Professor for Information Systems, Northeastern University; Interested in collective intelligence, human-AI teaming & crowdsourcing
Boston, MA
Joined January 2010
- Tweets1.6K
- Following441
- Followers1.5K
- Likes329
Pinned Tweet
"Synergy" is everywhere in AI: attention heads, agent swarms, human-AI teams. But without a formal definition, those claims can’t be compared or disputed. Partial information decomposition gives emergence claims a falsifiable test. #NeurIPS SPOTLIGHT 🔦
Christoph Riedl retweeted
Training data attribution methods are notoriously difficult to develop, and even to just evaluate! What the heck is ground truth for "most important training document?"
I am very proud of our undergrad @lamsheeper who devised a clever solution, which led to several discoveries.
Can we trace an AI model's answers back to its training data?
Surprisingly, even when we know exactly which documents taught a model a fact, attribution methods often fail to find them.
Our CATT benchmark investigates why and uncovers two simple fixes
catt.baulab.info🧵
Christoph Riedl retweeted
📢 ✨ Symposium at #AOM2026: Augmenting Human Potential with Generative AI: Opportunities & Risks
Excited to be co-organizing this with @mattgroh!
Come join us to hear from the brilliant @alexolegimas @criedl @hamsabastani @ShiriM528 & Anita Woolley!
Our article "Complex Contagion in Social Networks: Causal Evidence from a Country-Scale Field Experiment” published in Sociological Science won the James Coleman Best Paper Award sociologicalscience.com/arti…
@davidlazer and Jaemin Lee
Christoph Riedl retweeted
Please join us at NEMI 2026, the 3rd New England Mechanistic Interpretability Workshop!
August 14th at Boston University.
Register now:
nemiconf.github.io/summer26/
A remarkable time for AI. Come share your insights and research on the mechanisms inside our models.
Christoph Riedl retweeted
AI is not just a tool, it can reshape how people think, communicate, & connect.
New in #TOCHI: “Cognitive Spillover in Human-AI Teams” shows that AI use changes shared language & team cohesion.
Read:dl.acm.org/doi/abs/10.1145/3…
Authors: @criedl , Saiph Savage, Josie Zvelebilova
Think AI only affects the person using it? Our experiments show AI reshapes shared language, collective attention, mental models, AND social cohesion among human teammates. AI reshapes the cognitive ecology of teamwork
The complex contagion story, updated:
✅ Social reinforcement is real [1]
❌ You don't need hypergraphs to model it [1,2]
❌ You don't need simultaneous group interaction [1,2,3]
❌ It doesn't mean clustered networks win [3]
Christoph Riedl retweeted
At #ICLR2026 Sci4DL (101B 10:00AM) I will be talking about @kevinlu4588's new work cracking open protein folding models to decode their internals.
folding.baulab.info/
Our lab is looking to fill a post-doc position to do research on collective intelligence in AI and human-AI systems. More details here christophriedl.net/jobs.html
Evidence that multi-agent LLMs develop emergent coordination and specialized roles—especially when instructed to "think about others" (ie ToM). No free lunch tho: strong performance needs both alignment and complementarity #ICLR
Christoph Riedl retweeted
2026 is a whirlwind year for AI.
Underlying it all: the greatest scientific mystery of our age. How does a neural network think?
I talked w @oliver_whang22 in NYTimes Magazine, on how AI interpretability is a tangle of structure waiting to be unraveled:
nytimes.com/2026/04/15/magaz…
