Papers by Sandeep Kumar

12 papers
MixRevDetect: Towards Detecting AI-Generated Content in Hybrid Peer Reviews. (2025.naacl-short)

Copied to clipboard

Challenge: Existing methods for detecting fully AI-generated peer reviews fail to detect finer-grained AI-generated points within mixed-authorship reviews.
Approach: They propose a method to identify AI-generated points in peer reviews using large language models . their approach achieved an F1 score of 88.86%, significantly outperforming existing methods .
Outcome: The proposed method outperforms existing methods in identifying AI-generated points in peer reviews.
When Reviews Disagree: Fine-Grained Contradiction Analysis in Scientific Peer Reviews (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches frame reviewer disagreement as binary contradiction detection over isolated sentence pairs, abstracting away review context and obscuring differences in severity of evaluative conflict.
Approach: They propose a fine-grained formulation of reviewer contradiction analysis that operates over full peer reviews by explicitly identifying contradiction evidence spans and assigning graded disagreement intensity scores.
Outcome: The proposed framework outperforms strong single-agent and generic multi-agend baselines in evidence identification and intensity agreement.
Multimodal Differential Network for Visual Question Generation (D18-1)

Copied to clipboard

Challenge: Current dialog systems show improvement in visual question answering but this does not translate to improved human-AI dialog.
Approach: They propose to use a Multimodal Differential Network to generate natural questions from images using a multimodal differential network.
Outcome: The proposed approach significantly improves over state-of-the-art benchmarks on the quantitative metrics.
Longform Multimodal Lay Summarization of Scientific Papers: Towards Automatically Generating Science Blogs from Research Articles (2024.lrec-main)

Copied to clipboard

Challenge: Science blogs and lay-speak are critical to communicating scientific information to the general public and policymakers.
Approach: They propose to use presentation transcripts and slides to generate a scientific blog from a research article in layperson's terms.
Outcome: The proposed approach can generate a blog text and select the most relevant figures to explain a research article in layperson’s terms, essentially a science blog.
Many Hands Make Light Work: Using Essay Traits to Automatically Score Essays (2022.naacl-main)

Copied to clipboard

Challenge: In automatic essay grading, essay traits are important for scoring the essay holistically . a single-task learning system gives the best results for scoring essays holistically and scoring essay traits.
Approach: They propose a way to score essays using a multi-task learning approach . they compare the MTL-based BiLSTM system to a single-task Learning approach based on LSTMs and BiLStms .
Outcome: The proposed system gives better results for scoring essay holistically and scoring essay traits.
When Reviewers Lock Horns: Finding Disagreements in Scientific Peer Reviews (2023.emnlp-main)

Copied to clipboard

Challenge: despite being widely accepted standard for validating scholarly research, peer-review process has faced criticism.
Approach: They propose a task of automatically identifying contradictions among reviewers on a given article.
Outcome: The proposed model detects contradictory statements from the review pairs and makes it publicly available for further investigations.
Leveraging the Cross-Domain & Cross-Linguistic Corpus for Low Resource NMT: A Case Study On Bhili-Hindi-English Parallel Corpus (2025.findings-emnlp)

Copied to clipboard

Challenge: linguistic diversity of India poses significant machine translation challenges, authors say . underrepresented tribal languages like Bhili lack high-quality linguistic resources .
Approach: They introduce a Bhili-Hindi-English Parallel Corpus, the first and largest parallel corpus worldwide . they evaluated a wide range of proprietary and open-source MLLMs on bidirectional translation tasks .
Outcome: The proposed corpus spans critical domains such as education, administration, and news.
BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning (2026.acl-long)

Copied to clipboard

Challenge: Autoregressive models struggle with long-range dependencies, while standard diffusion processes apply uniform corruption across positions.
Approach: They propose a framework that bridges molecular structures and natural language . it assigns position-dependent corruption based on token recovery difficulty .
Outcome: The proposed framework improves molecule reconstruction and captioning performance on two datasets.
Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator (C18-1)

Copied to clipboard

Challenge: a novel method for obtaining sentence-level embeddings is proposed . the problem of obtaining a semantic embeddable sentence is at the core of understanding languages .
Approach: They propose a method for obtaining sentence-level embeddings by using a sequential encoder-decoder framework.
Outcome: The proposed method outperforms the state-of-the-art on a sentiment analysis task.
CourtEval: A Courtroom-Based Multi-Agent Evaluation Framework (2025.findings-acl)

Copied to clipboard

Challenge: Existing automated evaluation metrics like ROUGE and BLEU show low correlation with human judgments.
Approach: They propose a multi-agent evaluation framework that integrates multiple agents . they use ROUGE and BLEU to evaluate natural language models .
Outcome: The proposed evaluation framework outperforms the current state-of-the-art methods in two meta-evaluation benchmarks.
‘Quis custodiet ipsos custodes?’ Who will watch the watchmen? On Detecting AI-generated peer-reviews (2024.emnlp-main)

Copied to clipboard

Challenge: Recent studies have focused on generic AI-generated text detection or estimating fraction of peer-reviews that can be AI-generated.
Approach: They propose a model that detects whether a peer-review is written by ChatGPT and a reviewer-generated model that generates similar outputs upon re-prompting.
Outcome: The proposed model is more robust, but paraphrasing is more effective.
Can Large Language Models Unlock Novel Scientific Research Ideas? (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) and ChatGPT have marked a turning point in the integration of Artificial Intelligence (AI) into people’s everyday lives.
Approach: They conduct a human evaluation of the novelty, relevancy, and feasibility of the generated future research ideas.
Outcome: The proposed models generate more diverse ideas than GPT-4, GPT-3.5, and Gemini 1.0.

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