Papers by Atharva Naik

7 papers
Representation Learning for Conversational Data using Discourse Mutual Information Maximization (2022.naacl-main)

Copied to clipboard

Challenge: Existing language modeling pretraining objectives do not take structural information of conversational text into account.
Approach: They propose a structure-aware Mutual Information based loss-function DMI for training dialog-representation models that captures the inherent uncertainty in response prediction.
Outcome: The proposed model outperforms strong baseline models on nine diverse tasks.
Programming by Example meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction (2025.acl-long)

Copied to clipboard

Challenge: Historical linguists have written programs that convert reconstructed words into their attested descendants via ordered string rewrite functions.
Approach: They propose to use a model to generate a "similar distribution" for sound law induction . they propose four kinds of methods with varying amounts of inductive bias to investigate best performance .
Outcome: The proposed model shows that it can be fine tuned with training data and evaluation data.
An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have demonstrated impressive capabilities across complex reasoning and generation tasks.
Approach: They evaluate a broad spectrum of collaboration strategies for repository-level code generation where the weak model handles simpler tasks at lower cost and the most challenging tasks are delegated to the strong model.
Outcome: The proposed model achieves equivalent performance to the strong model while reducing the cost by 40%.
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks (2022.emnlp-main)

Copied to clipboard

Challenge: a benchmark of 1,616 diverse NLP tasks and their expert-written instructions is used to test generalization of models to unseen tasks . a recent study shows that instruction-following models outperform instruction-based models by over 9% .
Approach: They build a benchmark of 1,616 diverse NLP tasks and their expert-written instructions.
Outcome: The proposed model outperforms existing instruction-following models by over 9% on the benchmark despite being smaller.
CRScore: Grounding Automated Evaluation of Code Review Comments in Code Claims and Smells (2025.naacl-long)

Copied to clipboard

Challenge: Current review comment evaluation metrics rely on comparisons with a human-written reference for a given code change (also called a diff).
Approach: They propose to use a reference-free metric to measure review quality like conciseness, comprehensiveness, and relevance to compare the quality of code changes with human-written references.
Outcome: The proposed metric can produce fine-grained scores that have the greatest alignment with human judgment and are more sensitive than reference-based metrics.
PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics (2026.findings-acl)

Copied to clipboard

Challenge: a benchmark for inductive reasoning is based on sound law induction in historical linguistics . solve rates are below 5% on hard PBEBench instances with long program cascades despite expensive scaling strategies .
Approach: They propose a benchmark for inductive reasoning inspired by sound law induction in historical linguistics.
Outcome: The proposed approach generates problems with controllable difficulty and ordering constraints . solve rates remain below 5% on hard PBEBench instances with long program cascades .
Data Augmentation for Code Translation with Comparable Corpora and Multiple References (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for translating code between programming languages are limited by parallel training data.
Approach: They propose a data augmentation technique that builds comparable corpora and augments existing parallel data with multiple reference translations.
Outcome: The proposed techniques improve CodeT5 translation between Java, Python, and C++ by an average of 7.5% Computational Accuracy (CA@1) .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations