Unverified50% confidenceFactExact time
Hebbia defines "citation source selection" as the ability of a model, when faced with a question, to find the correct document or the correct source to answer it.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
Unverified口语化采样通过在提示词中要求模型生成一组候选答案并显式说出每个答案对应的概率分布来提升多样性65% similarUnverifiedHishob's core design principle is "code computes, model explains": all totals, averages and matching are computed by code, the model is only responsible for finding correlations, explaining causes and suggesting actions, and the model never does money addition.62% similarUnverifiedThe 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.62% similarUnverifiedMulti-hop reasoning refers to complex questions that require sequentially or jointly extracting information from multiple sources to answer; implementation methods include iterative retrieval, graph-structured retrieval, and agent-based approaches, which improve complex question answering but increase latency and the probability of errors.61% similarUnverifiedIntent-based prompting emphasizes explaining "why this output is needed," prompting the model to reason about the goal during generation, thereby aligning more closely with real scenarios in information filtering, depth adjustment, and format selection.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1101639API
curl https://kongchang.com/api/v1/knowledge/claims/1101639MCP
get_claim(id=1101639)