The paper investigates how language models decide between contextual information and their internal memory when the two conflict. By estimating "authority directions" from agreement prompts and swapping these directions between matched prompts, the authors show that such interventions can reproduce 30–68% of the shift in source choice across Qwen, Llama, and OLMo models. Cross‑task experiments reveal that authority directions learned on one task transfer only modestly (≈9%) to another, indicating that authority computations are largely task‑specific.
arXiv:2610.20067v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently encounter conflicts between internal parametric knowledge and external contextual knowledge, yet the mechanisms...
arXiv:2601.12075v2 Announce Type: replace Abstract: Language models used in retrieval-augmented settings must arbitrate between parametric knowledge stored in their weights and contextual information...
The study investigates how language models acquire in-context learning (ICL) by distinguishing between copying a nearby demonstration and integrating information across a prompt. Across 17 models, roughly one-third default to copied answers, a few are undecided, and the remainder favor rule-consistent answers that yield higher accuracy and are guided by the requested value rather than the nearest conflicting example. Analyses show that models prioritize task-relevant prompt tokens before accuracy surpasses chance, and that synthetic or fine-tuned training can shift models toward compositional responses or improve accuracy when prompts reassign label meanings.
arXiv:2601. 09445v2 Announce Type: replace-cross Abstract: In language models (LMs), intra-memory knowledge conflict arises when inconsistent information about the same subject is encoded within the model's parametric knowledge.
arXiv:2610.20179v1 Announce Type: cross Abstract: Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot...
arXiv:2609.24238v1 Announce Type: new Abstract: We reproduce and stress-test the work of Yu et al. (2023), who characterize how language models (LMs) arbitrate between memorized knowledge and contrad...
Probes on activation vectors are widely used to detect misbehavior in language models, but their success relies on the assumption that models cannot control what their activations encode. Humans can l...
arXiv:2610.14958v1 Announce Type: new Abstract: Activation steering has recently been used as a memory for skills: past experiences of an agent are stored as steering vectors and retrieved later. Fac...
The study investigates how task context reshapes the roles of shared attention heads in large language models. By applying identical graph facts and measuring interventions on attention heads and downstream activations, the authors show that task changes redistribute influence across five open‑weight models, causing the same heads to respond to different facts and affect later components differently. Linear response maps before and after activation edits reveal significant reductions in prediction error, indicating that task context alters both the facts processed and the downstream impact of shared components.
The paper questions whether large language models (LLMs) truly introspect by critiquing recent studies that claim they can detect and report their internal states. It proposes two necessary conditions for genuine introspection: privileged access to internal representations and second‑order computation that distinguishes from first‑order task performance. Re‑examining two existing paradigms, the authors find that apparent introspective abilities can be explained by input‑based classifiers or generic anomaly detection, concluding that current evidence does not support metacognitive monitoring in LLMs.
arXiv:2607. 21692v1 Announce Type: new Abstract: Sparse attention reduces the cost of long contexts by allowing each query to read only selected parts of the input.
arXiv:2609.37616v1 Announce Type: new Abstract: Language models tend to agree with whatever a user asserts, and post-training increasingly targets this sycophancy so that models evaluate claims on th...