6arXiv cs.AI (Artificial Intelligence)·
Counterfactual Report Coordinates method for certifying incentive-compatible LLM honesty
A new arXiv paper introduces Counterfactual Report Coordinates (CRC), a method for identifying and controlling low-rank activation-space coordinates governing a model's answer, confidence, and caveat outputs, with the goal of making LLMs internally incentive-compatible — resistant to sycophantic pressure while remaining responsive to genuine evidence. The authors use causal interchange interventions (not probe accuracy) to identify these coordinates and introduce a training-free two-pass clamp that achieves near-perfect resist and update scores on a Bayesian-witness benchmark. Results transfer across three model families and to SycophancyEval, though the deployable single-pass compilation is lossy. The work frames activation-level counterfactual incentive-invariance as a structural primitive for alignment research.
Related guides (3)
Related events (8)
Two-axis abstention framework separates LLM answer correctness from question answerability
A new arXiv paper identifies that LLM abstention involves two distinct axes — whether a model would answer correctly, and whether a question is even answerable (e.g., rests on a false premise) — and shows these cannot be collapsed into a single confidence score. Across five instruction-tuned models (2B–14B parameters), standard confidence signals like P(IK) and P(True) are nearly blind to false-premise questions, while hidden-state probes achieve 0.69–0.77 AUROC on the same task. The authors propose a two-axis calibrated policy that roughly triples challenge precision and certifies dual coverage budgets at 0.75 correct-answer coverage versus 0.31 for single-threshold baselines. The blind spot does not shrink with scale, making this a structural finding rather than a capability gap.
Canonical-Context On-Policy Distillation (CCOPD) for Multi-Turn LLM Consistency
This paper identifies 'self-anchored drift' as a key failure mode in multi-turn LLMs: when information is revealed incrementally across turns, models produce unsupported assumptions that distort final answers, even when the total evidence is identical to a single-prompt setting. The authors propose Canonical-Context On-Policy Distillation (CCOPD), which trains a student model on incremental multi-turn conversations to match the output distribution of a frozen teacher conditioned on the full clean prompt. Trained only on math conversations, CCOPD achieves a 32% average relative improvement on multi-turn (RAW-SHARDED) tasks and generalizes zero-shot to five out-of-domain task families while preserving single-prompt performance.
Framework for quantifying faithful confidence expression in large reasoning models
A new arXiv preprint introduces a framework to measure faithful calibration (FC) in large reasoning models (LRMs)—the alignment between a model's intrinsic confidence and its linguistically expressed confidence. The authors analyze linguistic decisiveness against three internal uncertainty sources (token probabilities, hidden states, sampled response consistency) and introduce prefix-conditioned sampling to handle structural variation in chain-of-thought traces. Applying the framework across leading models, they find FC is a significant and distinct failure mode for LRMs: extended reasoning traces do not automatically improve calibration, prompt interventions that help non-reasoning models fail in the reasoning setting, and different confidence estimators produce divergent assessments of the same traces.
Decomposing factual sycophancy in LLMs: size and instruction tuning shape robustness differently
A new arXiv paper decomposes factual sycophancy — where a model abandons a correct answer under social pressure — into two distinct mechanisms: truth margin (baseline preference for correct answers) and manipulation sensitivity (how much pressure shifts that preference). Evaluating 56 open-weight models from 0.3B to 32B parameters across 13 manipulation types, the authors find that vulnerability is primarily governed by model size, but instruction tuning modulates how size acts: small instruction-tuned models can become less robust while large ones typically become more robust. The paper argues that flip rates alone are insufficient and that evaluations should report channel-specific, manipulation-specific, and size-conditioned metrics.
LLM judges over-credit incorrect answers in no-reference evaluation settings
A new arXiv paper investigates the reliability of LLM-as-judge evaluation in no-reference settings, finding that judge models systematically over-credit incorrect answers when no ground-truth is provided. Sensitivity experiments across three languages show that adding reference answers to prompts flips correct/incorrect decisions by up to 85% in some settings, with these changes aligning with human annotations. The authors propose a calibration methodology—testing judge knowledge with reference-aware samples before deploying in reference-free setups—as a blueprint for practitioners.
LLMs fail to reliably self-report adversarial prefill attacks, study finds
A new arXiv paper evaluates whether LLMs can recognize that their own prior responses were elicited by adversarial prefill attacks, testing ten open-weight models (3B–70B) across four safety benchmarks. Models claim intent on prefilled responses only 27.3% of the time on average, and introspective signal is largely mediated by refusal-related reasoning. Three LoRA fine-tuning methods (SFT, GRPO, DPO) improve the intention-probe gap but counterintuitively raise attack success rates on most models, suggesting partial and fragile mitigation. The findings raise concerns about the reliability of LLM self-reports in safety-critical contexts.
Introspective Coupling: LMs trained on fixed counterfactual explanations develop self-faithful introspection
A new arXiv paper studies language models trained to explain their own predictions using counterfactual supervision derived from earlier checkpoints or behaviorally similar models. Surprisingly, models frequently produce explanations more faithful to their current behavior than to the training targets — a phenomenon the authors call 'introspective coupling.' The effect persists across tasks including sycophancy and refusal, tracks concurrent behavioral shifts from other post-training objectives, and is robust to label noise, suggesting fixed counterfactual explanation datasets can serve as scalable post-training signal for introspection.
Online Safety Monitoring for LLMs via Threshold-Based Risk Control
A new arXiv preprint proposes a real-time safety monitor for LLMs that converts an external verifier signal into an alarm by thresholding, with the threshold calibrated via risk control. The authors evaluate the approach on mathematical reasoning and red-teaming datasets, finding it competitive with more complex sequential hypothesis testing monitors. The work addresses the practical deployment problem of detecting unsafe outputs after alignment training.