Unverified50% confidenceFactExact time
In brain-to-text generation tasks, generative models (especially LLM-based decoders) readily output content that is fluent linguistically but unrelated to the brain signals, i.e., "hallucination."
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLanguage models generate text based on probability, and tend to output generic praise, generalized emotional expressions, or plausible-sounding details that did not actually happen, the so-called "false memories".77% similarUnverifiedAn agent typically contains a large language model as its brain, a number of callable tools as its hands and feet, as well as memory and workflow orchestration mechanisms.77% similarUnverifiedLarge language models generate fabricated content (hallucinations) with high confidence, including inventing non-existent tool names and forging API return results75% similarVerifiedTransformer-based large language models use attention mechanisms to uniformly encode system prompts, user inputs, and externally retrieved content as homogenized token sequences, making it impossible for the model to distinguish trusted instructions from untrusted data at the semantic level.74% similarVerifiedThe root cause of hallucinations in large language models lies in the Transformer architecture's objective of maximizing probability during text generation, rather than prioritizing factual accuracy.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130314API
curl https://kongchang.com/api/v1/knowledge/claims/1130314MCP
get_claim(id=1130314)