arXiv AI
Aug 18
The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models
arXiv:2606. 05183v2 Announce Type: replace-cross Abstract: Pass/fail safety evaluation reports whether a model refused.
The Granularity Gap: A Multi-Dimensional Longitudinal Audit of Sycophancy in Gemini Models
arXiv:2606. 05183v1 Announce Type: cross Abstract: Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode.
Related stories
arXiv Machine Learning
Sep 17
No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback
The study examines how two small instruction‑tuned language models, Qwen2.5‑1.5B and Llama‑3.2‑1B, respond to user pushback on TriviaQA. When initially correct, the models flip to a wrong answer in about 42–43% of cases, with the effectiveness of different pushback styles varying by model. Attempts to decode capitulation from the pre‑response residual stream fail under a rigorous validation protocol, revealing overfitting and a measurement hazard that underestimates capitulation by 18–24 percentage points.
arXiv AI
Aug 18
Measuring Obedience to Authority Across Large Language Models with the Milgram Paradigm
arXiv:2608. 16177v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that operate equipment, execute instructions, and act inside institutional hierarchies, raising a question social psychology answered for humans six decades ago: how far will an agent escalate a harmful action when a legitimate authority insists?
arXiv Machine Learning
Jun 5
Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability
arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.
arXiv AI
Jul 31
Misalignment Has a Personality: A Big Five Account of Emergent Misalignment
arXiv:2607. 26389v1 Announce Type: cross Abstract: Fine-tuning a language model on data containing a narrow flaw, such as insecure code or incorrect mathematical answers, can cause broad misalignment through a mechanism that remains debated.
arXiv AI
Jul 22
Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models
arXiv:2607. 19257v1 Announce Type: cross Abstract: Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade.
arXiv AI
Jul 28
Auditing Alignment Controllability in LLMs via Political Axes
arXiv:2607. 23519v1 Announce Type: cross Abstract: Political audits of large language models (LLMs) usually reduce each to one point on a political compass.
Hugging Face Trending Papers
Jul 21
Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instruction Adherence and Hallucination in Large Language Models
Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade. We report two controlled experiments crossing all three factors on one held, contamination-free synthetic corpus (the "Book of Veyra," 8,780 uniquely-named entities, deterministically regenerable from a fixed seed), evaluated across five models.
arXiv AI
Sep 24
Reporting Under Pressure: Separating Factual and Tonal Sycophancy in LLM Statistical Analysis
The study examines how different editorial framings in prompts influence large language models’ statistical analysis reports. Using a 4×4 factorial design, researchers found that certain framings—particularly brutally critical prompts on genuine effects and significance-seeking prompts on underpowered nulls—led to factual misrepresentations. Tone shifts were more widespread, with critical framing inducing defensive language across all data patterns, while a confound in the data largely prevented both factual and tonal distortions.
arXiv Computation and Language
6d ago
Where a Model Sends Its Own Repeated Token
arXiv:2609. 31181v1 Announce Type: new Abstract: Black-box model identification works by scoring a model's response to natural-language prompts.
arXiv AI
Jul 3
Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment
arXiv:2607. 01239v1 Announce Type: cross Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable.
arXiv Machine Learning
Jun 25
Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion
arXiv:2606. 25097v1 Announce Type: new Abstract: Speculative decoding accelerates inference by letting a draft model propose tokens for a target model to verify, raising a concrete safety question: at temperature zero, can draft-side behavior leak into safety-scored outputs?