Philippe Laban

@PhilippeLaban

Research Scientist @MSFTResearch. NLP/HCI Research.

New York City

Joined April 2022

Replies Reposts Media

Philippe Laban
@PhilippeLaban
Aug 25
Check out Yoonjoo's fantastic work on simulating users of different expertise levels? It makes progress on this concrete question: for a given task, how do we simulate how a novice vs. an expert would approach it? The validation study is a great example of careful research
Yoonjoo Lee
@yoonjoo_le2
Aug 24
AI assistants can provide correct, comprehensive information and still be poorly calibrated to the user: too difficult for novices, redundant for experts. KnowSim is a user simulator that tracks what a user knows and updates that knowledge as the conversation unfolds, so we can
00:00
Philippe Laban
@PhilippeLaban
Jul 28
Check out Jihoon's very interesting work on simulating long "situated" conversations where the user can change their mind, switch tasks, underspecify, etc. We need more work evaluating model performance outside of the single-turn, single-task, lab-like setting.
Jihoon Tack
@jihoontack
Jul 27
Excited to share my first work after joining @MSFTResearch! LLMs have entered the agentic era, and we now collaborate with agents on complex tasks over many turns of interaction. But does your agent actually follow what you intended? We show where agents get lost: LLMs Get Lost
Philippe Laban
@PhilippeLaban
Apr 21
New paper! LLMs Corrupt Your Documents When You Delegate LLMs are enabling a new way of working: delegated work, where users supervise an LLM as it edits documents on their behalf. Delegation requires trust: does the LLM complete tasks without introducing errors? We simulate
00:00
43
Philippe Laban
@PhilippeLaban
Feb 24
LLMs *Still* Get Lost In Multi-Turn Conversation. We re-ran experiments with newer models. Performance still drops, but with modest gains: mostly from improvements on the Python coding task. Also: Lost in Conversation will be presented at ICLR 2026 🎉🇧🇷
15
Philippe Laban
@PhilippeLaban
Feb 10
Very cool work!
Ai2
@allen_ai
Feb 10
LLMs often generate step-by-step instructions, from real-world tasks (how do I file taxes?) to plans for AI agents. Improving this is hard: outputs can sound fluent for steps that don't work, and current datasets cover few domains. How2Everything evals/trains for this at scale.