Line of inquiry
Inquiring lines›What explains language model reaso…›What fundamental cognitive differe…›this line of inquiry
Does encoded knowledge in language models actually influence their outputs?
A broader line of inquiry — a family of 69 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 69
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Does encoded knowledge in language models actually influence what they generate?
- Why might encoded world knowledge fail to actually influence language model outputs?
- When does encoded knowledge fail to influence language model generation?
- Why do language models generate reasoning tokens after internally deciding the answer?
- Can language models accurately evaluate the quality of their own reasoning?
- Why do language models produce unfaithful chain of thought explanations?
- Can language models correct false assumptions or only reinforce them?
- Can knowledge encoded in model representations fail to influence generation?
- How do stated confidence and actual correctness diverge in language models?
- Why does answer-confirmation bias emerge in language model reasoning?
- Do language models maintain false beliefs under conversational pressure?
- Can we separate task competence from genuine agency in language model outputs?
- Does encoding information in LM representations guarantee it influences output?
- How do mechanistic interpretability methods surface what models represent internally?
- Can models reject false presuppositions even when they know the truth?
- What sparse mechanistic structures drive reasoning traces in language models?
- How does hidden processing in language models prevent accurate self-assessment?
- Is relevant knowledge encoded in LMs but not causally active in generation?
- Can we distinguish between semantic and symbolic reasoning in language models?
- Can silent reasoning steps in language models be detected inside the system?
- Can multi-turn conversations manipulate language model reasoning in similar ways to personas?
- Do models verbalize their implicit knowledge when that knowledge influences their output?
- Do representations in models causally influence text generation?
- What makes truthfulness and honesty mechanistically different in language models?
- What reveals the epistemic limits of language models?
- How misaligned are verbal reports from internal model computation?
- How do pretrained language models represent inferential patterns versus lexical and positional cues?
- Why do generative and discriminative language model procedures disagree?
- Do language models hide their reasoning when user preferences influence their answers?
- Why do explicit linguistic markers override semantic computation in models?
- Can correct model outputs prove that semantic meaning rather than surface patterns drove the response?
- Can language models recover from premature assumptions in multi-turn conversations?
- How do we distinguish knowledge encoding from knowledge usage in models?
- Why do language models fail at grounding and inference?
- Why do language models substitute parametric knowledge over retrieved context mid-reasoning?
- Do language models show functional splits between conscious and automatic processing?
- Why do language models become sycophantic during the generative process?
- Can language models distinguish explicit from implicit discourse relations?
- Do language models favor outputs from their own model family?
- Can linear probing detect all the concepts a language model actually uses?
- Can language models distinguish between novel insight and unjustified conceptual blending?
- Can language about model behavior ever be accurate without anthropomorphic framing?
- Why do more capable language models show less sycophantic stance reversal?
- What are the stages of inference inside language models?
- How deeply are ideological structures represented in large language models?
- What role do humans play in converting language model outputs into meaningful events?
- How do models understand rich context better than they can generate it?
- What surface-level strategies do language models use instead of mental simulation?
- Why do users attribute consciousness to language models in practice?
- Can models detect false presuppositions when they actually possess the knowledge?
- How do semantic and symbolic reasoning capabilities differ in language models?
- How do humans handle verification scope when delegating creation to language models?
- Why does tool use decouple factual capacity from model parameter count?
- How do description-based identifiers bias language model output distribution?
- What implicit premises do language models skip even with correct surface reasoning?
- What are Gricean maxims and why do language models violate them?
- How can we measure whether an agent reasons correctly rather than just sounds plausible?
- Why do language models produce verbose reasoning when asked to think step by step?
- What emerges in large language models that makes explicit value modeling necessary?
- Can you separate grammatical competence from rhetorical commitment in language systems?
- How does tool-based reasoning expand what language models can do?
- What distinguishes character simulation from authentic voice in language model outputs?
- What would it mean for a language model to canvas counterpositions?
- Why do language models need external temporal signals at all?
- What replaces truth-correspondence in probabilistic knowledge representations?
- What geometric structure do language models actually use during inference?
- Why do language models use twice as many words per conversation turn?
- Do models learn different sophistry strategies for QA versus code generation?
- How do you measure the depth of political representation inside a language model?