claim

active

claim:of-the-three-categories-of-giving-false-information-only-confabulation-is-directly-applicable-to-llm-based-dialogue-agents

Of the three categories of giving false information, only confabulation is directly applicable to LLM-based dialogue agents

The paper distinguishes confabulation from good-faith error and deliberate deception, arguing the first is intrinsic to LLMs

Neighborhood — ranked by edge-count

Claims (1)

claim

It makes little sense to speak of an LLM dialogue agent's beliefs or intentions in a literal sense, so it cannot assert a falsehood in good faith nor deliberately deceive
supports
Philosophical claim grounding the analysis of deception in dialogue agents

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Confabulation is the natural mode for an LLM-based dialogue agent in the absence of mitigationclaim0.835
Characterisation of LLM default behaviour as producing false information without intent
NLA explanations confabulate false specifics but maintain thematic fidelity; claims repeated across tokens more likely true than isolated claims.claim0.794
Core limitation and usage heuristic: read NLAs for themes rather than individual factual claims; cross-check with original context.
Aside from basic detection and identification, other details of the model's response about injected thoughts may be confabulatedclaim0.779
Acknowledges that the model's additional descriptions of its experience are unverified.
With an LLM-based dialogue agent, it is role play all the way down — there is no such thing as the true authentic voice of the base modelclaim0.777
The paper's strong claim that there is no underlying authentic agent behind the simulator, only layers of role play
Confabulation is not a distinguishing feature between AI and biological cognition — all cognitive systems confabulate, telling stories based on their world-model without infallible access to lower-level processes.claim0.769
Directly challenges the use of confabulation as a wedge between AI and genuine cognition
LLMs linearly represent truth-relevant information beyond the plausibility of text, as evidenced by probes trained on likely performing poorly on anti-correlated datasetsclaim0.768
Establishes that the observed linear structure is not merely a representation of text probability
What remains after ruling out sycophancy and confabulation are interpretations in which self-referential processing drives models to claim subjective experience in ways that either actually reflect emergent phenomenology or constitute sophisticated simulation thereofclaim0.767
The paper's honest statement of the residual interpretive ambiguity after all controls
If a dialogue agent is prompted with knowledge of its own LLM nature, it will enact a superposition of theories of selfhood, narrowing as conversation proceedshypothesis0.766
Conditional prediction about how a well-informed dialogue agent would handle questions of personal identity