660128743249611]
  Large language models (LLMs) acquire extensive knowledge during pre-training, known as their parametric knowledge. LLMs inevitably require external knowledge during their interactions with users. This raises a crucial question: How will LLMs respond when external knowledge interferes with their parametric knowledge?
  arXiv  Detail & Related papers  (2023-09-15T17:47:59Z)
• Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models [26.342351417963965]
  Pre-trained language models (PLMs) have shown evidence of acquiring vast amounts of knowledge. It remains unclear how much of this parametric knowledge is actually usable in performing downstream tasks. We propose a systematic framework to measure parametric knowledge utilization in PLMs.
  arXiv  Detail & Related papers  (2023-05-24T06:26:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.