Influential Papers

Advocates and proposes directions for systematic AI evalutions involving real human interaction.

By creating an LM architecture in which input tokens have a direct log-linear effect on the output, we can intervene precisely on the model output.

Kontorovich reflects on how AI and formal verification systems like Lean are reshaping mathematical practice, intended for ICM 2026. What I find compelling is that the examples come from someone deeply embedded in both traditional research mathematics and these new technologies. The discussion of the 'Bitter Lesson' applied to mathematics is sobering, and the concrete examples of what formal verification looks like in practice are clarifying. A useful document for thinking about what 'doing math' might mean going forward.

Interesting way to automatically label datasets using mutual predictability and logical consistency.

By probing with sparsity constraints, we can identify not only if model activations represent some feature but whether specific neurons encode certain features.

Advocates for rhetoric over composition as the methodology for writing pedagogy in the AI era.

Really nice argumentative piece on why we can build much better AI interfaces than chat interfaces.

Really nice overview of how NLP methods can be applied to understand literary culture.

Creates a DSL and program optimizer to apply LLMs to large/complex document processing. Provides a more structured and visible way to interact with LLMs on large text corpuses.

A talk on the role of examples in mathematical practice. Kalai's observation that 'the methods for coming up with useful examples in mathematics are even less clear than the methods for proving mathematical statements' resonates with me -- examples are often the hardest and most creative part of mathematical work, yet we rarely discuss the craft of finding them.

Argues that human-AI collaborations represent a continuation of our basic nature to build hybrid thinking systems that fluidly incorporate non-biological resources. Discusses 'extended cognitive hygiene' as essential for critically evaluating what we incorporate into our digitally extended minds.

Cool classic HCI-style exploration into a new interaction for code editing using visual sketching, interpreted by VLMs.

A recognition that not only must AI 'align to' human (values, behavior, knowledge, etc.) (-- whatever this means), but we also need to think about how humans might 'align' to AI by working with AI-structured systems. This paper recognizes social 'looping effects' brought about by AI and its behavior.

Useful outline of what HCI researchers can contribute to 'AGI'. It's not obvious (and people may fear that) interaction problems will be solved by AGI. Perhaps not?

The title is all you need! Super cool!

A clean and simiple method for steering model behavior using discovered representations specified by positive and negative samples. I feel this has strong potential for helping out metaphor-/sense-making in the HCI space.

This paper defines LLM operations for extracting concepts from large amounts of unstructured text, useful for social sciences inquiry.

Makes a really interesting case for disambiguating prompt 'engineering' from a possible 'prompt science'. The writing is very compelling. A helpful analogy presented in the paper is the idea that plant breeders were able to infer a lot of the internal structure of plants before genetic theory explained it. Not sure where I stand on this still but it's given me a lot to think about, especially w.r.t. 'aesthetic' concerns in ML research that bar 'prompting' from being seen as a legitimate research method. I do agree with the paper's claim that many important works in NLP are basically interfaces/structures upon prompting, and we shouldn't be afraid to more closely associate them with a 'prompt science'.