Clement Neo

15 papers A* 5Journal 9Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Large Language Models.
CoRR
Philip Quirke, Narmeen Oozeer, Chaithanya Bandi, Amir Abdullah, Jason Hoelscher-Obermaier, Jeff M. Phillips, Joshua Greaves, Clement Neo, Fazl Barez, Shriyash Upadhyay
2025 J jnl
The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features.
CoRR
Jeremias Lino Ferrao, Matthijs van der Lende, Ilija Lichkovski, Clement Neo
2025 A* conf
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research.
EMNLP
Abir Harrasse, Philip Quirke, Clement Neo, Dhruv Nathawani, Luke Marks, Amir Abdullah
2025 J jnl
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research.
CoRR
Philip Quirke, Clement Neo, Abir Harrasse, Dhruv Nathawani, Amir Abdullah
2025 A* conf
Towards Interpreting Visual Information Processing in Vision-Language Models.
ICLR
Clement Neo, Luke Ong, Philip Torr, Mor Geva, David Krueger, Fazl Barez
2025 A* conf
Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs.
ICLR
Nguyen Nhat Minh, Andrew Baker, Clement Neo, Allen G. Roush, Andreas Kirsch, Ravid Shwartz-Ziv
2025 — conf
Understanding Refusal in Language Models with Sparse Autoencoders.
EMNLP (Findings)
Wei Jie Yeo, Nirmalendu Prakash, Clement Neo, Ranjan Satapathy, Roy Ka-Wei Lee, Erik Cambria
2025 J jnl
Understanding Refusal in Language Models with Sparse Autoencoders.
CoRR
Wei Jie Yeo, Nirmalendu Prakash, Clement Neo, Roy Ka-Wei Lee, Erik Cambria, Ranjan Satapathy
2024 J jnl
Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts.
CoRR
Jacob Haimes, Cenny Wenner, Kunvar Thaman, Vassil Tashev, Clement Neo, Esben Kran, Jason Schreiber
2024 J jnl
Increasing Trust in Language Models through the Reuse of Verified Circuits.
CoRR
Philip Quirke, Clement Neo, Fazl Barez
2024 A* conf
Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions.
EMNLP
Clement Neo, Shay B. Cohen, Fazl Barez
2024 J jnl
Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions.
CoRR
Clement Neo, Shay B. Cohen, Fazl Barez
2024 A* conf
Interpreting Learned Feedback Patterns in Large Language Models.
NeurIPS
Luke Marks, Amir Abdullah, Clement Neo, Rauno Arike, David Krueger, Philip Torr, Fazl Barez
2024 J jnl
Min P Sampling: Balancing Creativity and Coherence at High Temperature.
CoRR
Minh Nguyen, Andrew Baker, Andreas Kirsch, Clement Neo
2024 J jnl
Towards Interpreting Visual Information Processing in Vision-Language Models.
CoRR
Clement Neo, Luke Ong, Philip Torr, Mor Geva, David Krueger, Fazl Barez