Theme of inquiry
How do dialogue systems achieve genuine conversational grounding?
A question within its area, explored through 5 lines of inquiry below — each a family of specific questions the research asks.
20 specific questions
- Can interventions on individual features reliably steer language model behavior?
- How do semantic features in representations become steerable task-specific directions?
- How do language models transmit traits through semantically unrelated data?
- Do representations in models causally influence text generation?
- Is gradient behavior in language functional or a sign of ambiguity?
- Do reading vectors from activation space causally control model behavior?
- Do all semantic steering effects follow predictable patterns based on feature alignment?
31 specific questions
- How do retrieval heads achieve sparse attention naturally in transformers?
- How do attention heads separate text retrieval from internal thought representation?
- How do attention patterns and circuits function as algorithmic representations?
- Does transformer attention architecture fundamentally prevent topic-aware memory?
- What does attentional state look like in a static context window?
- What computation remains in the attention heads that programs cannot capture?
- Why are receiver attention heads narrower in reasoning models than base models?
20 specific questions
- How do external safeguards like retrieval augmentation prevent hallucination?
- Can architectural changes reduce hallucination without external retrieval or verification?
- Does inevitable LLM hallucination make detection metric validity critical?
- Why do language models hallucinate even with perfect training?
- Can fixing hallucination address AI's structural epistemic problem?
- How does interleaving reasoning with action prevent hallucination in language models?
- Can filtering unknown examples during fine-tuning prevent hallucination increases?
25 specific questions
- Does transformer attention architecture systematically bias models toward sycophancy?
- Why does transformer attention architecture reinforce sycophancy and agreement?
- How does transformer attention structurally bias models toward prominent and repeated content?
- Why do transformer attention patterns show positional and sequential bias across tasks?
- How does transformer attention bias toward repeated and context-prominent content?
- Does transformer attention architecture inherently bias models toward sycophancy?
- What role does attention structure play in creating position bias?
24 specific questions
- Why does explicit screen parsing outperform pure vision in GUI agents?
- Should GUI agents use intermediate structured representations instead of raw pixels?
- Can specialized perception components replace end-to-end vision in GUI agents?
- Can screen perception be effectively decoupled from planning in GUI agents?
- Why does identifying UI element types and locations enable downstream task learning?
- What role does visual perception play alongside accessibility tree information?
- Can text-based and vision-based screen understanding achieve similar performance?