Papers by Rishabh Maheshwary

8 papers
Adversarial Examples for Evaluating Math Word Problem Solvers (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing MWP solvers do not understand language and its relation with numbers, and their accuracy is unclear.
Approach: They propose two methods to generate adversarial attacks to evaluate the robustness of existing MWP solvers.
Outcome: The proposed method reduces the accuracy of existing MWP solvers by over 40% on two benchmark datasets.
A Strong Baseline for Query Efficient Attacks in a Black Box Setting (2021.emnlp-main)

Copied to clipboard

Challenge: Existing black box search methods are inefficient as they do not consider the amount of queries required to generate adversarial attacks.
Approach: They propose a query efficient attack strategy to generate plausible adversarial examples on text classification and entailment tasks.
Outcome: The proposed attack reduces query count by 75% across all datasets and target models compared to prior attacks in a limited query setting.
Prompting with Phonemes: Enhancing LLMs’ Multilinguality for Non-Latin Script Languages (2025.naacl-long)

Copied to clipboard

Challenge: Multilingual LLMs have achieved remarkable benchmark performance, but continue to underperform on non-Latin script languages.
Approach: They propose to integrate phonemic transcriptions as complementary signals to induce script-invariant representations by integrating phonemic and orthographic transcriptions.
Outcome: The proposed approach improves performance for Latin and non-Latin script languages, with 12.6% performance improvement and 15.1% performance improvement compared to randomized ICL retrieval.
M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Existing approaches to collect instruction fine-tuning data are limited due to their toxicity, privacy and toxicity concerns.
Approach: They propose to use a two-step taxonomy to transform a small set of human written instructions into complex and challenging conversations.
Outcome: M2Lingual has 175K conversations across 70 languages with a balanced mix of high, low and mid-resourced languages.
Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs (2025.findings-acl)

Copied to clipboard

Challenge: a meta quantization approach quantizes different layers of a large language model at different bit levels.
Approach: They propose a meta quantization approach that quantizes different layers of a large language model at different bit levels.
Outcome: The proposed method quantizes the most important layers to higher bit precision and less important layers at lower bits.
M-RewardBench: Evaluating Reward Models in Multilingual Settings (2025.acl-long)

Copied to clipboard

Challenge: Reward models (RMs) are primarily trained and evaluated in English and their capabilities in multilingual settings remain understudied.
Approach: They construct a multilingual RM evaluation benchmark that tests the chat, safety, reasoning, and translation capabilities of RMs in 23 languages.
Outcome: The proposed model performs better for high-resource languages and improves with translation quality.
Enhancing Alignment using Curriculum Learning & Ranked Preferences (2024.findings-emnlp)

Copied to clipboard

Challenge: Direct Preference Optimization (DPO) is an effective technique that leverages pairwise preference data to align LLMs to human preferences.
Approach: They propose to use pairwise preference data to create multiple preference pairs for a given prompt.
Outcome: The proposed method outperforms standard DPO on MTbench, Vicuna bench, and WizardLM with a score of 7.43 on the test sets.
Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem Solvers (2022.naacl-main)

Copied to clipboard

Challenge: Existing Math Word Problem solvers do not generalize well and rely on superficial cues to achieve high performance.
Approach: They propose several data augmentation techniques to increase the size of existing MWP datasets by five folds by deploying them to a benchmark dataset.
Outcome: The proposed methods increase the generalization and robustness of existing solvers by over five percentage points on benchmark datasets.

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