30 citations · 96 across the 31 of their papers we have counts for
36 papers
A Reality Check of Inference-Time Context Augmentation Methods
Haeun Yu, Geert Heyman, Pepa Atanasova +1
Large language models (LLMs) often fail to utilise the context given in the input, resulting in hallucinations or a fallback to parametric knowledge. Context augmentation methods a…
Explaining the Roles of Experts in Mixture-of-Experts LLMs for Personalization
Sekh Mainul Islam, Pepa Atanasova, Isabelle Augenstein
Personalization of Large Language Models (LLMs) is increasingly important for user-centric applications, yet prior methods mainly adapt dense LLMs, whose polysemantic neurons, each…
Claim Framing as a Driver of LLM Sycophancy
Jean Seo, Pepa Atanasova, Isabelle Augenstein
Sycophancy in Large Language Models, the tendency to align responses with user preferences over ground truth, has largely been studied using questions without a clear ground truth…
From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness
Qianli Wang, Yilong Wang, Dennis Wei +5
Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through input--output behavior or input at…
Understanding Helpfulness and Harmless Tension in Reward Models
Eshaan Tanwar, Pepa Atanasova
Reward models (RMs) are a key component of reinforcement learning from human feedback, enabling the alignment of large language models with human values such as helpfulness and har…
Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization
Jingyi Sun, Qianli Wang, Pepa Atanasova +2
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 p…
Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
Qianli Wang, Nils Feldhus, Pepa Atanasova +4
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…
Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement
Sekh Mainul Islam, Pepa Atanasova, Isabelle Augenstein
Natural Language Explanations (NLEs) describe how Large Language Models (LLMs) make decisions by drawing on external Context Knowledge (CK) and Parametric Knowledge (PK). Understan…
Evaluation Framework for Highlight Explanations of Context Utilisation in Language Models
Jingyi Sun, Pepa Atanasova, Sagnik Ray Choudhury +2
Context utilisation, the ability of Language Models (LMs) to incorporate relevant information from the provided context when generating responses, remains largely opaque to users,…
Self-Critique and Refinement for Faithful Natural Language Explanations
Yingming Wang, Pepa Atanasova
With the rapid development of Large Language Models (LLMs), Natural Language Explanations (NLEs) have become increasingly important for understanding model predictions. However, th…
Local Differences, Global Lessons: Insights from Organisation Policies for International Legislation
Lucie-Aimée Kaffee, Pepa Atanasova, Anna Rogers
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…
A Reality Check on Context Utilisation for Retrieval-Augmented Generation
Lovisa Hagström, Sara Vera Marjanović, Haeun Yu +5
Retrieval-augmented generation (RAG) helps address the limitations of parametric knowledge embedded within a language model (LM). In real world settings, retrieved information can…
Graph-Guided Textual Explanation Generation Framework
Shuzhou Yuan, Jingyi Sun, Ran Zhang +4
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…
DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
Sara Vera Marjanović, Haeun Yu, Pepa Atanasova +3
Knowledge-intensive language understanding tasks require Language Models (LMs) to integrate relevant context, mitigating their inherent weaknesses, such as incomplete or outdated k…
Evaluating Input Feature Explanations through a Unified Diagnostic Evaluation Framework
Jingyi Sun, Pepa Atanasova, Isabelle Augenstein
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…
Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods
Haeun Yu, Pepa Atanasova, Isabelle Augenstein
Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant cha…
Explaining Interactions Between Text Spans
Sagnik Ray Choudhury, Pepa Atanasova, Isabelle Augenstein
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 comprehensi…
Faithfulness Tests for Natural Language Explanations
Pepa Atanasova, Oana-Maria Camburu, Christina Lioma +3
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 salie…
bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark
Momchil Hardalov, Pepa Atanasova, Todor Mihaylov +7
We present bgGLUE(Bulgarian General Language Understanding Evaluation), a benchmark for evaluating language models on Natural Language Understanding (NLU) tasks in Bulgarian. Our b…
Accountable and Explainable Methods for Complex Reasoning over Text
Pepa Atanasova
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 prov…
Fact Checking with Insufficient Evidence
Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma +1
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…
Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing
Shailza Jolly, Pepa Atanasova, Isabelle Augenstein
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…
Diagnostics-Guided Explanation Generation
Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma +1
Explanations shed light on a machine learning model's rationales and can aid in identifying deficiencies in its reasoning process. Explanation generation models are typically train…
A Diagnostic Study of Explainability Techniques for Text Classification
Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma +1
Recent developments in machine learning have introduced models that approach human performance at the cost of increased architectural complexity. Efforts to make the rationales beh…