arXiv:2608. 11027v1 Announce Type: new Abstract: Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across generations.
arXiv:2609.35860v1 Announce Type: cross Abstract: Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors a...
arXiv:2506.17871v4 Announce Type: replace-cross Abstract: Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this cons...
arXiv:2606. 01060v1 Announce Type: cross Abstract: Preference alignment has substantially improved the observable behavior of large language models, yet it remains unclear what alignment changes internally.
arXiv:2604. 19139v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI, a growing and increasingly conspicuous phenomenon has emerged: the proliferation of verbal tics--repetitive, formulaic linguistic patterns that pervade model outputs.
arXiv:2607. 05679v1 Announce Type: cross Abstract: Language models (LMs) exhibit problematic biases, such as stereotypes.
arXiv:2512. 07019v3 Announce Type: replace-cross Abstract: The proliferation of Large Language Models (LLMs) necessitates valid evaluation methods to provide guidance for both downstream applications and actionable future improvements.
arXiv:2604. 16197v2 Announce Type: replace Abstract: Data attribution and valuation are critical for understanding data-model synergy for Large Language Models (LLMs), yet existing gradient-based methods suffer from scalability challenges on LLMs.
The paper introduces a new way to detect drift in stateful language‑model pipelines by treating the sequence of prompt, response, and next prompt as a single unit of analysis. It defines two metrics—communication closure and normalized conditional action contribution—to quantify how well a response aligns with the subsequent prompt and how much it resolves the next reply. Experiments on over 2,200 dialogues show that swapping a response drastically reduces measured contribution, indicating that drift can be detected without labels or predefined rules.
arXiv:2607. 20454v1 Announce Type: cross Abstract: All frontier large language models (LLMs) exhibit response drift -- producing outputs that deviate from expert-validated references -- yet the magnitude and structure of this drift remain uncharacterised by systematic human evaluation.
arXiv:2608. 11138v1 Announce Type: cross Abstract: We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident prediction is \emph{fragile} under perturbation of its attention pathways.
The paper introduces a fine-grained method called interactions to analyze prompt sensitivity in large language models (LLMs). By decomposing output scores into nonlinear interactions, the authors show that subtle prompt changes can destabilize these interactions even when overall outputs stay unchanged. They propose an Interaction-based Prompt Sensitivity (IPS) metric and use it to evaluate 50 open-source LLMs, finding that supervised fine‑tuning, larger model scales, dense architectures, and few‑shot learning all reduce prompt sensitivity, primarily by stabilizing low‑order interactions.
arXiv:2603.18908v5 Announce Type: replace Abstract: Independently trained language models often learn compatible late-stage representations, despite differences in training objectives, architectures,...