REVIEW 7 cited by
Forecasting Rare Language Model Behaviors
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Forecasting Rare Language Model Behaviors
read the original abstract
Standard language model evaluations can fail to capture risks that emerge only at deployment scale. For example, a model may produce safe responses during a small-scale beta test, yet reveal dangerous information when processing billions of requests at deployment. To remedy this, we introduce a method to forecast potential risks across orders of magnitude more queries than we test during evaluation. We make forecasts by studying each query's elicitation probability -- the probability the query produces a target behavior -- and demonstrate that the largest observed elicitation probabilities predictably scale with the number of queries. We find that our forecasts can predict the emergence of diverse undesirable behaviors -- such as assisting users with dangerous chemical synthesis or taking power-seeking actions -- across up to three orders of magnitude of query volume. Our work enables model developers to proactively anticipate and patch rare failures before they manifest during large-scale deployments.
Forward citations
Cited by 7 Pith papers
-
Forecasting Future Behavior as a Learning Task
Behavior Forecasters trained on LRM trajectories outperform larger models in predicting repeatability and input sensitivity at low cost.
-
Where do LLMs Fall Short in CBT-Guided Affective Reasoning?
CBT knowledge alone does not change LLM therapeutic strategy; MCoT guidance yields only ~1.2–1.3% Protocol Leverage Force and models stay biased toward Validation & Reflection.
-
Predicting LLM Safety Before Release by Simulating Deployment
Regenerating model responses on de-identified production conversation prefixes yields pre-deployment misbehavior rate forecasts that track realized production rates within 2-5x and outperform adversarial-prompt baselines.
-
SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings
SCARCE uses learned latent representations and adaptive thresholding to achieve 400-500x lower error than traditional subset simulation for MNIST misclassification and low relative error on LLM jailbreak probabilities.
-
Comprehensive AI governance requires addressing non-model gains
Non-model gains via inference, systems, and assets can drive AI capabilities independently of base models, requiring governance beyond model-level evaluation and mitigation.
-
Estimating Tail Risks in Language Model Output Distributions
Importance sampling via activation-steered unsafe proposal models estimates rare harmful-output probabilities in language models with 10-20x fewer samples than brute-force Monte Carlo.
-
Estimating Tail Risks in Language Model Output Distributions
Importance sampling with unsafe model variants estimates tail probabilities of harmful language model outputs using 10-20x fewer samples than brute-force Monte Carlo.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.