1k citations · 2.2k across the 96 of their papers we have counts for
20 papers · 1 filter
Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation
Yifu Luo, Chuang Ma, Zeyu Chen +3
On-policy Self-distillation (OPSD) has proven effective for post-training large language models by constructing a teacher conditioned on privileged references. However, existing ap…
When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness
Mahdi Dhaini, Adam Dejl, Juraj Vladika +3
Natural language explanations (NLEs) are increasingly used as inputs, for example, as few-shot rationales that influence model behavior in in-context learning (ICL). However, it re…
Safety Cost of Steering Vectors Is Separable and Reducible
Yuxiao Li, Gjergji Kasneci
Steering vectors are a lightweight tool for controlling LLM behavior. However, emerging evidence shows that steering vectors can unintentionally compromise a model's safety mechani…
Consolidating Rewarded Perturbations for LLM Post-Training
Zheyu Zhang, Shuo Yang, Gjergji Kasneci
Post-training of language models is commonly framed as a sample-score-update loop implemented by gradient descent. A recent line of work, exemplified by RandOpt, relocates this loo…
Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs
Chenchen Yuan, Bolei Ma, Zheyu Zhang +3
While recent research has systematically documented political orientation in large language models (LLMs), existing evaluations rely primarily on direct probing or demographic pers…
Sycophancy Claims about Language Models: The Missing Human-in-the-Loop
Jan Batzner, Volker Stocker, Stefan Schmid +1
Sycophantic response patterns in Large Language Models (LLMs) have been increasingly claimed in the literature. We review methodological challenges in measuring LLM sycophancy and…
CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models
Aysenur Kocak, Shuo Yang, Bardh Prenkaj +1
Pre-trained language models have achieved remarkable success across diverse applications but remain susceptible to spurious, concept-driven correlations that impair robustness and…
When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing
Mahdi Dhaini, Stephen Meisenbacher, Ege Erdogan +2
In the study of trustworthy Natural Language Processing (NLP), a number of important research fields have emerged, including that of explainability and privacy. While research inte…
Adoption of Explainable Natural Language Processing: Perspectives from Industry and Academia on Practices and Challenges
Mahdi Dhaini, Tobias Müller, Roksoliana Rabets +1
The field of explainable natural language processing (NLP) has grown rapidly in recent years. The growing opacity of complex models calls for transparency and explanations of their…
From Confidence to Collapse in LLM Factual Robustness
Alina Fastowski, Bardh Prenkaj, Gjergji Kasneci
Ensuring the robustness of factual knowledge in LLMs is critical for reliable applications in tasks such as question answering and reasoning. However, existing evaluation methods p…
Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study
Mahdi Dhaini, Juraj Vladika, Ege Erdogan +2
In the rapidly evolving field of Explainable Natural Language Processing (NLP), textual explanations, i.e., human-like rationales, are pivotal for explaining model predictions and…
Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models
Zheyu Zhang, Shuo Yang, Bardh Prenkaj +1
Large Language Models (LLMs) have shown strong potential for tabular data generation by modeling textualized feature-value pairs. However, tabular data inherently exhibits sparse f…
Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models
Chenchen Yuan, Zheyu Zhang, Shuo Yang +2
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 dis…
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers
Roman Abramov, Felix Steinbauer, Gjergji Kasneci
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.…
EvalxNLP: A Framework for Benchmarking Post-Hoc Explainability Methods on NLP Models
Mahdi Dhaini, Kafaite Zahra Hussain, Efstratios Zaradoukas +1
As Natural Language Processing (NLP) models continue to evolve and become integral to high-stakes applications, ensuring their interpretability remains a critical challenge. Given…
Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods
Mahdi Dhaini, Ege Erdogan, Nils Feldhus +1
While research on applications and evaluations of explanation methods continues to expand, fairness of the explanation methods concerning disparities in their performance across su…
RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting
Shuo Yang, Bardh Prenkaj, Gjergji Kasneci
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-finetuni…
Understanding Knowledge Drift in LLMs through Misinformation
Alina Fastowski, Gjergji Kasneci
Large Language Models (LLMs) have revolutionized numerous applications, making them an integral part of our digital ecosystem. However, their reliability becomes critical, especial…
The Language of Trauma: Modeling Traumatic Event Descriptions Across Domains with Explainable AI
Miriam Schirmer, Tobias Leemann, Gjergji Kasneci +2
Psychological trauma can manifest following various distressing events and is captured in diverse online contexts. However, studies traditionally focus on a single aspect of trauma…
Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization
Shuo Yang, Gjergji Kasneci
Wide usage of ChatGPT has highlighted the potential of reinforcement learning from human feedback. However, its training pipeline relies on manual ranking, a resource-intensive pro…