Swathi Shree Narashiman

Haricharan Balasundaram, Swathi Shree Narashiman, Pranay Mathur et al.

We propose semantic smoothing, a smoothing method for language models that uses embeddings to share statistical observations across semantically similar contexts. The starting point is a decomposition of log-perplexity that motivates smoothing as a collection of distribution-estimation problems under Kullback-Leibler (KL) loss. We then show that, under a Lipschitz-logit model for embedding-based language generation, proximity of context embeddings implies proximity of the corresponding next-word distributions in KL divergence. Combining these observations, we formulate semantic smoothing as distribution estimation in KL loss with KL-proximity side information. For $n$ samples on a $d$-symbol alphabet with a side-information distribution at KL distance $Δ$, we give an interpolation estimator with worst-case KL risk $O(\min\{Δ,d/n\})$, and prove a matching-order lower bound for uniform side information. We extend the estimator to multiple and empirically estimated synonymous distributions. Experiments on synthetic Markov data and WikiText-103 bigram models using Word2Vec, GloVe, and GPT-2 embeddings show that semantic smoothing consistently reduces test perplexity when applied to add-constant and Kneser-Ney estimates.

Swathi Shree Narashiman, Nitin Chandrachoodan

Data compression continues to evolve, with traditional information theory methods being widely used for compressing text, images, and videos. Recently, there has been growing interest in leveraging Generative AI for predictive compression techniques. This paper introduces a lossless text compression approach using a Large Language Model (LLM). The method involves two key steps: first, prediction using a dense neural network architecture, such as a transformer block; second, compressing the predicted ranks with standard compression algorithms like Adaptive Huffman, LZ77, or Gzip. Extensive analysis and benchmarking against conventional information-theoretic baselines demonstrate that neural compression offers improved performance.

Francesco D'Angelo, Oguz Kaan Yuksel, Swathi Shree Narashiman et al.

Induction heads are attention circuits believed to underlie in-context learning in transformers, yet a precise characterization of the estimators they implement remains elusive. We study transformers trained on order-$k$ Markov chains and identify two complementary smoothing mechanisms. First, at finite attention-weight scale, the circuit implements a soft context-matching estimator: it aggregates contributions from exact and partial context matches, weighted exponentially by their overlap, and induces a data-dependent interpolation across context orders analogous to Jelinek-Mercer smoothing. Second, a beginning-of-sequence (BOS) token induces additive pseudo-counts, recovering Dirichlet-style smoothing. We construct a disentangled transformer implementing both mechanisms and show that trained transformers recover the predicted attention patterns. Across settings where pseudo-count smoothing is optimal or lower-order contexts provide structured evidence, trained transformers match or outperform classical count-based baselines. Our results bridge mechanistic interpretability of induction heads with classical statistical smoothing, revealing that transformers learn to regularize in-context estimation rather than simply count.