Alessandro Stolfo

27 papers A* 7Journal 15Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Fluid Representations in Reasoning Models. CoRR Dmitrii Kharlapenko, Alessandro Stolfo, Arthur Conmy, Mrinmaya Sachan, Zhijing Jin
2025	J	`jnl`	Dense SAE Latents Are Features, Not Bugs. CoRR Xiaoqing Sun, Alessandro Stolfo, Joshua Engels, Ben Wu, Senthooran Rajamanoharan, Mrinmaya Sachan, Max Tegmark
2025	A*	`conf`	Improving Instruction-Following in Language Models through Activation Steering. ICLR Alessandro Stolfo, Vidhisha Balachandran, Safoora Yousefi, Eric Horvitz, Besmira Nushi
2025	A*	`conf`	MIB: A Mechanistic Interpretability Benchmark. ICML Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fried Fiotto-Kaufman, Tal Haklay, Michael Hanna, Jing Huang, Rohan Gupta, Yaniv Nikankin, Hadas Orgad, Nikhil Prakash, Anja Reusch, Aruna Sankaranarayanan, Shun Shao, Alessandro Stolfo, Martin Tutek, Amir Zur, David Bau, Yonatan Belinkov
2025	J	`jnl`	MIB: A Mechanistic Interpretability Benchmark. CoRR Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fiotto-Kaufman, Tal Haklay, Michael Hanna, Jing Huang, Rohan Gupta, Yaniv Nikankin, Hadas Orgad, Nikhil Prakash, Anja Reusch, Aruna Sankaranarayanan, Shun Shao, Alessandro Stolfo, Martin Tutek, Amir Zur, David Bau, Yonatan Belinkov
2025	J	`jnl`	On the Emergence of Induction Heads for In-Context Learning. CoRR Tiberiu Musat, Tiago Pimentel, Lorenzo Noci, Alessandro Stolfo, Mrinmaya Sachan, Thomas Hofmann
2025	A*	`conf`	Probing for Arithmetic Errors in Language Models. EMNLP Yucheng Sun, Alessandro Stolfo, Mrinmaya Sachan
2025	J	`jnl`	Probing for Arithmetic Errors in Language Models. CoRR Yucheng Sun, Alessandro Stolfo, Mrinmaya Sachan
2025	J	`jnl`	Transferring Features Across Language Models With Model Stitching. CoRR Alan Chen, Jack Merullo, Alessandro Stolfo, Ellie Pavlick
2024	A*	`conf`	Confidence Regulation Neurons in Language Models. NeurIPS Alessandro Stolfo, Ben Wu, Wes Gurnee, Yonatan Belinkov, Xingyi Song, Mrinmaya Sachan, Neel Nanda
2024	J	`jnl`	Confidence Regulation Neurons in Language Models. CoRR Alessandro Stolfo, Ben Wu, Wes Gurnee, Yonatan Belinkov, Xingyi Song, Mrinmaya Sachan, Neel Nanda
2024	A*	`conf`	Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? ICML Andreas Opedal, Alessandro Stolfo, Haruki Shirakami, Ying Jiao, Ryan Cotterell, Bernhard Schölkopf, Abulhair Saparov, Mrinmaya Sachan
2024	J	`jnl`	Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? CoRR Andreas Opedal, Alessandro Stolfo, Haruki Shirakami, Ying Jiao, Ryan Cotterell, Bernhard Schölkopf, Abulhair Saparov, Mrinmaya Sachan
2024	—	`conf`	Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study. NAACL-HLT (Findings) Alessandro Stolfo
2024	J	`jnl`	Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study. CoRR Alessandro Stolfo
2024	J	`jnl`	Improving Instruction-Following in Language Models through Activation Steering. CoRR Alessandro Stolfo, Vidhisha Balachandran, Safoora Yousefi, Eric Horvitz, Besmira Nushi
2023	—	`conf`	A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models. ACL (1) Alessandro Stolfo, Zhijing Jin, Kumar Shridhar, Bernhard Schölkopf, Mrinmaya Sachan
2023	A*	`conf`	A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis. EMNLP Alessandro Stolfo, Yonatan Belinkov, Mrinmaya Sachan
2023	—	`conf`	Distilling Reasoning Capabilities into Smaller Language Models. ACL (Findings) Kumar Shridhar, Alessandro Stolfo, Mrinmaya Sachan
2023	—	`conf`	Longtonotes: OntoNotes with Longer Coreference Chains. EACL (Findings) Kumar Shridhar, Nicholas Monath, Raghuveer Thirukovalluru, Alessandro Stolfo, Manzil Zaheer, Andrew McCallum, Mrinmaya Sachan
2023	A*	`conf`	Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models. EMNLP Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut, Mrinmaya Sachan
2023	J	`jnl`	Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models. CoRR Yifan Hou, Jiaoda Li, Yu Fei, Alessandro Stolfo, Wangchunshu Zhou, Guangtao Zeng, Antoine Bosselut, Mrinmaya Sachan
2023	J	`jnl`	Understanding Arithmetic Reasoning in Language Models using Causal Mediation Analysis. CoRR Alessandro Stolfo, Yonatan Belinkov, Mrinmaya Sachan
2022	J	`jnl`	A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models. CoRR Alessandro Stolfo, Zhijing Jin, Kumar Shridhar, Bernhard Schölkopf, Mrinmaya Sachan
2022	—	`conf`	A Simple Unsupervised Approach for Coreference Resolution using Rule-based Weak Supervision. *SEM@NAACL-HLT Alessandro Stolfo, Chris Tanner, Vikram Gupta, Mrinmaya Sachan
2022	J	`jnl`	Distilling Multi-Step Reasoning Capabilities of Large Language Models into Smaller Models via Semantic Decompositions. CoRR Kumar Shridhar, Alessandro Stolfo, Mrinmaya Sachan
2022	J	`jnl`	Longtonotes: OntoNotes with Longer Coreference Chains. CoRR Kumar Shridhar, Nicholas Monath, Raghuveer Thirukovalluru, Alessandro Stolfo, Manzil Zaheer, Andrew McCallum, Mrinmaya Sachan