Papers by Bhavya Bhavya

10 papers
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have highlighted the need for effective unlearning mechanisms to comply with data regulations and ethical AI practices.
Approach: They propose a second-order optimization-based LLM unlearning framework which extends the static, one-shot model update using influence unlearning to a dynamic, iterative unlearning process.
Outcome: The proposed framework outperforms first-order methods across unlearning tasks, models, and metrics.
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) show promising results in language generation but often “hallucinate”, making their outputs less reliable.
Approach: They propose to shift attention to more relevant components at token- and sentence-levels for better UQ.
Outcome: The proposed approach improves the performance of a range of popular “off-the-shelf” LLMs with model sizes extending up to 33B parameters.
Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods to accelerate large language model inference are limited by the reliance on incremental token generation in existing draft models.
Approach: They propose an adaptation of speculative decoding which uses discrete diffusion models to generate draft sequences and allows parallelization of both the drafting and verification steps.
Outcome: The proposed approach provides 7.2x speedups over standard generation processes and 1.75x speed ups over existing speculative decoding approaches.
AnaDE1.0: A Novel Data Set for Benchmarking Analogy Detection and Extraction (2024.eacl-long)

Copied to clipboard

Challenge: Textual analogies that make comparisons between two concepts are often used for explaining complex ideas, creative writing, and scientific discovery.
Approach: They propose a task that includes three synergistic tasks: detecting documents containing analogies, extracting text segments that make up the analogy, and identifying the (source and target) concepts being compared.
Outcome: The proposed task performs well on all sub-tasks and smaller models perform better than non-finetuned ChatGPT, suggesting high task difficulty.
Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods to defend against jailbreak attacks exploit vulnerabilities to elicit unintended or harmful outputs.
Approach: They propose a method to defend against jailbreak attacks by patching specific layers within large language models through self-augmented datasets.
Outcome: The proposed approach reduces harmfulness and attack success rate of jailbreak attacks without compromising utility for benign queries compared to previous methods.
GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models (2025.findings-acl)

Copied to clipboard

Challenge: Foundation models for single-cell RNA sequencing ignore biological prior knowledge encoded in gene regulatory relationships and fail to leverage multi-omics signals.
Approach: They propose a framework that integrates multi-scale gene regulatory networks into RNA foundation model training.
Outcome: The proposed framework improves on state-of-the-art models on three downstream tasks . it integrates multi-scale gene regulatory networks (GRNs) from multi-omics data into training .
Extracting and Understanding the Superficial Knowledge in Alignment (2025.naacl-long)

Copied to clipboard

Challenge: Recent studies have shown that alignment of large language models with human values and preferences requires substantial data and computation resources.
Approach: They propose a method to extract and isolate superficial knowledge from aligned models by focusing on the shallow modifications to the final token selection process.
Outcome: The proposed method extracts and isolates superficial knowledge from aligned models, focusing on the shallow modifications to the final token selection process.
RankMean: Module-Level Importance Score for Merging Fine-tuned LLM Models (2024.findings-acl)

Copied to clipboard

Challenge: Traditionally, developing new language models involves fine-tuning pre-trained LMs . model merging is a cost-effective alternative to fine-timing LM models for multiple tasks .
Approach: They propose an algorithm for merging fine-tuned language models without additional training.
Outcome: The proposed algorithm outperforms baseline methods on multiple benchmarks.
ReTA: Recursively Thinking Ahead to Improve the Strategic Reasoning of Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Existing logical reasoning evaluations of Large Language Models (LLMs) focus on single-turn and static environments, such as arithmetic problems.
Approach: They propose a Recursively Thinking-Ahead agent that analyzes the opponents’ future moves/actions and assigns reward signals for these situations.
Outcome: The proposed agent is based on two scenarios: Online Racing and Offline Probing.
BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks (2026.acl-long)

Copied to clipboard

Challenge: Multiple-choice question answering (MCQ) is standard in NLP, but benchmarks lack rigorous quality control.
Approach: They propose an education-inspired toolkit that uses LLM judges to flag flaws in MCQs . they validate the tool with annotations and run it to audit 12 benchmarks based on 19-rule education rubric .
Outcome: The proposed toolkit flags three common MCQ flaws based on a 19-rule education rubric . contaminated MCqs tend to inflate accuracy, while writing errors lower it and change rankings .

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