Large language models (LLMs) have achieved impressive progress in natural language processing tasks but still struggle with complex logical reasoning. We observe that in propositional logic question-answering (QA), LLMs' performance varies with the order of training samples during fine-tuning. Motivated by this, we propose a data-driven approach to automatically determine the fine-tuning sample order, enhancing the logical QA performance of LLMs. Specifically, we first quantify the logical reasoning complexity of propositional reasoning samples and then stratify the training data into several subsets of ascending complexity. Subsequently, we fine-tune the LLMs on these subsets, progressing from low to high reasoning complexity. Experimental results demonstrate that our approach outperforms single-stage fine-tuning baselines across diverse reasoning benchmarks.

Uplift modeling has obtained significant attention, with broad applications in medicine, economics, and marketing. For example, in a push notification scenario, accurately estimating the uplift of different push frequencies on user activation and notification switch close rate is critical for balancing user experience and business goals. Existing methods only use binary labels, i.e., convert or not within the observational window. However, they ignore time information (e.g., users who convert on day 1 vs. day 14 reflect different sensitivities) and fail to model potential closures outside the window, i.e., due to treatments always taking time to manifest causal impacts on outcomes, the potential outcomes of interest cannot be observed promptly and accurately. Failing to account for these issues can result in skewed uplift modeling. To address this gap, this work examines how observation timing influences the assessment of uplift by explicitly modeling the potential response time. Theoretical analysis establishes the conditions for identifiability under delayed feedback scenarios. We introduce CFR-DF (Counterfactual Regression with Delayed Feedback), a systematic framework that jointly learns both the latent response times and the underlying potential outcomes. Empirical evaluations on synthetic and real-world datasets, including an A/B test with over 1 billion users for 14 days, validate the approach, demonstrating its ability to handle temporal delays and improve estimation accuracy compared to previous uplift modeling methods.

Estimating the conditional average treatment effect (CATE) from observational data plays a crucial role in areas such as e-commerce, healthcare, and economics. Existing studies mainly rely on the strong ignorability assumption that there are no unmeasured confounders, whose presence cannot be tested from observational data and can invalidate any causal conclusion. In contrast, data collected from randomized controlled trials (RCT) do not suffer from confounding, but are usually limited by a small sample size. In this paper, we propose a two-stage pretraining-finetuning (TSPF) framework using both large-scale observational data and small-scale RCT data to estimate the CATE in the presence of unmeasured confounding. In the first stage, a foundational representation of covariates is trained to estimate counterfactual outcomes through large-scale observational data. In the second stage, we propose to train an augmented representation of the covariates, which is concatenated to the foundational representation obtained in the first stage to adjust for the unmeasured confounding. To avoid overfitting caused by the small-scale RCT data in the second stage, we further propose a partial parameter initialization approach, rather than training a separate network. The superiority of our approach is validated on two public datasets with extensive experiments. The code is available at https://github.com/zhouchuanCN/KDD25-TSPF.

In recommendation systems, implicit feedback data can be automatically recorded and is more common than explicit feedback data. However, implicit feedback poses two challenges for relevance prediction, namely (a) positive-unlabeled (PU): negative feedback does not necessarily imply low relevance and (b) missing not at random (MNAR): items that are popular or frequently recommended tend to receive more clicks than other items, even if the user does not have a significant interest in them. Existing methods either overlook the MNAR issue or fail to account for the inherent mechanism of the PU issue. As a result, they may lead to inaccurate relevance predictions or inflated biases and variances. In this paper, we formulate the implicit feedback problem as a counterfactual estimation problem with missing treatment variables. Prediction of the relevance in implicit feedback is equivalent to answering the counterfactual question that ``whether a user would click a specific item if exposed to it?". To solve the counterfactual question, we propose the Counterfactual Implicit Feedback (Counter-IF) prediction approach that divides the user-item pairs into four disjoint groups, namely definitely positive (DP), highly exposed (HE), highly unexposed (HU), and unknown (UN) groups. Specifically, Counter-IF first performs missing treatment imputation with different confidence levels from raw implicit feedback, then estimates the counterfactual outcomes via causal representation learning that combines pointwise loss and pairwise loss based on the user-item pairs stratification. Theoretically the generalization bound of the learned model is derived. Extensive experiments are conducted on publicly available datasets to demonstrate the effectiveness of our approach. The code is available at https://github.com/zhouchuanCN/NeurIPS25-Counter-IF.