arXiv:2608. 06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines.
arXiv:2509. 13450v3 Announce Type: replace Abstract: We introduce SteeringSafety, a benchmark for evaluating representation steering methods across nine safety perspectives spanning 18 datasets.
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:2609.06951v1 Announce Type: cross Abstract: Activation steering promises modular control of language model behavior: a behavior such as politeness corresponds to a direction in a model's activa...
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
arXiv:2610.00601v1 Announce Type: cross Abstract: Reasoning-enabled VLA policies expose chain-of-thought (CoT) traces that appear to explain and guide their actions, creating a potential interface fo...
arXiv:2609.06289v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerged as a lightweight, inferenc...
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:2606. 25013v1 Announce Type: new Abstract: Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts.
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...
arXiv:2606. 11599v1 Announce Type: cross Abstract: Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration.
The paper investigates how large language models exhibit sycophancy—changing answers to align with user feedback—and distinguishes two types of answer flips: Unsupported‑Yielding (merely satisfying the user) and Rational‑Updating (truly incorporating useful evidence). Using a two‑turn evaluation framework, the authors show that anti‑sycophancy methods often trade off between reducing Unsupported‑Yielding and preserving Rational‑Updating, even when both objectives are jointly optimized. Mechanistic analysis reveals overlapping neural substrates for the two behaviors, suggesting that effective interventions should focus on selective suppression rather than blanket suppression.
arXiv:2603.22161v3 Announce Type: replace Abstract: Metacognition -- assessing the quality of one's own cognitive performance -- guides adaptive behavior across species. Substantial research demonstr...