Theme of inquiry
How do learned model representations diverge from human language understanding?
A question within its area, explored through 7 lines of inquiry below — each a family of specific questions the research asks.
60 specific questions
- How do model compression biases differ from human conceptual representation strategies?
- Does encoding information in LM representations guarantee it influences output?
- How should meaning spaces be systematically modeled across different applications?
- Can we balance interpretability with the efficiency gains of compressed inter-model communication?
- How do corpus statistics shape the abstraction hierarchy in language model representations?
- Why does language compression via statistical dependencies capture cultural and situated language use?
- How does the compression view extend from trained models to training objectives?
76 specific questions
- Do language models show the same truth bias as humans?
- Do language models systematically overestimate accuracy on collective behavior tasks?
- Do language models actively adopt false beliefs under sustained conversational pressure?
- Do language models exhibit the same causal biases that humans show?
- How vulnerable are language models themselves to multi-turn persuasive pressure?
- Why do language models presume common ground instead of establishing it?
- Can language models accurately evaluate the quality of their own ideas?
29 specific questions
- Can models learn to ask clarifying questions instead of making assumptions?
- Should LLMs query users back when presented with under-specified scenarios?
- Can LLMs learn to ask clarifying questions instead of guessing?
- Can language models ask clarifying questions when sentences are ambiguous?
- Do models naturally learn to ask clarifying questions without explicit supervision?
- Can language systems learn when to ask for clarification instead of choosing one reading?
- What makes a clarifying question aligned with user interests versus structurally sound?
34 specific questions
- Do standard language benchmarks underestimate what LLMs can actually do?
- Why do NLP benchmarks exclude ambiguous instances from evaluation?
- Why do NLP benchmarks systematically exclude ambiguous test cases from evaluation?
- Why do standard NLP benchmarks hide the most critical language limitations?
- Why do NLP benchmarks hide LLM failures in ambiguity handling?
- Why do benchmark scores rise while reasoning quality declines?
- Why do benchmark tests fail to detect LLM comprehension gaps?
21 specific questions
- How does the articulatory substrate explain direct speech-to-speech superiority over transcription pipelines?
- Do speech models learn the articulatory processes that produce acoustic signals?
- Do speech encoders actually learn the physics of how vocal tracts produce sound?
- Can speech embeddings carry articulatory structure that text cannot?
- How do speech encoders learn articulatory physics without phonetic labels?
- Why do current speech benchmarks fail to measure reasoning over audio?
- What information does transcription destroy that direct speech-to-speech models preserve?
72 specific questions
- Do language models learn surface patterns instead of underlying linguistic principles?
- Why does context information fail to override prior training associations?
- Do language models learn surface patterns that appear generalizable but actually fail under shift?
- Do newer language models diverge further from human lexical patterns?
- Do LLMs learn surface patterns instead of genuine linguistic structure?
- Do instruction-tuned models learn tasks or just output format distributions?
- Do language models actually learn linguistic structure or just surface statistics?
66 specific questions
- Can language models accurately evaluate the quality of their own reasoning?
- Can we distinguish between semantic and symbolic reasoning in language models?
- Why do language models produce unfaithful chain of thought explanations?
- Why do language models generate reasoning tokens after internally deciding the answer?
- Can language models correct false assumptions or only reinforce them?
- Does more thinking always improve language model accuracy?
- How does hidden processing in language models prevent accurate self-assessment?