Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models

Large Language Models (LLMs) have shown impressive moral reasoning abilities. Yet they often diverge when confronted with complex, multi-factor moral dilemmas. To address these discrepancies, we propose a framework that synthesizes multiple LLMs' moral judgments into a collectively formulated moral judgment, realigning models that deviate significantly from this consensus. Our aggregation mechanism fuses continuous moral acceptability scores (beyond binary labels) into a collective probability, weighting contributions by model reliability. For misaligned models, a targeted embedding-optimization procedure fine-tunes token embeddings for moral philosophical theories, minimizing JS divergence to the consensus while preserving semantic integrity. Experiments on a large-scale social moral dilemma dataset show our approach builds robust consensus and improves individual model fidelity. These findings highlight the value of data-driven moral alignment across multiple models and its potential for safer, more consistent AI systems.

SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification

Shortcut learning undermines model generalization to out-of-distribution data. While the literature attributes shortcuts to biases in superficial features, we show that imbalances in the semantic distribution of sample embeddings induce spurious semantic correlations, compromising model robustness. To address this issue, we propose SCISSOR (Semantic Cluster Intervention for Suppressing ShORtcut), a Siamese network-based debiasing approach that remaps the semantic space by discouraging latent clusters exploited as shortcuts. Unlike prior data-debiasing approaches, SCISSOR eliminates the need for data augmentation and rewriting. We evaluate SCISSOR on 6 models across 4 benchmarks: Chest-XRay and Not-MNIST in computer vision, and GYAFC and Yelp in NLP tasks. Compared to several baselines, SCISSOR reports +5.3 absolute points in F1 score on GYAFC, +7.3 on Yelp, +7.7 on Chest-XRay, and +1 on Not-MNIST. SCISSOR is also highly advantageous for lightweight models with ~9.5% improvement on F1 for ViT on computer vision datasets and ~11.9% for BERT on NLP. Our study redefines the landscape of model generalization by addressing overlooked semantic biases, establishing SCISSOR as a foundational framework for mitigating shortcut learning and fostering more robust, bias-resistant AI systems.

Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents

Large-language models (LLMs) and chatbot agents are known to provide wrong outputs at times, and it was recently found that this can never be fully prevented. Hence, uncertainty quantification plays a crucial role, aiming to quantify the level of ambiguity in either one overall number or two numbers for aleatoric and epistemic uncertainty. This position paper argues that this traditional dichotomy of uncertainties is too limited for the open and interactive setup that LLM agents operate in when communicating with a user, and that we need to research avenues that enrich uncertainties in this novel scenario. We review the literature and find that popular definitions of aleatoric and epistemic uncertainties directly contradict each other and lose their meaning in interactive LLM agent settings. Hence, we propose three novel research directions that focus on uncertainties in such human-computer interactions: Underspecification uncertainties, for when users do not provide all information or define the exact task at the first go, interactive learning, to ask follow-up questions and reduce the uncertainty about the current context, and output uncertainties, to utilize the rich language and speech space to express uncertainties as more than mere numbers. We expect that these new ways of dealing with and communicating uncertainties will lead to LLM agent interactions that are more transparent, trustworthy, and intuitive.

Graph Style Transfer for Counterfactual Explainability

Counterfactual explainability seeks to uncover model decisions by identifying minimal changes to the input that alter the predicted outcome. This task becomes particularly challenging for graph data due to preserving structural integrity and semantic meaning. Unlike prior approaches that rely on forward perturbation mechanisms, we introduce Graph Inverse Style Transfer (GIST), the first framework to re-imagine graph counterfactual generation as a backtracking process, leveraging spectral style transfer. By aligning the global structure with the original input spectrum and preserving local content faithfulness, GIST produces valid counterfactuals as interpolations between the input style and counterfactual content. Tested on 8 binary and multi-class graph classification benchmarks, GIST achieves a remarkable +7.6% improvement in the validity of produced counterfactuals and significant gains (+45.5%) in faithfully explaining the true class distribution. Additionally, GIST's backtracking mechanism effectively mitigates overshooting the underlying predictor's decision boundary, minimizing the spectral differences between the input and the counterfactuals. These results challenge traditional forward perturbation methods, offering a novel perspective that advances graph explainability.

Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods

While research on applications and evaluations of explanation methods continues to expand, fairness of the explanation methods concerning disparities in their performance across subgroups remains an often overlooked aspect. In this paper, we address this gap by showing that, across three tasks and five language models, widely used post-hoc feature attribution methods exhibit significant gender disparity with respect to their faithfulness, robustness, and complexity. These disparities persist even when the models are pre-trained or fine-tuned on particularly unbiased datasets, indicating that the disparities we observe are not merely consequences of biased training data. Our results highlight the importance of addressing disparities in explanations when developing and applying explainability methods, as these can lead to biased outcomes against certain subgroups, with particularly critical implications in high-stakes contexts. Furthermore, our findings underscore the importance of incorporating the fairness of explanations, alongside overall model fairness and explainability, as a requirement in regulatory frameworks.

EvalxNLP: A Framework for Benchmarking Post-Hoc Explainability Methods on NLP Models

As Natural Language Processing (NLP) models continue to evolve and become integral to high-stakes applications, ensuring their interpretability remains a critical challenge. Given the growing variety of explainability methods and diverse stakeholder requirements, frameworks that help stakeholders select appropriate explanations tailored to their specific use cases are increasingly important. To address this need, we introduce EvalxNLP, a Python framework for benchmarking state-of-the-art feature attribution methods for transformer-based NLP models. EvalxNLP integrates eight widely recognized explainability techniques from the Explainable AI (XAI) literature, enabling users to generate and evaluate explanations based on key properties such as faithfulness, plausibility, and complexity. Our framework also provides interactive, LLM-based textual explanations, facilitating user understanding of the generated explanations and evaluation outcomes. Human evaluation results indicate high user satisfaction with EvalxNLP, suggesting it is a promising framework for benchmarking explanation methods across diverse user groups. By offering a user-friendly and extensible platform, EvalxNLP aims at democratizing explainability tools and supporting the systematic comparison and advancement of XAI techniques in NLP.

Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers

Transformers have achieved great success in numerous NLP tasks but continue to exhibit notable gaps in multi-step factual reasoning, especially when real-world knowledge is sparse. Recent advances in grokking have demonstrated that neural networks can transition from memorizing to perfectly generalizing once they detect underlying logical patterns - yet these studies have primarily used small, synthetic tasks. In this paper, for the first time, we extend grokking to real-world factual data and address the challenge of dataset sparsity by augmenting existing knowledge graphs with carefully designed synthetic data to raise the ratio $\phi_r$ of inferred facts to atomic facts above the threshold required for grokking. Surprisingly, we find that even factually incorrect synthetic data can strengthen emergent reasoning circuits rather than degrade accuracy, as it forces the model to rely on relational structure rather than memorization. When evaluated on multi-hop reasoning benchmarks, our approach achieves up to 95-100% accuracy on 2WikiMultiHopQA - substantially improving over strong baselines and matching or exceeding current state-of-the-art results. We further provide an in-depth analysis of how increasing $\phi_r$ drives the formation of generalizing circuits inside Transformers. Our findings suggest that grokking-based data augmentation can unlock implicit multi-hop reasoning capabilities, opening the door to more robust and interpretable factual reasoning in large-scale language models.

RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting

Despite the widespread use of LLMs due to their superior performance in various tasks, their high computational costs often lead potential users to opt for the pretraining-finetuning pipeline. However, biases prevalent in manually constructed datasets can introduce spurious correlations between tokens and labels, creating so-called shortcuts and hindering the generalizability of fine-tuned models. Existing debiasing methods often rely on prior knowledge of specific dataset biases, which is challenging to acquire a priori. We propose RAZOR (Rewriting And Zero-bias Optimization Refinement), a novel, unsupervised, and data-focused debiasing approach based on text rewriting for shortcut mitigation. RAZOR leverages LLMs to iteratively rewrite potentially biased text segments by replacing them with heuristically selected alternatives in a shortcut space defined by token statistics and positional information. This process aims to align surface-level text features more closely with diverse label distributions, thereby promoting the learning of genuine linguistic patterns. Compared with unsupervised SoTA models, RAZOR improves by 3.5% on the FEVER and 6.5% on MNLI and SNLI datasets according to the F1 score. Additionally, RAZOR effectively mitigates specific known biases, reducing bias-related terms by x2 without requiring prior bias information, a result that is on par with SoTA models that leverage prior information. Our work prioritizes data manipulation over architectural modifications, emphasizing the pivotal role of data quality in enhancing model performance and fairness. This research contributes to developing more robust evaluation benchmarks for debiasing methods by incorporating metrics for bias reduction and overall model efficacy.

Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers

Feature engineering is crucial for optimizing machine learning model performance, particularly in tabular data classification tasks. Leveraging advancements in natural language processing, this study presents a systematic approach to enrich tabular datasets with features derived from large language model embeddings. Through a comprehensive ablation study on diverse datasets, we assess the impact of RoBERTa and GPT-2 embeddings on ensemble classifiers, including Random Forest, XGBoost, and CatBoost. Results indicate that integrating embeddings with traditional numerical and categorical features often enhances predictive performance, especially on datasets with class imbalance or limited features and samples, such as UCI Adult, Heart Disease, Titanic, and Pima Indian Diabetes, with improvements particularly notable in XGBoost and CatBoost classifiers. Additionally, feature importance analysis reveals that LLM-derived features frequently rank among the most impactful for the predictions. This study provides a structured approach to embedding-based feature enrichment and illustrates its benefits in ensemble learning for tabular data.

Understanding Knowledge Drift in LLMs through Misinformation

Large Language Models (LLMs) have revolutionized numerous applications, making them an integral part of our digital ecosystem. However, their reliability becomes critical, especially when these models are exposed to misinformation. We primarily analyze the susceptibility of state-of-the-art LLMs to factual inaccuracies when they encounter false information in a QnA scenario, an issue that can lead to a phenomenon we refer to as *knowledge drift*, which significantly undermines the trustworthiness of these models. We evaluate the factuality and the uncertainty of the models' responses relying on Entropy, Perplexity, and Token Probability metrics. Our experiments reveal that an LLM's uncertainty can increase up to 56.6% when the question is answered incorrectly due to the exposure to false information. At the same time, repeated exposure to the same false information can decrease the models uncertainty again (-52.8% w.r.t. the answers on the untainted prompts), potentially manipulating the underlying model's beliefs and introducing a drift from its original knowledge. These findings provide insights into LLMs' robustness and vulnerability to adversarial inputs, paving the way for developing more reliable LLM applications across various domains. The code is available at https://github.com/afastowski/knowledge_drift.