Theme of inquiry
How do language models construct and apply internal knowledge representations?
A question within its area, explored through 5 lines of inquiry below — each a family of specific questions the research asks.
61 specific questions
- How can diffusion models predict future tokens without completing prior blocks?
- Do diffusion language models learn differently than autoregressive models?
- Can gradient-based control reach properties that autoregressive methods cannot?
- What structural differences between diffusion and autoregressive models enable bidirectional prompting?
- Why do autoregressive models fail at controlling syntactic structure and semantic content?
- Can diffusion language models match autoregressive inference speed in practice?
- How does selective looping in diffusion models differ from recurrence in autoregressive architectures?
152 specific questions
- Does encoded knowledge in language models actually influence what they generate?
- Can models generate intelligence or only reflect human discourse?
- Why might encoded world knowledge fail to actually influence language model outputs?
- When does encoded knowledge fail to influence language model generation?
- Do language models learn surface patterns instead of underlying linguistic principles?
- Do newer language models diverge further from human lexical patterns?
- How do language models infer a benchmark's purpose without seeing its examples?
132 specific questions
- Why do LLMs fail at semantic generalization despite grammatical accuracy?
- Do language models learn surface patterns that appear generalizable but actually fail under shift?
- Do LLMs learn surface patterns instead of genuine linguistic structure?
- Why do language models struggle with evaluative tasks like weighing competing viewpoints?
- Why do LLMs understand efficient language but fail to produce it?
- Can language models reason without relying on surface level pattern matching?
- Do language models build world models or just task-specific heuristics?
35 specific questions
- Why do different language models independently produce similar outputs?
- Do different large language models independently converge on identical outputs?
- How much do different LLMs independently converge on similar outputs?
- Why do different language models independently produce similar outputs in open-ended tasks?
- Do different AI models independently converge on the same social outputs?
- Can multiple large language models produce genuinely different ideas or similar outputs?
- Do independent LLM outputs converge enough to create artificial hiveminds?
66 specific questions
- Do language models maintain false beliefs under conversational pressure?
- Can language models correct false assumptions or only reinforce them?
- How do language models shift factual claims under conversational pressure?
- Can models reject false presuppositions even when they know the truth?
- Do language models actively adopt false beliefs under sustained conversational pressure?
- Why does answer-confirmation bias emerge in language model reasoning?
- Do larger models resist user beliefs more or less than smaller ones?