arXiv subjects

Pepa Atanasova

Publications and source records attributed to Pepa Atanasova.

At least 19 recordsLinked to original sources

arXiv2026

Understanding helpfulness and harmless tension in reward models

Reward models are a key component of reinforcement learning from human feedback (RLHF), aligning language models toward both helpful and harmless behaviour. However, the internal mechanisms underlying these objectives and their conflicts remain poorly understood. We study alignment tension in reward models trained under helpfulness-only, harmlessness-only, and mixed-objective settings. We find that mixed-objective models often underperform single-objective models, indicating interference between objectives. Using activation-based methods, we identify neurons associated with each objective and study their functional roles via targeted ablations. We find that these neurons causally support their corresponding objectives while often negatively affecting the opposing one. We find that a substantial proportion of neurons are shared between helpfulness and harmlessness, and that these shared neurons exert a disproportionate influence on model behaviour, contributing to alignment tension. Additionally, our results provide insights and mechanistic interpretation into how alignment objectives are represented in reward models and why multi-objective alignment remains challenging, motivating future work on disentangled and controllable alignment methods.

cs.LG↗

arXiv2026

Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization

Chain-of-Thought (CoT) faithfulness, i.e., whether CoTs genuinely reflect large language models' (LLM) underlying behavior, is typically evaluated with metrics under two disjoint paradigms: contextual faithfulness, measured by perturbing the input or CoT trace, and parametric faithfulness, assessed by intervening on a model's parametric knowledge. Yet prior work compares them only descriptively. We fill this gap by proposing FaithMATE, a unified preference-alignment interface for optimizing models towards either faithfulness paradigm. It enables us to investigate the interplay between the two paradigms, examining whether and to what extent faithfulness gains generalize within and across paradigms. Across three models, two datasets, and six faithfulness metrics, we find that the two paradigms are positively coupled, yet asymmetric: optimizing towards parametric faithfulness yields consistent gains across both paradigms, whereas the contextual counterpart delivers more variable gains. Within the contextual paradigm, faithfulness gains on one metric do not consistently transfer to others, implying that existing contextual metrics capture disjoint facets of faithfulness and exposing inherent trade-offs. These findings imply that CoT faithfulness is not a monolithic objective and therefore requires multifaceted optimization and evaluation.

cs.CL↗

arXiv2026

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations

Quantization is widely used to accelerate inference and streamline the deployment of large language models (LLMs), yet its effects on self-explanations (SEs) remain unexplored. SEs, generated by LLMs to justify their own outputs, require reasoning about the model's own decision-making process, a capability that may exhibit particular sensitivity to quantization. As SEs are increasingly relied upon for transparency in high-stakes applications, understanding whether and to what extent quantization degrades SE quality and faithfulness is critical. To address this gap, we examine two types of SEs: natural language explanations (NLEs) and counterfactual examples, generated by LLMs quantized using three common techniques at distinct bit widths. Our findings indicate that quantization typically leads to moderate declines in both SE quality (up to 4.4%) and faithfulness (up to 3.9%). The user study further demonstrates that quantization considerably diminishes both the coherence and trustworthiness of SEs (by up to 8.5%). Compared to smaller models, larger models show limited resilience to quantization in terms of SE quality but maintain more faithfulness. Moreover, no quantization technique consistently excels across task accuracy, SE quality, and faithfulness. Because quantization's impact varies considerably by context and can be sizable in specific cases, we recommend validating SE quality for the intended use case. Despite these sometimes considerable drops, quantization remains an effective compression technique when its impact on SEs is properly validated.

cs.CL↗

arXiv2025

Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement

Natural Language Explanations (NLEs) describe how Large Language Models (LLMs) make decisions by drawing on external Context Knowledge (CK) and Parametric Knowledge (PK). Understanding the interaction between these sources is key to assessing NLE grounding, yet these dynamics remain underexplored. Prior work has largely focused on i) single-step generation and ii) modeled PK--CK interaction as a binary choice within a rank-1 subspace. This approach overlooks richer interactions and how they unfold over longer generations, such as complementary or supportive knowledge. We propose a novel rank-2 projection subspace that disentangles PK and CK contributions more accurately and use it for the first multi-step analysis of knowledge interactions across longer NLE sequences. Experiments across four QA datasets and three open-weight LLMs demonstrate that rank-1 subspaces struggle to represent diverse interactions, whereas our rank-2 formulation captures them effectively, highlighting PK alignment for supportive interactions and CK alignment for conflicting ones. Our multi-step analysis reveals that hallucinated generations exhibit strong alignment with the PK direction, though context-faithful generations maintain a more balanced alignment between PK and CK.

cs.CL↗

arXiv2025

Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models

Context utilisation, the ability of Language Models (LMs) to incorporate relevant information from the provided context when generating responses, remains largely opaque to users, who cannot determine whether models draw from parametric memory or provided context, nor identify which specific context pieces inform the response. Highlight explanations (HEs) offer a natural solution as they can point the exact context pieces and tokens that influenced model outputs. However, no existing work evaluates their effectiveness in accurately explaining context utilisation. We address this gap by introducing the first gold standard HE evaluation framework for context attribution, using controlled test cases with known ground-truth context usage, which avoids the limitations of existing indirect proxy evaluations. To demonstrate the framework's broad applicability, we evaluate four HE methods -- three established techniques and MechLight, a mechanistic interpretability approach we adapt for this task -- across four context scenarios, four datasets, and five LMs. Overall, we find that MechLight performs best across all context scenarios. However, all methods struggle with longer contexts and exhibit positional biases, pointing to fundamental challenges in explanation accuracy that require new approaches to deliver reliable context utilisation explanations at scale.

cs.CL↗

arXiv2025

Self-Critique and Refinement for Faithful Natural Language Explanations

With the rapid development of Large Language Models (LLMs), Natural Language Explanations (NLEs) have become increasingly important for understanding model predictions. However, these explanations often fail to faithfully represent the model's actual reasoning process. While existing work has demonstrated that LLMs can self-critique and refine their initial outputs for various tasks, this capability remains unexplored for improving explanation faithfulness. To address this gap, we introduce Self-critique and Refinement for Natural Language Explanations (SR-NLE), a framework that enables models to improve the faithfulness of their own explanations -- specifically, post-hoc NLEs -- through an iterative critique and refinement process without external supervision. Our framework leverages different feedback mechanisms to guide the refinement process, including natural language self-feedback and, notably, a novel feedback approach based on feature attribution that highlights important input words. Our experiments across three datasets and four state-of-the-art LLMs demonstrate that SR-NLE significantly reduces unfaithfulness rates, with our best method achieving an average unfaithfulness rate of 36.02%, compared to 54.81% for baseline -- an absolute reduction of 18.79%. These findings reveal that the investigated LLMs can indeed refine their explanations to better reflect their actual reasoning process, requiring only appropriate guidance through feedback without additional training or fine-tuning.

cs.CL↗

arXiv2025

Local Differences, Global Lessons: Insights from Organisation Policies for International Legislation

The rapid adoption of AI across diverse domains has led to the development of organisational guidelines that vary significantly, even within the same sector. This paper examines AI policies in two domains, news organisations and universities, to understand how bottom-up governance approaches shape AI usage and oversight. By analysing these policies, we identify key areas of convergence and divergence in how organisations address risks such as bias, privacy, misinformation, and accountability. We then explore the implications of these findings for international AI legislation, particularly the EU AI Act, highlighting gaps where practical policy insights could inform regulatory refinements. Our analysis reveals that organisational policies often address issues such as AI literacy, disclosure practices, and environmental impact, areas that are underdeveloped in existing international frameworks. We argue that lessons from domain-specific AI policies can contribute to more adaptive and effective AI governance at the global level. This study provides actionable recommendations for policymakers seeking to bridge the gap between local AI practices and international regulations.

cs.CY↗

arXiv2024

A Reality Check on Context Utilisation for Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) helps address the limitations of parametric knowledge embedded within a language model (LM). In real world settings, retrieved information can vary in complexity, yet most investigations of LM utilisation of context has been limited to synthetic text. We introduce DRUID (Dataset of Retrieved Unreliable, Insufficient and Difficult-to-understand contexts) with real-world queries and contexts manually annotated for stance. The dataset is based on the prototypical task of automated claim verification, for which automated retrieval of real-world evidence is crucial. We compare DRUID to synthetic datasets (CounterFact, ConflictQA) and find that artificial datasets often fail to represent the complexity and diversity of realistically retrieved context. We show that synthetic datasets exaggerate context characteristics rare in real retrieved data, which leads to inflated context utilisation results, as measured by our novel ACU score. Moreover, while previous work has mainly focused on singleton context characteristics to explain context utilisation, correlations between singleton context properties and ACU on DRUID are surprisingly small compared to other properties related to context source. Overall, our work underscores the need for real-world aligned context utilisation studies to represent and improve performance in real-world RAG settings.

cs.CL↗

arXiv2024

Graph-Guided Textual Explanation Generation Framework

Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned their faithfulness, as they may not accurately reflect the model's internal reasoning process regarding its predicted answer. In contrast, highlight explanations--input fragments critical for the model's predicted answers--exhibit measurable faithfulness. Building on this foundation, we propose G-Tex, a Graph-Guided Textual Explanation Generation framework designed to enhance the faithfulness of NLEs. Specifically, highlight explanations are first extracted as faithful cues reflecting the model's reasoning logic toward answer prediction. They are subsequently encoded through a graph neural network layer to guide the NLE generation, which aligns the generated explanations with the model's underlying reasoning toward the predicted answer. Experiments on T5 and BART using three reasoning datasets show that G-Tex improves NLE faithfulness by up to 12.18% compared to baseline methods. Additionally, G-Tex generates NLEs with greater semantic and lexical similarity to human-written ones. Human evaluations show that G-Tex can decrease redundant content and enhance the overall quality of NLEs. Our work presents a novel method for explicitly guiding NLE generation to enhance faithfulness, serving as a foundation for addressing broader criteria in NLE and generated text.

cs.CL↗

arXiv2024

DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models

Knowledge-intensive language understanding tasks require Language Models (LMs) to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated knowledge. However, conflicting knowledge can be present in the LM's parameters, termed intra-memory conflict, which can affect a model's propensity to accept contextual knowledge. To study the effect of intra-memory conflict on an LM's ability to accept relevant context, we utilize two knowledge conflict measures and a novel dataset containing inherently conflicting data, DynamicQA. This dataset includes facts with a temporal dynamic nature where facts can change over time and disputable dynamic facts, which can change depending on the viewpoint. DynamicQA is the first to include real-world knowledge conflicts and provide context to study the link between the different types of knowledge conflicts. We also evaluate several measures on their ability to reflect the presence of intra-memory conflict: semantic entropy and a novel coherent persuasion score. With our extensive experiments, we verify that LMs exhibit a greater degree of intra-memory conflict with dynamic facts compared to facts that have a single truth value. Furthermore, we reveal that facts with intra-memory conflict are harder to update with context, suggesting that retrieval-augmented generation will struggle with the most commonly adapted facts.

cs.CL↗

arXiv2024

Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework

Explaining the decision-making process of machine learning models is crucial for ensuring their reliability and transparency for end users. One popular explanation form highlights key input features, such as i) tokens (e.g., Shapley Values and Integrated Gradients), ii) interactions between tokens (e.g., Bivariate Shapley and Attention-based methods), or iii) interactions between spans of the input (e.g., Louvain Span Interactions). However, these explanation types have only been studied in isolation, making it difficult to judge their respective applicability. To bridge this gap, we develop a unified framework that facilitates an automated and direct comparison between highlight and interactive explanations comprised of four diagnostic properties. We conduct an extensive analysis across these three types of input feature explanations -- each utilizing three different explanation techniques -- across two datasets and two models, and reveal that each explanation has distinct strengths across the different diagnostic properties. Nevertheless, interactive span explanations outperform other types of input feature explanations across most diagnostic properties. Despite being relatively understudied, our analysis underscores the need for further research to improve methods generating these explanation types. Additionally, integrating them with other explanation types that perform better in certain characteristics could further enhance their overall effectiveness.

cs.CL↗

arXiv2024

Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods

Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant challenges for understanding a model's inner workings and further for updating or correcting this embedded knowledge without the significant cost of retraining. This underscores the importance of unveiling exactly what knowledge is stored and its association with specific model components. Instance Attribution (IA) and Neuron Attribution (NA) offer insights into this training-acquired knowledge, though they have not been compared systematically. Our study introduces a novel evaluation framework to quantify and compare the knowledge revealed by IA and NA. To align the results of the methods we introduce the attribution method NA-Instances to apply NA for retrieving influential training instances, and IA-Neurons to discover important neurons of influential instances discovered by IA. We further propose a comprehensive list of faithfulness tests to evaluate the comprehensiveness and sufficiency of the explanations provided by both methods. Through extensive experiments and analysis, we demonstrate that NA generally reveals more diverse and comprehensive information regarding the LM's parametric knowledge compared to IA. Nevertheless, IA provides unique and valuable insights into the LM's parametric knowledge, which are not revealed by NA. Our findings further suggest the potential of a synergistic approach of combining the diverse findings of IA and NA for a more holistic understanding of an LM's parametric knowledge.

cs.CL↗

arXiv2023

Explaining Interactions Between Text Spans

Reasoning over spans of tokens from different parts of the input is essential for natural language understanding (NLU) tasks such as fact-checking (FC), machine reading comprehension (MRC) or natural language inference (NLI). However, existing highlight-based explanations primarily focus on identifying individual important tokens or interactions only between adjacent tokens or tuples of tokens. Most notably, there is a lack of annotations capturing the human decision-making process w.r.t. the necessary interactions for informed decision-making in such tasks. To bridge this gap, we introduce SpanEx, a multi-annotator dataset of human span interaction explanations for two NLU tasks: NLI and FC. We then investigate the decision-making processes of multiple fine-tuned large language models in terms of the employed connections between spans in separate parts of the input and compare them to the human reasoning processes. Finally, we present a novel community detection based unsupervised method to extract such interaction explanations from a model's inner workings.

cs.CL↗

arXiv2023

bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark

We present bgGLUE(Bulgarian General Language Understanding Evaluation), a benchmark for evaluating language models on Natural Language Understanding (NLU) tasks in Bulgarian. Our benchmark includes NLU tasks targeting a variety of NLP problems (e.g., natural language inference, fact-checking, named entity recognition, sentiment analysis, question answering, etc.) and machine learning tasks (sequence labeling, document-level classification, and regression). We run the first systematic evaluation of pre-trained language models for Bulgarian, comparing and contrasting results across the nine tasks in the benchmark. The evaluation results show strong performance on sequence labeling tasks, but there is a lot of room for improvement for tasks that require more complex reasoning. We make bgGLUE publicly available together with the fine-tuning and the evaluation code, as well as a public leaderboard at https://bgglue.github.io/, and we hope that it will enable further advancements in developing NLU models for Bulgarian.

cs.CL↗

arXiv2023

Faithfulness Tests for Natural Language Explanations

Explanations of neural models aim to reveal a model's decision-making process for its predictions. However, recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misleading, as they are prone to present reasons that are unfaithful to the model's inner workings. This work explores the challenging question of evaluating the faithfulness of natural language explanations (NLEs). To this end, we present two tests. First, we propose a counterfactual input editor for inserting reasons that lead to counterfactual predictions but are not reflected by the NLEs. Second, we reconstruct inputs from the reasons stated in the generated NLEs and check how often they lead to the same predictions. Our tests can evaluate emerging NLE models, proving a fundamental tool in the development of faithful NLEs.

cs.CL↗

arXiv2022

Accountable and Explainable Methods for Complex Reasoning over Text

A major concern of Machine Learning (ML) models is their opacity. They are deployed in an increasing number of applications where they often operate as black boxes that do not provide explanations for their predictions. Among others, the potential harms associated with the lack of understanding of the models' rationales include privacy violations, adversarial manipulations, and unfair discrimination. As a result, the accountability and transparency of ML models have been posed as critical desiderata by works in policy and law, philosophy, and computer science. In computer science, the decision-making process of ML models has been studied by developing accountability and transparency methods. Accountability methods, such as adversarial attacks and diagnostic datasets, expose vulnerabilities of ML models that could lead to malicious manipulations or systematic faults in their predictions. Transparency methods explain the rationales behind models' predictions gaining the trust of relevant stakeholders and potentially uncovering mistakes and unfairness in models' decisions. To this end, transparency methods have to meet accountability requirements as well, e.g., being robust and faithful to the underlying rationales of a model. This thesis presents my research that expands our collective knowledge in the areas of accountability and transparency of ML models developed for complex reasoning tasks over text.

cs.LG↗

arXiv2022

Fact Checking with Insufficient Evidence

Automating the fact checking (FC) process relies on information obtained from external sources. In this work, we posit that it is crucial for FC models to make veracity predictions only when there is sufficient evidence and otherwise indicate when it is not enough. To this end, we are the first to study what information FC models consider sufficient by introducing a novel task and advancing it with three main contributions. First, we conduct an in-depth empirical analysis of the task with a new fluency-preserving method for omitting information from the evidence at the constituent and sentence level. We identify when models consider the remaining evidence (in)sufficient for FC, based on three trained models with different Transformer architectures and three FC datasets. Second, we ask annotators whether the omitted evidence was important for FC, resulting in a novel diagnostic dataset, SufficientFacts, for FC with omitted evidence. We find that models are least successful in detecting missing evidence when adverbial modifiers are omitted (21% accuracy), whereas it is easiest for omitted date modifiers (63% accuracy). Finally, we propose a novel data augmentation strategy for contrastive self-learning of missing evidence by employing the proposed omission method combined with tri-training. It improves performance for Evidence Sufficiency Prediction by up to 17.8 F1 score, which in turn improves FC performance by up to 2.6 F1 score.

cs.CL↗

arXiv2021

Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing

Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when human-readable explanations accompany the veracity labels. However, manual collection of such explanations is expensive and time-consuming. Recent works frame explanation generation as extractive summarization, and propose to automatically select a sufficient subset of the most important facts from the ruling comments (RCs) of a professional journalist to obtain fact-checking explanations. However, these explanations lack fluency and sentence coherence. In this work, we present an iterative edit-based algorithm that uses only phrase-level edits to perform unsupervised post-editing of disconnected RCs. To regulate our editing algorithm, we use a scoring function with components including fluency and semantic preservation. In addition, we show the applicability of our approach in a completely unsupervised setting. We experiment with two benchmark datasets, LIAR-PLUS and PubHealth. We show that our model generates explanations that are fluent, readable, non-redundant, and cover important information for the fact check.

cs.CL↗