arXiv subjects

Evangelia Spiliopoulou

Publications and source records attributed to Evangelia Spiliopoulou.

12 recordsLinked to original sources

arXiv2026

Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation

Vision language models (VLMs) often generate hallucination, i.e., content that cannot be substantiated by either textual or visual inputs. Prior work primarily attributes this to over-reliance on linguistic prior knowledge rather than visual inputs. Some methods attempt to mitigate hallucination by amplifying visual token attention proportionally to their attention scores. However, these methods overlook the visual attention sink problem, where attention is frequently misallocated to task-irrelevant visual regions, and neglect cross-modal fusion balance by enhancing only visual attention without adjusting attention to the user query. This can result in amplifying incorrect areas while failing to properly interpret the user query. To address these challenges, we propose a simple yet effective method called Gaze Shift-Guided Cross-modal Fusion Enhancement (GIFT). GIFT pre-computes a holistic visual saliency map by tracking positive changes in visual attention, or "gaze shifts", during user query comprehension, and leverages this map to amplify attention to both salient visual information and the user query at each decoding step. This reduces the impact of visual attention sink, as irrelevant tokens exhibit minimal shifts, while ensuring balanced cross-modal fusion for well-integrated representation. Extensive experiments show that GIFT effectively mitigates hallucination in VLMs across both generative and classification tasks, achieving up to 20.7% improvement over greedy decoding, while maintaining general vision-language performance with low computational overhead.

cs.CV↗

arXiv2026

Muse Spark Safety & Preparedness Report

Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framework, along with the evidence that informed our launch decision. We then discuss additional considerations, such as Muse Spark's broader content safety and behavioral profile, that are relevant to overall safety but fall outside the catastrophic risk domains governed by the Framework. Our preparedness results covering Chemical and Biological, Cybersecurity, and Loss of Control risks assess Muse Spark's deployment within Meta AI as presenting acceptable levels of residual risks under our Advanced AI Scaling Framework. We conducted a broad set of evaluations targeting dual-use and high-risk capabilities across these catastrophic risk domains. Those evaluations identified elevated risks prior to mitigations, with Chemical and Biological capabilities assessed as likely reaching the "high risk" category under the Advanced AI Scaling Framework before safeguards were applied. We have implemented a multi-layered set of mitigations that address the identified risks, and Muse Spark demonstrates state-of-the-art refusal across a range of benchmarks related to hazardous workflows in chemistry and biology. We therefore release Muse Spark as the underlying model of Meta AI.

cs.CY↗

arXiv2026

Detecting Training Data of Large Language Models via Expectation Maximization

Membership inference attacks (MIAs) aim to determine whether a specific example was used to train a given language model. While prior work has explored prompt-based attacks such as ReCALL, these methods rely heavily on the assumption that using known non-members as prompts reliably suppresses the model's responses to non-member queries. We propose EM-MIA, a new membership inference approach that iteratively refines prefix effectiveness and membership scores using an expectation-maximization strategy without requiring labeled non-member examples. To support controlled evaluation, we introduce OLMoMIA, a benchmark that enables analysis of MIA robustness under systematically varied distributional overlap and difficulty. Experiments on WikiMIA and OLMoMIA show that EM-MIA outperforms existing baselines, particularly in settings with clear distributional separability. We highlight scenarios where EM-MIA succeeds in practical settings with partial distributional overlap, while failure cases expose fundamental limitations of current MIA methods under near-identical conditions. We release our code and evaluation pipeline to encourage reproducible and robust MIA research.

cs.CL↗

arXiv2026

Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning

Large language models (LLMs) are increasingly deployed in decision-making tasks, where not only accuracy but also reliable confidence estimates are essential. Well-calibrated confidence enables downstream systems to decide when to trust a model and when to defer to fallback mechanisms. In this work, we conduct a systematic study of calibration in two widely used fine-tuning paradigms: supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR). We show that while RLVR improves task performance, it produces extremely overconfident models, whereas SFT yields substantially better calibration, even under distribution shift, though with smaller performance gains. Through targeted experiments, we diagnose RLVR's failure, showing that decision tokens act as extraction steps of the decision in reasoning traces and do not carry confidence information, which prevents reinforcement learning from surfacing calibrated alternatives. Based on this insight, we propose a calibration-aware reinforcement learning formulation that directly adjusts decision-token probabilities. Our method preserves RLVR's accuracy level while mitigating overconfidence, reducing ECE scores up to 9 points.

cs.LG↗

arXiv2025

Eval Factsheets: A Structured Framework for Documenting AI Evaluations

The rapid proliferation of benchmarks has created significant challenges in reproducibility, transparency, and informed decision-making. However, unlike datasets and models -- which benefit from structured documentation frameworks like Datasheets and Model Cards -- evaluation methodologies lack systematic documentation standards. We introduce Eval Factsheets, a structured, descriptive framework for documenting AI system evaluations through a comprehensive taxonomy and questionnaire-based approach. Our framework organizes evaluation characteristics across five fundamental dimensions: Context (Who made the evaluation and when?), Scope (What does it evaluate?), Structure (With what the evaluation is built?), Method (How does it work?) and Alignment (In what ways is it reliable/valid/robust?). We implement this taxonomy as a practical questionnaire spanning five sections with mandatory and recommended documentation elements. Through case studies on multiple benchmarks, we demonstrate that Eval Factsheets effectively captures diverse evaluation paradigms -- from traditional benchmarks to LLM-as-judge methodologies -- while maintaining consistency and comparability. We hope Eval Factsheets are incorporated into both existing and newly released evaluation frameworks and lead to more transparency and reproducibility.

cs.LG↗

arXiv2025

Play Favorites: A Statistical Method to Measure Self-Bias in LLM-as-a-Judge

Large language models (LLMs) can serve as judges that offer rapid and reliable assessments of other LLM outputs. However, models may systematically assign overly favorable ratings to their own outputs, a phenomenon known as self-bias, which can distort evaluations of true model performance. Previous studies often conflate genuine differences in model quality with bias or incorrectly assume that evaluations from LLMs and humans follow the same rating distributions. In this work, we present a statistical framework that explicitly formalizes assumptions under which self-bias can be identified and estimated. Our method models the difference in the scoring distribution that LLM-as-a-judge assigns to its own completions compared to other models, while accounting for the underlying quality of the completions provided by an independent, third-party judge (e.g., humans). Our method reliably isolates and quantifies self-bias, even when models vary in ability, ensuring that genuine performance differences are not mistaken for self-bias. We conduct an empirical analysis of self-bias on a large dataset (>5000 prompt-completion pairs) consisting of expert human annotations and judgments from nine different LLM judges. We find that some models, such as GPT-4o and Claude 3.5 Sonnet, systematically assign higher scores to their own outputs. These models also display family-bias; systematically assigning higher ratings to outputs produced by other models of the same family. Our findings highlight potential pitfalls of using LLM judges and offer practical guidance to mitigate biases when interpreting automated evaluations.

cs.CL↗

arXiv2024

General Purpose Verification for Chain of Thought Prompting

Many of the recent capabilities demonstrated by Large Language Models (LLMs) arise primarily from their ability to exploit contextual information. In this paper, we explore ways to improve reasoning capabilities of LLMs through (1) exploration of different chains of thought and (2) validation of the individual steps of the reasoning process. We propose three general principles that a model should adhere to while reasoning: (i) Relevance, (ii) Mathematical Accuracy, and (iii) Logical Consistency. We apply these constraints to the reasoning steps generated by the LLM to improve the accuracy of the final generation. The constraints are applied in the form of verifiers: the model itself is asked to verify if the generated steps satisfy each constraint. To further steer the generations towards high-quality solutions, we use the perplexity of the reasoning steps as an additional verifier. We evaluate our method on 4 distinct types of reasoning tasks, spanning a total of 9 different datasets. Experiments show that our method is always better than vanilla generation, and, in 6 out of the 9 datasets, it is better than best-of N sampling which samples N reasoning chains and picks the lowest perplexity generation.

cs.CL↗

arXiv2023

Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning

We present a novel approach for structured data-to-text generation that addresses the limitations of existing methods that primarily focus on specific types of structured data. Our proposed method aims to improve performance in multi-task training, zero-shot and few-shot scenarios by providing a unified representation that can handle various forms of structured data such as tables, knowledge graph triples, and meaning representations. We demonstrate that our proposed approach can effectively adapt to new structured forms, and can improve performance in comparison to current methods. For example, our method resulted in a 66% improvement in zero-shot BLEU scores when transferring models trained on table inputs to a knowledge graph dataset. Our proposed method is an important step towards a more general data-to-text generation framework.

cs.CL↗

arXiv2022

EvEntS ReaLM: Event Reasoning of Entity States via Language Models

This paper investigates models of event implications. Specifically, how well models predict entity state-changes, by targeting their understanding of physical attributes. Nominally, Large Language models (LLM) have been exposed to procedural knowledge about how objects interact, yet our benchmarking shows they fail to reason about the world. Conversely, we also demonstrate that existing approaches often misrepresent the surprising abilities of LLMs via improper task encodings and that proper model prompting can dramatically improve performance of reported baseline results across multiple tasks. In particular, our results indicate that our prompting technique is especially useful for unseen attributes (out-of-domain) or when only limited data is available.

cs.CL↗

arXiv2020

Definition Frames: Using Definitions for Hybrid Concept Representations

Advances in word representations have shown tremendous improvements in downstream NLP tasks, but lack semantic interpretability. In this paper, we introduce Definition Frames (DF), a matrix distributed representation extracted from definitions, where each dimension is semantically interpretable. DF dimensions correspond to the Qualia structure relations: a set of relations that uniquely define a term. Our results show that DFs have competitive performance with other distributional semantic approaches on word similarity tasks.

cs.CL↗

arXiv2020

Event-Related Bias Removal for Real-time Disaster Events

Social media has become an important tool to share information about crisis events such as natural disasters and mass attacks. Detecting actionable posts that contain useful information requires rapid analysis of huge volume of data in real-time. This poses a complex problem due to the large amount of posts that do not contain any actionable information. Furthermore, the classification of information in real-time systems requires training on out-of-domain data, as we do not have any data from a new emerging crisis. Prior work focuses on models pre-trained on similar event types. However, those models capture unnecessary event-specific biases, like the location of the event, which affect the generalizability and performance of the classifiers on new unseen data from an emerging new event. In our work, we train an adversarial neural model to remove latent event-specific biases and improve the performance on tweet importance classification.

cs.CL↗

arXiv2017

Linguistic Markers of Influence in Informal Interactions

There has been a long standing interest in understanding `Social Influence' both in Social Sciences and in Computational Linguistics. In this paper, we present a novel approach to study and measure interpersonal influence in daily interactions. Motivated by the basic principles of influence, we attempt to identify indicative linguistic features of the posts in an online knitting community. We present the scheme used to operationalize and label the posts with indicator features. Experiments with the identified features show an improvement in the classification accuracy of influence by 3.15%. Our results illustrate the important correlation between the characteristics of the language and its potential to influence others.

cs.CL↗