This paper presents a reproducibility study examining how Large Language Models (LLMs) manage competing factual and counterfactual information, focusing on the role of attention heads in this process. We attempt to reproduce and reconcile findings from three recent studies by Ortu et al., Yu, Merullo, and Pavlick and McDougall et al. that investigate the competition between model-learned facts and contradictory context information through Mechanistic Interpretability tools. Our study specifically examines the relationship between attention head strength and factual output ratios, evaluates competing hypotheses about attention heads' suppression mechanisms, and investigates the domain specificity of these attention patterns. Our findings suggest that attention heads promoting factual output do so via general copy suppression rather than selective counterfactual suppression, as strengthening them can also inhibit correct facts. Additionally, we show that attention head behavior is domain-dependent, with larger models exhibiting more specialized and category-sensitive patterns.

We present a reproduction study of "Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals" (Ortu et al., 2024), which investigates competition of mechanisms in language models between factual recall and counterfactual in-context repetition. Our study successfully reproduces their primary findings regarding the localization of factual and counterfactual information, the dominance of attention blocks in mechanism competition, and the specialization of attention heads in handling competing information. We reproduce their results on both GPT-2 (Radford et al., 2019) and Pythia 6.9B (Biderman et al., 2023). We extend their work in three significant directions. First, we explore the generalizability of these findings to even larger models by replicating the experiments on Llama 3.1 8B (Grattafiori et al., 2024), discovering greatly reduced attention head specialization. Second, we investigate the impact of prompt structure by introducing variations where we avoid repeating the counterfactual statement verbatim or we change the premise word, observing a marked decrease in the logit for the counterfactual token. Finally, we test the validity of the authors' claims for prompts of specific domains, discovering that certain categories of prompts skew the results by providing the factual prediction token as part of the subject of the sentence. Overall, we find that the attention head ablation proposed in Ortu et al. (2024) is ineffective for domains that are underrepresented in their dataset, and that the effectiveness varies based on model architecture, prompt structure, domain and task.

Test-Time Adaptation (TTA) aims to adapt pre-trained models to the target domain during testing. In reality, this adaptability can be influenced by multiple factors. Researchers have identified various challenging scenarios and developed diverse methods to address these challenges, such as dealing with continual domain shifts, mixed domains, and temporally correlated or imbalanced class distributions. Despite these efforts, a unified and comprehensive benchmark has yet to be established. To this end, we propose a Unified Test-Time Adaptation (UniTTA) benchmark, which is comprehensive and widely applicable. Each scenario within the benchmark is fully described by a Markov state transition matrix for sampling from the original dataset. The UniTTA benchmark considers both domain and class as two independent dimensions of data and addresses various combinations of imbalance/balance and i.i.d./non-i.i.d./continual conditions, covering a total of \( (2 \times 3)^2 = 36 \) scenarios. It establishes a comprehensive evaluation benchmark for realistic TTA and provides a guideline for practitioners to select the most suitable TTA method. Alongside this benchmark, we propose a versatile UniTTA framework, which includes a Balanced Domain Normalization (BDN) layer and a COrrelated Feature Adaptation (COFA) method--designed to mitigate distribution gaps in domain and class, respectively. Extensive experiments demonstrate that our UniTTA framework excels within the UniTTA benchmark and achieves state-of-the-art performance on average. Our code is available at \url{https://github.com/LeapLabTHU/UniTTA}.

Interpretability research aims to bridge the gap between empirical success and our scientific understanding of the inner workings of large language models (LLMs). However, most existing research focuses on analyzing a single mechanism, such as how models copy or recall factual knowledge. In this work, we propose a formulation of competition of mechanisms, which focuses on the interplay of multiple mechanisms instead of individual mechanisms and traces how one of them becomes dominant in the final prediction. We uncover how and where mechanisms compete within LLMs using two interpretability methods: logit inspection and attention modification. Our findings show traces of the mechanisms and their competition across various model components and reveal attention positions that effectively control the strength of certain mechanisms. Code: https://github.com/francescortu/comp-mech. Data: https://huggingface.co/datasets/francescortu/comp-mech.