Papers by Koyel Mukherjee

6 papers
From Selection to Generation: A Survey of LLM-based Active Learning (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been used for selection and training of data for active learning.
Approach: They propose an intuitive taxonomy that categorizes LLM-based active learning techniques and discuss the transformative roles they can play in the active learning loop.
Outcome: The proposed model can generate entirely new data instances and provide more cost-effective annotations with fewer labeled data instances.
PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from related Example Banks (2025.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated impressive few-shot learning capabilities through in-context learning.
Approach: They propose a novel Alternating Minimization approach for example selection that improves ICL performance on low-resource Indic languages.
Outcome: The proposed approach outperforms existing frameworks for retrieving examples on low-resource Indic languages.
FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reduction (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to improve latency via skipping layers have limitations . fiRST is a model-agnostic framework that reduces inference latency while maintaining quality .
Approach: They propose a model-agnostic framework that skips transformer layers during decoding . it is fully compatible with KV caching, enabling faster decoding while maintaining quality .
Outcome: a new framework reduces inference latency by using layer-specific routers to skip transformer layers during decoding.
Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG (2026.findings-acl)

Copied to clipboard

Challenge: Query enhancement techniques are now standard in retrieval-augmented generation systems, yet their impact on these biases remains unexplored.
Approach: They evaluate query enhancement techniques that improve retrieval quality . they find that simple rewriting reduces bias through increased score variance . no technique uniformly addresses all biases, and effects vary substantially across retrievers .
Outcome: The proposed method achieves strongest aggregate reduction, but fails under adversarial conditions where multiple biases combine.
TTD-SQL: Tree-Guided Token Decoding for Efficient and Schema-Aware SQL Generation (2025.emnlp-industry)

Copied to clipboard

Challenge: Large language models (LLMs) have achieved state-of-the-art accuracy on benchmarks like Spider and BIRD, but inference latency due to sequential autoregressive decoding remains a challenge for real-time deployments.
Approach: a new framework integrates SQL grammar and database schema constraints into the decoding process . tree-Guided Token Decoding (TTD-SQL) precomputes token-level decision trees over SQL keywords, table names, and column identifiers .
Outcome: a new framework reduces schema hallucinations and inference latency due to autoregressive decoding . tree-Guided Token Decoding achieves 19.96% token-rate speedups .
An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA (2026.findings-acl)

Copied to clipboard

Challenge: Existing QA benchmarks do not explicitly support document-grounded related insight generation . Existing document-based QA efforts focus on answering fact-based questions .
Approach: They propose a task to generate additional insights from a document collection that improves, extends or rethinks an initial answer to an open-ended question.
Outcome: The proposed task improves, extends, or rethinks an answer to an open-ended question.

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