The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing

Large language models (LLMs) are increasingly used as knowledge bases, but keeping them up to date requires targeted knowledge editing (KE). However, it remains unclear how edits are implemented inside the model once applied. In this work, we take a mechanistic view of KE using neuron-level knowledge attribution (NLKA). Unlike prior work that focuses on pre-edit causal tracing and localization, we use post-edit attribution -- contrasting successful and failed edits -- to isolate the computations that shift when an edit succeeds. Across representative KE methods, we find a consistent pattern: mid-to-late attention predominantly promotes the new target, while attention and FFN modules cooperate to suppress the original fact. Motivated by these findings, we propose MEGA, a MEchanism-Guided Activation steering method that performs attention-residual interventions in attribution-aligned regions without modifying model weights. On CounterFact and Popular, MEGA achieves strong editing performance across KE metrics on GPT2-XL and LLaMA2-7B. Overall, our results elevate post-edit attribution from analysis to engineering signal: by pinpointing where and how edits take hold, it powers MEGA to deliver reliable, architecture-agnostic knowledge edits.

Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders

Better cross-lingual alignment is often assumed to yield better cross-lingual transfer. However, explicit alignment techniques -- despite increasing embedding similarity -- frequently fail to improve token-level downstream performance. In this work, we show that this mismatch arises because alignment and downstream task objectives are largely orthogonal, and because the downstream benefits from alignment vary substantially across languages and task types. We analyze four XLM-R encoder models aligned on different language pairs and fine-tuned for either POS Tagging or Sentence Classification. Using representational analyses, including embedding distances, gradient similarities, and gradient magnitudes for both task and alignment losses, we find that: (1) embedding distances alone are unreliable predictors of improvements (or degradations) in task performance and (2) alignment and task gradients are often close to orthogonal, indicating that optimizing one objective may contribute little to optimizing the other. Taken together, our findings explain why ``better'' alignment often fails to translate into ``better'' cross-lingual transfer. Based on these insights, we provide practical guidelines for combining cross-lingual alignment with task-specific fine-tuning, highlighting the importance of careful loss selection.

GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models

We present GLUScope, an open-source tool for analyzing neurons in Transformer-based language models, intended for interpretability researchers. We focus on more recent models than previous tools do; specifically we consider gated activation functions such as SwiGLU. This introduces a new challenge: understanding positive activations is not enough. Instead, both the gate and the in activation of a neuron can be positive or negative, leading to four different possible sign combinations that in some cases have quite different functionalities. Accordingly, for any neuron, our tool shows text examples for each of the four sign combinations, and indicates how often each combination occurs. We describe examples of how our tool can lead to novel insights. A demo is available at https: //sjgerstner.github.io/gluscope.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical insights while lacking a systematic framework for actionable intervention. To bridge this gap, we present a practical survey structured around the pipeline: "Locate, Steer, and Improve." We formally categorize Localizing (diagnosis) and Steering (intervention) methods based on specific Interpretable Objects to establish a rigorous intervention protocol. Furthermore, we demonstrate how this framework enables tangible improvements in Alignment, Capability, and Efficiency, effectively operationalizing MI as an actionable methodology for model optimization. The curated paper list of this work is available at https://github.com/rattlesnakey/Awesome-Actionable-MI-Survey.

Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models

Large language models (LLMs) can recall a wide range of factual knowledge across languages. However, existing factual recall evaluations primarily assess fact retrieval in isolation, where the queried entity is explicitly named and the fact is requested directly. In natural language use, facts are often accessed through context, where the relevant entity is introduced only indirectly. In this work, we study contextually mediated factual recall, asking whether LLMs can reliably retrieve factual knowledge when the target entity is embedded in a naturalistic context rather than queried explicitly, across languages. We construct controlled prompts that preserve the underlying fact while introducing referential mediation through contextual sentences. To disentangle contextual effects from name-specific associations, we further compare performance using synthetic names and real names across languages. Evaluating multiple model families in five languages, we find that contextual mediation consistently degrades factual recall, with substantial variation across relations. Larger models are more robust to contextual mediation, exhibiting a reduced performance gap relative to direct queries, while the effect of real names and name origin is mixed and unsystematic. These findings highlight a gap between isolated factual recall and context-dependent language understanding in multilingual LLMs.

Relational Linearity is a Predictor of Hallucinations

Hallucination is a central failure mode in large language models (LLMs). We focus on hallucinations of answers to questions like: "Which instrument did Glenn Gould play?", but we ask these questions for synthetic entities that are unknown to the model. Surprisingly, we find that medium-size models like Gemma-7B-IT frequently hallucinate, i.e., they have difficulty recognizing that the hallucinated fact is not part of their knowledge. We hypothesize that an important factor in causing these hallucinations is the linearity of the relation: linear relations tend to be stored more abstractly, making it difficult for the LLM to assess its knowledge; the facts of nonlinear relations tend to be stored more directly, making knowledge assessment easier. To investigate this hypothesis, we create SyntHal, a dataset of 6000 synthetic entities for six relations. In our experiments with four models, we determine, for each relation, the hallucination rate on SyntHal and also measure its linearity, using $Δ\cos$. We find a strong correlation ($r \in [.78,.82]$) between relational linearity and hallucination rate, providing evidence for our hypothesis that the underlying storage of triples of a relation is a factor in how well a model can self-assess its knowledge. This finding has implications for how to manage hallucination behavior and suggests new research directions for improving the representation of factual knowledge in LLMs.

SAD: A Large-Scale Strategic Argumentative Dialogue Dataset

Argumentation generation has attracted substantial research interest due to its central role in human reasoning and decision-making. However, most existing argumentative corpora focus on non-interactive, single-turn settings, either generating arguments from a given topic or refuting an existing argument. In practice, however, argumentation is often realized as multi-turn dialogue, where speakers defend their stances and employ diverse argumentative strategies to strengthen persuasiveness. To support deeper modeling of argumentation dialogue, we present the first large-scale \textbf{S}trategic \textbf{A}rgumentative \textbf{D}ialogue dataset, SAD, consisting of 392,822 examples. Grounded in argumentation theories, we annotate each utterance with five strategy types, allowing multiple strategies per utterance. Unlike prior datasets, SAD requires models to generate contextually appropriate arguments conditioned on the dialogue history, a specified stance on the topic, and targeted argumentation strategies. We further benchmark a range of pretrained generative models on SAD and present in-depth analysis of strategy usage patterns in argumentation.

High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning

As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning, which is widely used to reduce resource requirements. However, decreasing the rank encounters challenges with limited representational capacity when compared to full parameter fine-tuning. We present \textbf{SMoA}, a high-rank \textbf{S}tructured \textbf{MO}dulation \textbf{A}dapter that uses fewer trainable parameters while maintaining a higher rank, thereby improving the model's representational capacity and offering improved performance potential. The core idea is to freeze the original pretrained weights and selectively amplify or suppress important features of the original weights across multiple subspaces. The subspace mechanism provides an efficient way to increase the capacity and complexity of a model. We conduct both theoretical analyses and empirical studies on various tasks. Experiment results show that SMoA outperforms LoRA and its variants on 10 tasks, with extensive ablation studies validating its effectiveness.

PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs

Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically degrades this text's reasoning capability, undermining multimodal performance. To address this issue, we propose a training-free framework to mitigate this degradation. Through layer-wise vision token masking, we reveal a common three-stage pattern in multimodal large language models: early-modal separation, mid-modal alignment, and late-modal degradation. By analyzing the behavior of MLLMs at different stages, we propose a plateau-guided model merging method that selectively injects base language model parameters into MLLMs. Experimental results based on five MLLMs on nine benchmarks demonstrate the effectiveness of our method. Attention-based analysis further reveals that merging shifts attention from diffuse, scattered patterns to focused localization on task-relevant visual regions. Our repository is on https://github.com/wzj1718/PlaM.

Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations

Confidence estimation (CE) indicates how reliable the answers of large language models (LLMs) are, and can impact user trust and decision-making. Existing work evaluates CE methods almost exclusively through calibration, examining whether stated confidence aligns with accuracy, or discrimination, whether confidence is ranked higher for correct predictions than incorrect ones. However, these facets ignore pitfalls of CE in the context of LLMs and language variation: confidence estimates should remain consistent under semantically equivalent prompt or answer variations, and should change when the answer meaning differs. Therefore, we present a comprehensive evaluation framework for CE that measures their confidence quality on three new aspects: robustness of confidence against prompt perturbations, stability across semantic equivalent answers, and sensitivity to semantically different answers. In our work, we demonstrate that common CE methods for LLMs often fail on these metrics: methods that achieve good performance on calibration or discrimination are not robust to prompt variations or are not sensitive to answer changes. Overall, our framework reveals limitations of existing CE evaluations relevant for real-world LLM use cases and provides practical guidance for selecting and designing more reliable CE methods.