Amit Sharma

New paper: On the unreasonable effectiveness of LLMs for causal inference. GPT4 achieves new SoTA on a wide range of causal tasks: graph discovery (97%, 13 pts gain), counterfactual reasoning (92%, 20 pts gain) & actual causality. How is this possible?🧵 arxiv.org/abs/2305.00050

🚀 Meet FrugalRAG at #ICML2025 in Vancouver 🇨🇦! 📍 July 18 – VecDB Workshop, West 208–209 📍 July 19 – ES-FoMO Workshop, East Exhibition Hall A Come chat with me and @naga86 and learn how we're rethinking training efficiency and inference latency for RAG systems. 🧵

Extremely happy to have our work on Teaching Transformers Causal Reasoning through Axiomatic Training accepted at ICML!!! Very proud of this work and the potential avenues it opens up on improving causal reasoning capabilities of LLMs.

Sounds very cool. Here is link to paper (hard to find since it seems to be a TMLR paper, not an official ICLR paper): arxiv.org/abs/2305.00050

PywhyLLM: Creating an API for language models to interact with causal methods and vice versa. v0.1 out, welcome feedback. If you are at #iclr2025, come check out our poster today at 10am-12:30pm. github.com/py-why/pywhyllm

Job Alert: @MSFTResearch India is hiring postdocs! A chance to work with some amazing colleagues while doing world-class research. Apply here: jobs.careers.microsoft.com/global/en/job/… DM me if interested in ML/reasoning/causality.

Excited to present Axiomatic Training at #NeurIPS2024, a new paradigm to teach causal reasoning to language models! I try to summarize what LLM systems can do today and what new training paradigms we need to improve their causal reasoning. Slides: amitsharma.in/talk/teaching-…

We are happy 😁 to announce 📢 the First Workshop on Causality and Large Models (C♥️LM) at #NeurIPS2024 📜 Submission deadline: September 06 (4-6 pages) 💻 Website: calm-workshop-2024.github.io

Teaching Transformers Causal Reasoning through Axiomatic Training The ability to reason causally is increasingly recognized as a crucial skill for AI systems to interact effectively with the real world. However, teaching LLMs to understand and apply causal relationships has…

Can we teach Transformers Causal Reasoning? We propose Axiomatic Framework, a new paradigm for training LMs. Our 67M-param model, trained from scratch on simple causal chains, outperforms billion-scale LLMs and rivals GPT-4 in inferring cause-effect relations over complex graphs

We take a closer look at prompt optimization problem & develop UniPrompt for learning LM prompt for a task from scratch. We argue when greedy opt. methods could help in this discrete & challenging problem. @GurushaJuneja, @amt_shrma, Hua Li & Jian Jiao. arxiv.org/pdf/2406.10504

PyWhy talk series: DAGitty. This Monday @JohannesTextor will be talking about the amazing dagitty tool and lessons learnt about using causal graphs in science. Monday, Feb 26, 8am PT/9:30pm IST. Join here: groups.google.com/g/pywhy-causal…