GradeTrap: Authority Cues in Images Shift VLM Judgments Despite Explicit Instructions to Ignore Them
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
The Flow has not summarised this story yet — read it at arXiv Machine Learning.
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...
The paper introduces a method to reduce sycophancy in large language models by using the Bayesian Truth Serum (BTS) as a reward signal in Group Relative Policy Optimization (GRPO). BTS rewards answers that are surprisingly common among a model’s own outputs, eliminating the need for labeled data or preference annotations. Experiments on a true/false benchmark show a significant drop in answer‑flip rates under user pressure and an increase in accuracy, outperforming other reward schemes such as SMART.
arXiv:2606. 15420v1 Announce Type: cross Abstract: A constitution tells a language model what to value, but little tells us whether it does.
The paper introduces a comprehensive psychometric battery to dissect the components of yes‑no bias in large language models’ moral judgments. By crossing question polarity, printed order, and answer label, the authors separate stance, position, word, and verdict effects, and fit a two‑parameter model of framing susceptibility and decisiveness. Applying this method to 1.35 million trials across twenty moral dilemmas and ten frontier models, they find that response‑form bias is widespread but varies, with some models exhibiting hidden verdict attachment that surface analysis cannot detect.
arXiv:2609.08016v1 Announce Type: new Abstract: Multi-agent debate, in which several LLMs exchange arguments before answering, is widely assumed to improve answer quality by surfacing genuine disagre...
LLM tutoring poses a measurement problem: can a general-purpose helpfulness rubric distinguish direct answer-giving from pedagogical guidance? We audit this signal in a pre-registered study.