Topic-aware Causal Intervention for Counterfactual Detection
Counterfactual statements, which describe events that did not or cannot take place, are beneficial to numerous NLP applications. Hence, we consider the problem of counterfactual detection (CFD) and seek to enhance the CFD models. Previous models are reliant on clue phrases to predict counterfactuality, so they suffer from significant performance drop when clue phrase hints do not exist during testing. Moreover, these models tend to predict non-counterfactuals over counterfactuals. To address these issues, we propose to integrate neural topic model into the CFD model to capture the global semantics of the input statement. We continue to causally intervene the hidden representations of the CFD model to balance the effect of the class labels. Extensive experiments show that our approach outperforms previous state-of-the-art CFD and bias-resolving methods in both the CFD and other bias-sensitive tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualCounterfactual DetectionSimilar Papers 제목 키워드 기반
The Causal Uncertainty Principle: Manifold Tearing and the Topological Limits of Counterfactual Interventions
Judea Pearl's do-calculus provides a foundation for causal inference, but its translation to continuous generative models remains fraught with geometric challenges. We establish the fundamental limits of such interventio…
Causal InferenceDoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Series
Time-series forecasting increasingly demands not only accurate observational predictions but also causal forecasting under interventional and counterfactual queries in multivariate systems. We present DoFlow, a flow-base…
Anomaly DetectionCausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics
In this work, CausalVAE is introduced as a plug-in structural module for latent world models and is attached to diverse encoder-transition backbones. Across the reported benchmarks, competitive factual prediction is pres…
CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models
Despite the groundbreaking advancements made by large language models (LLMs), hallucination remains a critical bottleneck for their deployment in high-stakes domains. Existing classification-based methods mainly rely on …
Teleological Inference in Structural Causal Models via Intentional Interventions
Structural causal models (SCMs) were conceived to formulate and answer causal questions. This paper shows that SCMs can also be used to formulate and answer teleological questions, concerning the intentions of a state-aw…