CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models

• URL: http://arxiv.org/abs/2509.01535v2
• Date: Tue, 09 Sep 2025 04:01:50 GMT
• Title: CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models
• Authors: Kairong Han, Wenshuo Zhao, Ziyu Zhao, JunJian Ye, Lujia Pan, Kun Kuang,
• Abstract summary: Causal Attention Tuning (CAT) is a novel approach that injects fine-grained causal knowledge into the attention mechanism.<n>We propose an automated pipeline that leverages human priors to automatically generate token-level causal signals.<n>Cat achieves an average improvement of 5.76% on the STG dataset and 1.56% on downstream tasks.
• Score: 42.12079243701232
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have achieved remarkable success across various domains. However, a fundamental question remains: Can LLMs effectively utilize causal knowledge for prediction and generation? Through empirical studies, we find that LLMs trained directly on large-scale data often capture spurious correlations rather than true causal relationships, leading to suboptimal performance, especially in out-of-distribution (OOD) scenarios. To address this challenge, we propose Causal Attention Tuning (CAT), a novel approach that injects fine-grained causal knowledge into the attention mechanism. We propose an automated pipeline that leverages human priors to automatically generate token-level causal signals and introduce the Re-Attention mechanism to guide training, helping the model focus on causal structures while mitigating noise and biases in attention scores. Experimental results on our proposed Spurious Token Game (STG) benchmark and multiple downstream tasks demonstrate that our approach effectively leverages causal knowledge for prediction and remains robust in OOD scenarios. The CAT achieves an average improvement of 5.76% on the STG dataset and 1.56% on downstream tasks. Notably, the OOD performance of the Llama-3.1-8B model on STG_M increased from 64.5% to 90.5%, and Qwen's OOD performance on the STG_H dataset improved from 25.4% to 55.9%. Implementation details can be found at https://github.com/Kairong-Han/CAT.

Related papers

• Efficient Hate Speech Detection: Evaluating 38 Models from Traditional Methods to Transformers [0.0]
  This study evaluates 38 model configurations in detecting hate speech across datasets ranging from 6.5K to 451K samples.<n>Our results show that transformers, particularly RoBERTa, consistently achieve superior performance with accuracy and F1-scores exceeding 90%.
  arXiv  Detail & Related papers  (2025-09-14T21:17:04Z)
• Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training [57.03005244917803]
  Large language models (LLMs) often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training.<n>Here, we aim to mitigate such spurious correlations through causality-aware post-training (CAPT)<n> Experiments on the formal causal inference benchmark CLadder and the logical reasoning dataset PrOntoQA show that 3B-scale language models fine-tuned with CAPT can outperform both traditional SFT and larger LLMs on in-distribution (ID) and OOD tasks.
  arXiv  Detail & Related papers  (2025-06-11T06:30:28Z)
• Accelerated Test-Time Scaling with Model-Free Speculative Sampling [58.69141724095398]
  We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach.<n>We show that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding.<n>As a model-free approach, STAND can be applied to any existing language model without additional training.
  arXiv  Detail & Related papers  (2025-06-05T07:31:18Z)
• AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection [9.555955025064895]
  We propose AttentionInfluence to identify reasoning-intensive pretraining data.<n>Our approach enables a small pretrained language model to act as a strong data selector through a simple attention head masking operation.<n>Our experimental results demonstrate substantial improvements, ranging from 1.4pp to 3.5pp, across several knowledge-intensive and reasoning-heavy benchmarks.
  arXiv  Detail & Related papers  (2025-05-12T07:25:51Z)
• Fairness-Driven LLM-based Causal Discovery with Active Learning and Dynamic Scoring [1.5498930424110338]
  Causal discovery (CD) plays a pivotal role in numerous scientific fields by clarifying the causal relationships that underlie phenomena observed in diverse disciplines.<n>Despite significant advancements in CD algorithms, their application faces challenges due to the high computational demands and complexities of large-scale data.<n>This paper introduces a framework that leverages Large Language Models (LLMs) for CD, utilizing a metadata-based approach akin to the reasoning processes of human experts.
  arXiv  Detail & Related papers  (2025-03-21T22:58:26Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [49.61246073215651]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.<n>Recent advancements in OpenAI o1 and DeepSeek-R1 have further improved performance in System-2 reasoning domains.<n>However, they also introduce significant computational overhead due to verbose and redundant outputs.
  arXiv  Detail & Related papers  (2025-03-20T17:59:38Z)
• Can Large Language Models Help Experimental Design for Causal Discovery? [94.66802142727883]
  Large Language Model Guided Intervention Targeting (LeGIT) is a robust framework that effectively incorporates LLMs to augment existing numerical approaches for the intervention targeting in causal discovery.<n>LeGIT demonstrates significant improvements and robustness over existing methods and even surpasses humans.
  arXiv  Detail & Related papers  (2025-03-03T03:43:05Z)
• S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
  We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.<n>Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
  arXiv  Detail & Related papers  (2025-02-18T13:40:22Z)
• From Pre-training Corpora to Large Language Models: What Factors Influence LLM Performance in Causal Discovery Tasks? [51.42906577386907]
  This study explores the factors influencing the performance of Large Language Models (LLMs) in causal discovery tasks. A higher frequency of causal mentions correlates with better model performance, suggesting that extensive exposure to causal information during training enhances the models' causal discovery capabilities.
  arXiv  Detail & Related papers  (2024-07-29T01:45:05Z)
• C-XGBoost: A tree boosting model for causal effect estimation [8.246161706153805]
  Causal effect estimation aims at estimating the Average Treatment Effect as well as the Conditional Average Treatment Effect of a treatment to an outcome from the available data. We propose a new causal inference model, named C-XGBoost, for the prediction of potential outcomes.
  arXiv  Detail & Related papers  (2024-03-31T17:43:37Z)
• Multi-modal Causal Structure Learning and Root Cause Analysis [67.67578590390907]
  We propose Mulan, a unified multi-modal causal structure learning method for root cause localization. We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data. We also introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph.
  arXiv  Detail & Related papers  (2024-02-04T05:50:38Z)
• Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals [91.59906995214209]
  We propose a new evaluation method, Counterfactual Attentiveness Test (CAT) CAT uses counterfactuals by replacing part of the input with its counterpart from a different example, expecting an attentive model to change its prediction. We show that GPT3 becomes less attentive with an increased number of demonstrations, while its accuracy on the test data improves.
  arXiv  Detail & Related papers  (2023-11-16T06:27:35Z)
• PACE-LM: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis [17.362895895214344]
  Large language models (LLMs) are used to help humans identify the root causes of cloud incidents. We propose to perform confidence estimation for the predictions to help on-call engineers make decisions on whether to adopt the model prediction. We show that our method is able to produce calibrated confidence estimates for predicted root causes, validate the usefulness of retrieved historical data and the prompting strategy.
  arXiv  Detail & Related papers  (2023-09-11T21:24:00Z)
• Integrating Large Language Model for Improved Causal Discovery [25.50313039584238]
  Large Language Models (LLM) have been used for causal analysis across various domain-specific scenarios.<n>We propose an error-tolerant LLM-driven causal discovery framework.
  arXiv  Detail & Related papers  (2023-06-29T12:48:00Z)
• Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations [111.88727295707454]
  This paper reexamines the research on out-of-distribution (OOD) robustness in the field of NLP. We propose a benchmark construction protocol that ensures clear differentiation and challenging distribution shifts. We conduct experiments on pre-trained language models for analysis and evaluation of OOD robustness.
  arXiv  Detail & Related papers  (2023-06-07T17:47:03Z)

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.