The paper investigates how post‑hoc spectral smoothing and spiking interventions on transformer feed‑forward projection matrices affect large language models. By altering singular‑value spectra while preserving singular vectors and the geometric mean, the authors evaluate the impact on a range of tasks—including reasoning, truthfulness, hallucination, safety, and personality probes—across several Llama and Qwen models. The results reveal that structured perturbations can selectively suppress or enhance specific capabilities, suggesting a lightweight method for probing how different abilities are organized and traded off within these models.
Singular-value spectra encode important structure in transformer feed-forward projections, yet their causal role in downstream behavior remains underexplored. We study post-hoc spectral smoothing and...
arXiv:2605.30018v3 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of the...
The paper investigates how the choice of Transformer layers for fine‑tuning affects both task performance and the preservation of pre‑trained capabilities. By measuring layer sensitivity with a forward‑only input–output cosine similarity metric, the authors identify layers that are more suitable for adaptation. They introduce Layer‑Selective LoRA (LS‑LoRA), which trains adapters only in low‑similarity layers, and demonstrate that this approach improves target‑task results while better retaining commonsense reasoning compared to standard all‑layer LoRA.
The paper investigates how the upper spectral tails of weight matrices in decoder‑only transformer language models influence reasoning behavior. By performing controlled interventions on the query–key product and comparing them to factor‑level surgeries, the authors find that edits targeting the spectral tail more strongly affect model performance across multiple checkpoints and reasoning benchmarks. The study also explores how inverse participation ratios predict accuracy transitions and shows that tail‑aware low‑rank adaptations converge faster than standard methods.
arXiv:2607. 07916v1 Announce Type: new Abstract: Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decomposing, measuring, and controlling them.
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.
arXiv:2609.39929v1 Announce Type: cross Abstract: Long-context failures of RoPE-based language models can arise from RoPE's intrinsic tradeoff between maintaining stable token preferences and disting...
arXiv:2609.35599v2 Announce Type: replace Abstract: When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large language models (LLMs) organise thei...
arXiv:2510.01030v2 Announce Type: replace Abstract: The human ability to translate diverse perceptual and linguistic inputs into structured behavior has been thought to rest on learning robust repres...
arXiv:2604. 09670v2 Announce Type: replace-cross Abstract: Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals.
arXiv:2608.21766v1 Announce Type: cross Abstract: Both capability and safety benchmarks rest upon the assumption that the behavior of language models undergoing a test is informative about their beha...
arXiv:2608.21664v1 Announce Type: new Abstract: Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especiall...