Fine‑tuning reshapes internal representations of large language models, affecting attention patterns and layer‑wise activations. The study shows that components identified by EAP as important for task performance cluster in specific layers, yet these layers do not align with those undergoing the largest representational changes. Additionally, overlapping EAP components across different tasks do not guarantee cross‑task transfer and can even degrade performance when tasks differ in nature.
By Lingfang Li, Procheta Sen, Shubham Das, Danushka Bollegala
arXiv:2608. 04347v1 Announce Type: new Abstract: Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence.
By Kotaro Yoshida, Laura Gomezjurado Gonzalez, Yukinori Yamamoto, Yuji Naraki, Ryotaro Shimizu, Wenya Wang
arXiv:2605. 24059v2 Announce Type: replace Abstract: We present a three-step recipe for identifying attention-head circuits in pretrained transformers.
By Yongzhong Xu
Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence. However, this adaptation process can also degrade alignment properties that were present in the source model.
arXiv:2606. 02378v1 Announce Type: cross Abstract: We track the developmental trajectory of attention-head circuit formation across three 1B-class language models spanning two architecture families (dense transformer, mixture-of-experts) and two pretraining corpora (The Pile, DCLM): Pythia 1B, OLMo 1B-0724-hf, and OLMoE 1B-7B-0924.
By Yongzhong Xu
arXiv:2609.39188v1 Announce Type: new
Abstract: Developmental psychology holds that certain priors are given to infants prior to experience rather than induced from data, and that the influence of su...
By Dong Gyun Kang, Megha Thukral, Kwangsoo Kim
arXiv:2606. 24396v1 Announce Type: new Abstract: Large Transformer models function as Dense Associative Memories (DAMs), retrieving knowledge via high-dimensional attractor dynamics driven by the self-attention mechanism \citep{ramsauer2020hopfield, wu2024attention}.
By Kanishk Awadhiya
The paper proposes a principled way to design hybrid transformer architectures that combine Full Attention (FA) and Linear Attention (LA). By introducing two intervention metrics—RoPE Frequency Importance Score (RFIS) and RoPE Positional Dependence (RPD)—the authors identify a clear taxonomy of retrieval and positional heads, defining a Global Positional Band (GPBand) that aligns with training-length positional scales. Using these insights, they build a Head‑wise Hybrid Architecture (HwH) that assigns FA to global retrieval and LA to local positional modeling, achieving strong language modeling, improved retrieval, and superior zero‑shot long‑context extrapolation compared to standard Transformers and other hybrids.
By Runlin Shi, Bojian Yin, Guoqi Li
The study investigates whether unusually high‑gain parameters in transformer models—specifically gated feed‑forward network (gated‑FFN) rows—play a critical functional role across both text and genomic foundation models. By computing exact bilinear weight operators and testing structural extremeness, the authors find that high‑gain rows are enriched for functional importance but do not reliably predict causal effect size or severity. The analysis reveals model‑specific causal organizations, including super‑additive interactions in DNABERT‑2 and position‑localized dependencies in GENERator, indicating that structural prominence signals enrichment rather than calibrated criticality.
By Alexandros Tzanakakis, Aris Karatzikos, Ilias Georgakopoulos-Soares
arXiv:2608. 09248v1 Announce Type: new Abstract: Skill-based LLM agents select reusable procedures from an external library to solve complex tasks, yet their routing decisions rely entirely on text-level signals such as task descriptions, verbal reflections, and experience-derived rules, while the model's own internal representational state remains unobserved.
By Bohan Lin, Hejia Geng, Xinyi Xie, Heng Zhou, Qinghua Xing, Bo Liu, Chen Zhang, Yudong Zhang
arXiv:2608. 11510v1 Announce Type: cross Abstract: Congruency effects, observed in conflict tasks such as Stroop and flanker tasks, have been investigated for nearly a century in psychology and neuroscience, but their mechanistic basis is not fully understood.
By Xiaoyang Hu, Mike Angstadt, Shane Storks, Zan Huang, Aman Taxali, Alex Weigard, Richard L. Lewis, Chandra Sripada
arXiv:2602. 22600v2 Announce Type: replace-cross Abstract: Training selects for behavior, not circuitry: many weight configurations can implement the same function.
By Joshua S. Schiffman