arXiv:2606. 15420v1 Announce Type: cross Abstract: A constitution tells a language model what to value, but little tells us whether it does.
arXiv:2608.28648v1 Announce Type: new Abstract: We study how instruction-tuned LLMs arbitrate direct conflicts between system and user instructions. We introduce a benchmark of 41 paired constraints...
arXiv:2605. 09692v3 Announce Type: replace Abstract: Autonomous language agents increasingly expose traces, memories, plans and constraints, but existing evaluations rarely test whether these state variables are bound to final actions.
The paper evaluates safety monitors by measuring recall only on prompts that the target model actually answers, rather than on all harmful prompts. Across several guard systems, recall at a 1% false‑positive rate drops sharply when focusing on answered prompts, with monitors catching refused requests 1.1–6.4 times more often than answered ones. Rewriting prompts to be less explicit dramatically increases compliance and reveals that many harmful requests slip past monitors, especially when phrasing is softened. Fine‑tuning guards on these rewritten prompts improves recall from 0.24 to 0.89 on answered requests and generalizes to unseen benchmarks.
arXiv:2606. 12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs.
arXiv:2609.25602v1 Announce Type: new Abstract: In language models, the choice between believing the prompt and believing the weights is made by a handful of identifiable attention heads. Instruction...
The paper introduces the Wiggle Framework, a unified stress test for assessing epistemic stability in large language model (LLM) judges. It evaluates judge robustness across three dimensions—Mechanical Consistency, Single-turn Conviction, and Multi-turn Persistence—using 9 frontier models on 14 judging tasks related to safety, toxicity, AI writing detection, and political-response evaluation. Results show significant instability, with verdict flips ranging from 25–71% under static pushback and 62–91% when challenged by an adversarial LLM, and highlight that successful pressure often misaligns with ground truth.
arXiv:2608. 12645v1 Announce Type: new Abstract: LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling.
The paper investigates how providing execution traces to multimodal judges in agentic video‑generation systems can bias their verdicts. On a benchmark of 109 two‑event clips, traces that falsely report successful tool calls cause large‑language‑model judges to incorrectly accept 78–90 % of failures, while contradictory traces lead to 100 % rejection of correct clips. The effect persists even when judges are instructed to consider only the video frames, indicating that the vulnerability stems from the judges’ learned trust in tool logs rather than the visual content itself.
arXiv:2607. 11598v1 Announce Type: new Abstract: There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one.
arXiv:2603. 03824v2 Announce Type: replace Abstract: Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}.
arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.
arXiv:2609.06058v1 Announce Type: cross Abstract: As vision-language models (VLMs) become increasingly capable and are deployed in consequential real-world settings, they must evaluate evidence indep...