| Humanity's last exam L Phan, A Gatti, Z Han, N Li, J Hu, H Zhang, CBC Zhang, M Shaaban, ... arXiv preprint arXiv:2501.14249, 2025 | 301 | 2025 |
| Distilling Reasoning Capabilities into Smaller Language Models K Shridhar*, A Stolfo*, M Sachan ACL 2023 (Findings), 2023 | 276* | 2023 |
| A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis A Stolfo, Y Belinkov, M Sachan EMNLP 2023, 2023 | 164 | 2023 |
| A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models A Stolfo*, Z Jin*, K Shridhar, B Schölkopf, M Sachan ACL 2023, 2022 | 78 | 2022 |
| Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models Y Hou, J Li, Y Fei, A Stolfo, W Zhou, G Zeng, A Bosselut, M Sachan EMNLP 2023, 2023 | 65 | 2023 |
| Improving Instruction-Following in Language Models through Activation Steering A Stolfo, V Balachandran, S Yousefi, E Horvitz, B Nushi ICLR 2025, 2024 | 59 | 2024 |
| Confidence Regulation Neurons in Language Models A Stolfo*, B Wu*, W Gurnee, Y Belinkov, X Song, M Sachan, N Nanda NeurIPS 2024, 2024 | 36* | 2024 |
| Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? A Opedal*, A Stolfo*, H Shirakami, Y Jiao, R Cotterell, B Schölkopf, ... ICML 2024, 2024 | 29 | 2024 |
| MIB: A Mechanistic Interpretability Benchmark A Mueller, A Geiger, S Wiegreffe, D Arad, I Arcuschin, A Belfki, YS Chan, ... ICML 2025, 2025 | 14 | 2025 |
| A Simple Unsupervised Approach for Coreference Resolution using Rule-based Weak Supervision A Stolfo, C Tanner, V Gupta, M Sachan Proceedings of the 11th Joint Conference on Lexical and Computational …, 2022 | 10 | 2022 |
| Groundedness in Retrieval-augmented Long-form Generation: An Empirical Study A Stolfo NAACL 2024 (Findings), 2024 | 8 | 2024 |
| Longtonotes: OntoNotes with Longer Coreference Chains K Shridhar, N Monath, R Thirukovalluru, A Stolfo, M Zaheer, A McCallum, ... EACL 2023 (Findings), 2022 | 7 | 2022 |
| Probing for Arithmetic Errors in Language Models Y Sun*, A Stolfo*, M Sachan EMNLP 2025 Oral, 2025 | 3 | 2025 |
| Antipodal Pairing and Mechanistic Signals in Dense SAE Latents A Stolfo, BP Wu, M Sachan Sparsity in LLMs (SLLM): Deep Dive into Mixture of Experts, Quantization …, 2025 | 2 | 2025 |
| Transferring Features Across Language Models With Model Stitching A Chen, J Merullo, A Stolfo, E Pavlick NeurIPS 2025 Spotlight, 2025 | 1 | 2025 |
| On the Emergence of Induction Heads for In-Context Learning T Musat, T Pimentel, L Noci, A Stolfo, M Sachan, T Hofmann arXiv preprint arXiv:2511.01033, 2025 | | 2025 |
| Dense SAE Latents Are Features, Not Bugs X Sun*, A Stolfo*, J Engels, B Wu, S Rajamanoharan, M Sachan, ... NeurIPS 2025, 2025 | | 2025 |
| Fluid Reasoning Representations D Kharlapenko, A Stolfo, A Conmy, M Sachan, Z Jin Mechanistic Interpretability Workshop at NeurIPS 2025, 2025 | | 2025 |
Mrinmaya SachanAssistant Professor, ETH ZürichVerified email at inf.ethz.ch
