Papers by Nikhil Garg
When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models (2026.eacl-srw)
Copied to clipboard
| Challenge: | Existing safety evaluations rely on fixed collections of harmful prompts . such attacks span single-shot prompts, multi-turn interactions, cross-lingual settings . |
| Approach: | They propose to use black-box prompt optimization techniques to search for safety failures . they use GPT-5.1 to optimize for a continuous danger score . |
| Outcome: | The proposed approach reduces effective safeguards for large language models . the average danger score of Qwen 3 8B increases from 0.09 in its baseline setting to 0.79 after optimization. |
Improving Answer Selection and Answer Triggering using Hard Negatives (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to answer selection and answer triggering have been proposed. |
| Approach: | They propose to use hard negatives with a siamese network and a suitable loss function for answer selection and answer triggering. |
| Outcome: | The proposed model improves on InsuranceQA, SelQA, and an internal QA dataset by 2.3 points over previous baselines. |
Topics, Authors, and Institutions in Large Language Model Research: Trends from 17K arXiv Papers (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in language modeling have caused disruptive shifts throughout AI research, spurring discussion about how the field is changing and how it should change. |
| Approach: | They analyze a dataset of 16,979 LLM-related arXiv papers and examine industry and academic publishing trends. |
| Outcome: | The authors examine the impact of large language models on AI research in 2023 and 2022. |
Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings (N19-1)
Copied to clipboard
| Challenge: | a new framework for studying political polarization in social media is needed to understand how group divisions manifest in language. |
| Approach: | They propose to cluster tweet embeddings to uncover four dimensions of political polarization in social media . their results apply existing lexical methods to analyze 4.4M tweets on 21 mass shootings . |
| Outcome: | The proposed framework generates more cohesive topics than traditional models. |
SandhiKosh: A Benchmark Corpus for Evaluating Sanskrit Sandhi Tools (L18-1)
Copied to clipboard
| Challenge: | Several important texts which are of interest to people all over the world were written in Sanskrit. |
| Approach: | They develop a Sanskrit benchmark to evaluate the completeness and accuracy of tools . they use three most prominent tools to evaluate their completeness . |
| Outcome: | The proposed tools have substantial scope for improvement and are available to researchers worldwide. |