Papers by Siddharth Verma
NEST: Nested Evidence Survival for Retrieval (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to retrieval-augmented generation (RAG) rely on rigid heuristics or computational overhead. |
| Approach: | They propose a lightweight, training-free RAG framework that separates recall amplification from precision selection. |
| Outcome: | Evaluated on WebQuestions, HotpotQA and internalQA benchmarks, NEST outperforms strong adaptive RAG baselines. |
ALERT: Adapt Language Models to Reasoning Tasks (2023.acl-long)
Copied to clipboard
Ping Yu, Tianlu Wang, Olga Golovneva, Badr AlKhamissi, Siddharth Verma, Zhijing Jin, Gargi Ghosh, Mona Diab, Asli Celikyilmaz
| Challenge: | Large language models have shown increasing in-context learning capabilities with scaling up the model and data sizes. |
| Approach: | They propose a benchmark and suite of analyses to evaluate reasoning skills of large language models. |
| Outcome: | The proposed model compares pre-trained and fine-tuned models on tasks that require reasoning skills to solve. |
TEEMIL : Towards Educational MCQ Difficulty Estimation in Indic Languages (2025.coling-main)
Copied to clipboard
| Challenge: | Traditionally, educators manually create and calibrate MCQs, a process that is time-consuming and subjective. |
| Approach: | They propose to use TEEMIL-H and TEIMEL-K to create a dataset with manually annotated difficulty labels for MCQs in Hindi and Kannada. |
| Outcome: | The proposed datasets contain 4689 and 4215 MCQs with manually annotated difficulty labels. |
Lived Experience Not Found: LLMs Struggle to Align with Experts on Addressing Adverse Drug Reactions from Psychiatric Medication Use (2025.naacl-long)
Copied to clipboard
Mohit Chandra, Siddharth Sriraman, Gaurav Verma, Harneet Singh Khanuja, Jose Suarez Campayo, Zihang Li, Michael L. Birnbaum, Munmun De Choudhury
| Challenge: | Adverse Drug Reactions (ADRs) from psychiatric medications are the leading cause of hospitalizations among mental health patients. |
| Approach: | They propose a benchmark and a framework to evaluate LLMs' ability to detect ADRs . they find that LLM responses are more complex and harder to read than experts . |
| Outcome: | The proposed framework evaluates LLMs' ability to detect and deliver expert-aligned mitigation strategies. |
CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to training dialogue agents are supervised learning, but this is prohibitively expensive and time-consuming. |
| Approach: | They propose offline reinforcement learning methods that can be used to train dialogue agents . offline reinforcement learn methods can be combined with language models to yield realistic dialogue agents. |
| Outcome: | The proposed method can be combined with language models to produce realistic dialogue agents . the results show that the offline method can achieve the goal of the proposed system . |
SELENE: Selective and Evidence-Weighted LLM Debating for Efficient and Reliable Reasoning (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing multi-agent debate frameworks are computationally expensive and prone to degradation under pro-longed debates due to redundant exchanges and unstable judging. |
| Approach: | They propose a framework that unifies Selective Debate Initiation (SDI) with Evidence Weighted Self-Consistency (EWSC) for adaptive, debate-on-demand reasoning. |
| Outcome: | Evaluated on BoolQ, CosmosQA, and an internal QnA benchmark, the proposed framework achieves higher factual robustness and efficiency. |
ReflectiveRAG: Rethinking Adaptivity in Retrieval-Augmented Generation (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing methods for retrieval-augmented generation (RAG) fail to assess evidence sufficiency, detect subtle mismatches or reduce redundancy. |
| Approach: | They propose a lightweight yet reasoning-driven architecture that enhances factual grounding . ReflectiveRAG employs self-reflective retrieval and Contrastive noise removal . |
| Outcome: | a new architecture improves factual grounding by using self-reflective retrieval and Contrastive noise removal. |