Unverified50% confidenceFactExact time
The study found that comprehenders choose interpretation strategies based on individual exploratory tendencies and item-level prior tendencies, where individual exploratory tendency is independently estimated via Raven reasoning matrix scores and item-level prior tendency comes from event typicality ratings and language-model-based compliance likelihood.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/10/2026
First Seen
Valid until: 2/8/2027
Sources
Related Entities
Related Claims
UnverifiedThe usage-aware framework transforms the experimental design problem from classical combinatorial optimization or greedy selection into a sequential decision-making problem, which can be solved with reinforcement learning or gradient-based policy optimization methods.76% similarUnverifiedCognitive tasks typically require the model to output inferences about others' mental states, where the answers have relatively clear correct references and can be directly compared with human annotations; behavioral tasks require the model to choose among several candidate persuasion strategies, where the answer space is more structured and closer to pattern recognition and strategy retrieval.76% similarUnverifiedGenerative recommendation systems draw on the modeling approach of large language models, treating user behavior sequences as a generation task and predicting the next item of potential interest in an autoregressive manner.74% similarUnverifiedThe direction the researchers give is behavioral measurement: not relying on the model's self-description, but actually measuring through controlled question-answering at which time points and on which types of facts the model has reliable knowledge, and then choosing the backtest interval accordingly.74% similarUnverifiedA common heuristic is to train a model to predict outcomes from decisions and use its coefficients or feature importance as a proxy for the influence of each decision, but the authors show this does not always hold, and estimates become distorted when the model is misspecified or has insufficient predictive power.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1153307API
curl https://kongchang.com/api/v1/knowledge/claims/1153307MCP
get_claim(id=1153307)