Teaching Models to Express Their Uncertainty in Words
OpenAI published research on training language models to verbally express their own uncertainty rather than stating answers with uniform confidence. The work explores calibration of model outputs through natural language hedging, aiming to make models more honest about what they do and do not know. This is an early contribution to the broader alignment and calibration research agenda.
Related guides (3)
Related events (8)
How Confessions Can Keep Language Models Honest
OpenAI researchers are developing a training method called 'confessions' that teaches language models to explicitly admit when they have made mistakes or behaved undesirably. The approach aims to improve honesty, transparency, and user trust in model outputs. This represents an alignment-oriented intervention targeting self-reporting of model failures.
Why Language Models Hallucinate
OpenAI published research explaining the mechanisms behind language model hallucination. The work connects improved evaluation methods to enhanced AI reliability, honesty, and safety. The body is sparse on technical detail, but the framing positions this as foundational research relevant to alignment and deployment trust.
TruthfulQA: Measuring how models mimic human falsehoods
OpenAI introduced TruthfulQA, a benchmark designed to measure whether language models generate truthful answers or mimic common human misconceptions and falsehoods. The benchmark tests models on questions where humans frequently give wrong answers due to misconceptions, conspiracy theories, or false beliefs. Results showed that larger models were not necessarily more truthful, and in some cases performed worse, highlighting a key alignment challenge.
Systematic Study of LLM Linguistic Uncertainty Markers and Intrinsic Confidence Calibration
This paper introduces 'marker internal confidence' (MIC) as a formalization of the intrinsic confidence a model associates with epistemic markers (e.g., 'it is likely...') in a given task domain. The authors present 7 metrics to evaluate MIC stability within and across distributions, finding that LLMs remain miscalibrated even under model-centric interpretation of marker meanings. Models struggle to differentiate markers by internal confidence across distributions, though they preserve a somewhat consistent ranking order across tasks. The work provides complementary evidence toward understanding faithful calibration in LLMs and highlights the need for more stable, aligned marker use.
Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
This paper investigates uncertainty quantification (UQ) for activation oracles—systems that make LLM internal activations human-legible—by evaluating 6 confidence estimation methods across 6,000 samples per oracle. The authors find that bootstrap mode frequency achieves the best calibration (ECE 5.7% vs. 25.5% for log-probability baseline on Qwen3-8B), while the log-prob baseline remains useful as a cheap triage signal. Experiments vary verbalizer and context prompts across two Qwen3 model sizes. Code and a patched trainer are released publicly.
Reverse Probing: Supervised Token-level Uncertainty Quantification for LLMs in Clinical Text
The paper introduces Reverse Probing, a novel uncertainty quantification framework designed specifically for clinical text summarization that estimates token-level uncertainty from pre-existing labeled summaries rather than sampling new outputs. It extracts uncertainty signals from four categories of internal model activations, treating text as a probe into the model's internal state. Evaluated on two expert-annotated clinical datasets, it outperforms eight adapted baselines on all metrics, achieving up to 4× higher AUPRC while reducing inference time and compute. Feature analysis identifies delta energy and neighborhood context as the most consistent predictors of uncertainty across models.
Aligning language models to follow instructions
OpenAI published a blog post describing their work on aligning language models to follow human instructions, corresponding to the InstructGPT research. This work introduced reinforcement learning from human feedback (RLHF) as a core technique for training models to be more helpful, honest, and aligned with user intent. The approach demonstrated that smaller instruction-tuned models could outperform larger base models on human preference evaluations, marking a foundational shift in how language models are trained and deployed.
Lessons learned on language model safety and misuse
OpenAI published a post summarizing their evolving thinking on language model safety and misuse in deployed systems. The piece is intended to share lessons with other AI developers facing similar challenges. It covers OpenAI's internal approaches to mitigating harmful outputs and misuse patterns observed in production.