10 papers
CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse
Samuel Schapiro, Core Francisco Park, Felix Sosa +1
Divergent thinking is a crucial aspect of creativity, yet large language models (LLMs) tend to consistently generate similar responses to open-ended questions, in what has been ter…
Containment Verification: AI Safety Guarantees Independent of Alignment
Royce Moon, Lav R. Varshney
Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable…
A Pāninian Foundation for Indic Language Processing
Ritwik Banerjee, Lav R. Varshney
More than a billion people communicate in Indic languages, yet the natural language processing infrastructure serving them remains fragmented and underdeveloped. The cause is struc…
Distributed Experimental Design: Bayes-optimal Fusion of Local Designs
Nagananda K G, Lav R. Varshney, Pramod K. Varshney
We develop a decision-theoretic framework for distributed Bayesian experimental design in which local agents evaluate candidate experiments using expected information gain and tran…
Information Lattice Learning as Probabilistic Graphical Model Structure Learning
Haizi Yu, Lav R. Varshney
Information lattice learning (ILL) learns interpretable rules of a signal by alternately projecting the signal onto a partition lattice that encodes a hierarchy of abstractions and…
Context-Gated Associative Retrieval: From Theory to Transformers
Moulik Choraria, Argyrios Gerogiannis, Vidhata Jayaraman +2
Hopfield networks and their generalizations have established deep connections among biological associative memories, statistical physics, and transformers. Yet most models treat re…
A Theoretical Game of Attacks via Compositional Skills
Xinbo Wu, Huan Zhang, Abhishek Umrawal +1
As large language models grow increasingly capable, concerns about their safe deployment have intensified. While numerous alignment strategies aim to restrict harmful behavior, the…
Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations
Kalyan Cherukuri, Lav R. Varshney
Large language models (LLMs) hallucinate: they produce fluent outputs that are factually incorrect. We present a geometric dynamical systems framework in which hallucinations arise…
Know Thy Reasoner: Not All Language Models Explore Alike
Moulik Choraria, Argyrios Gerogiannis, Anirban Das +4
Compute scaling for LLM reasoning trades off exploring solution approaches (\emph{breadth}) against refining promising ones (\emph{depth}), yet why a given trade-off works, and why…
CAETC: Causal Autoencoding and Treatment Conditioning for Counterfactual Estimation over Time
Nghia D. Nguyen, Pablo Robles-Granda, Lav R. Varshney
Counterfactual estimation over time is important in various applications, such as personalized medicine. However, time-dependent confounding bias in observational data still poses…