Unverified50% confidenceTradeoffExact time
Choosing a small causal language model reduces computational cost and makes experimental phenomena easier to observe, since larger models may exhibit entirely different resistance to small-scale fabricated corpora.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
Unverified结构化、类型强约束的工具响应可以显著降低模型在解析阶段产生误解的概率80% similarUnverifiedModels that more substantially reconstruct their own representations based on example content actually benefit more from few-shot prompting, which is contrary to the popular disruption hypothesis.78% similarVerifiedIf a low-cost model has insufficient reasoning capability, it leads to more retry rounds, and the hidden costs of accumulated failed retries may exceed those of a high-cost, high-efficiency solution (the paradox of "cheap models actually being more expensive").78% similarUnverifiedResearchers have found that fine-tuning only a small number of model parameters is sufficient to remove safety alignment (de-alignment attacks), and that certain jailbreak prompts can transfer across different models.77% similarVerifiedSmaller models are more prone to embedding collapse than larger models, due to reasons including limited parameter capacity, a tendency toward optimization shortcuts, and amplified anisotropy issues.77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949185API
curl https://kongchang.com/api/v1/knowledge/claims/949185MCP
get_claim(id=949185)