Papers by Vikas Yadav

21 papers
If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering (2021.naacl-main)

Copied to clipboard

Challenge: et al. : evidence retrieval is highly dependent on partial, incorrect or no supporting knowledge.
Approach: They propose a method that retrieves and reranks evidence facts jointly . they propose to account for links between sentences and coverage with the given query .
Outcome: The proposed approach achieves state-of-the-art evidence retrieval performance on two multi-hop question answering datasets.
Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework (2025.naacl-short)

Copied to clipboard

Challenge: Graph databases like Neo4j are gaining popularity for handling complex, interconnected data, over traditional relational databases.
Approach: They propose an automated pipeline to generate Cypher queries for Neo4j using LLM-As-Database-Filler, a novel strategy for ensuring Cyphere query correctness.
Outcome: The proposed pipeline generates high quality Cypher data containing 29.8k instances across various domains and queries with varying complexities.
A Survey on Recent Advances in Named Entity Recognition from Deep Learning models (C18-1)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a key component in NLP systems for question answering, information retrieval, relation extraction, etc.
Approach: They propose to use recurrent neural networks to generate NERs over characters, sub-words and/or word embeddings to improve named entity recognition.
Outcome: The proposed architectures are better than those based on feature engineering and other supervised or semi-supervised learning algorithms.
Prompting with Phonemes: Enhancing LLMs’ Multilinguality for Non-Latin Script Languages (2025.naacl-long)

Copied to clipboard

Challenge: Multilingual LLMs have achieved remarkable benchmark performance, but continue to underperform on non-Latin script languages.
Approach: They propose to integrate phonemic transcriptions as complementary signals to induce script-invariant representations by integrating phonemic and orthographic transcriptions.
Outcome: The proposed approach improves performance for Latin and non-Latin script languages, with 12.6% performance improvement and 15.1% performance improvement compared to randomized ICL retrieval.
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection (2024.naacl-long)

Copied to clipboard

Challenge: Instruction-tuned Large Language Models (LLMs) can modulate responses based on human instructions, but they can be maliciously steered to impact society in subtle but persistent ways.
Approach: They propose a backdoor attack setting that allows an attacker to inject a virtual prompt into an LLM to steer it without any explicit injection at its input.
Outcome: The proposed method is able to poison the model's instruction tuning data and show that it is highly effective in steering the model.
Multi-class Hierarchical Question Classification for Multiple Choice Science Exams (2020.lrec-1)

Copied to clipboard

Challenge: Prior work has demonstrated that question classification (QC) can help answer a question more accurately.
Approach: They propose to use a large dataset for question classification (QC) that contains 7,787 science exam questions paired with detailed classification labels from a fine-grained hierarchical taxonomy of 406 problem domains to train a BERT-based model.
Outcome: The proposed model achieves a large (+0.12 MAP) gain while also achieving state-of-the-art performance on benchmark open-domain and biomedical QC datasets.
M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Existing approaches to collect instruction fine-tuning data are limited due to their toxicity, privacy and toxicity concerns.
Approach: They propose to use a two-step taxonomy to transform a small set of human written instructions into complex and challenging conversations.
Outcome: M2Lingual has 175K conversations across 70 languages with a balanced mix of high, low and mid-resourced languages.
Grammar Search for Multi-Agent Systems (2026.acl-long)

Copied to clipboard

Challenge: Several prior approaches have relied on LLM-based free-form search over the code space.
Approach: They propose a more structured framework that explores the same space through a fixed set of composable components.
Outcome: The proposed framework outperforms existing approaches on most benchmarks across two backbone LLMs and two domains: mathematics and question answering.
Explicit over Implict: Explicit Diversity Conditions for Effective Question Answer Generation (2024.lrec-main)

Copied to clipboard

Challenge: Recent pretrained and large language model-based QAG methods suffer from redundant generation of QA pairs, affecting downstream QA systems.
Approach: They propose to use explicit diversity conditions to generate diverse question-answer synthetic data by focusing on spatial aspects, question types, and entities.
Outcome: The proposed diversity conditions significantly increase diversity in QA generation over existing diversity techniques.
Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering (2020.acl-main)

Copied to clipboard

Challenge: Evidence retrieval is a critical stage of question answering (QA) . Several multi-hop QA datasets have been proposed recently .
Approach: They propose an unsupervised method that uses only GloVe embeddings to soft-align questions with justification sentences and an iterative process that reformulates queries focusing on terms that are not covered by existing justifications.
Outcome: The proposed method outperforms all previous methods on the evidence selection task on two datasets: MultiRC and QASC.
Eidos, INDRA, & Delphi: From Free Text to Executable Causal Models (N19-4)

Copied to clipboard

Challenge: a paper proposes a method for building probabilistic models of complex phenomena such as food insecurity . currently, these models are hand-built for each new situation and require months to construct .
Approach: They propose an approach that builds executable probabilistic models from raw, free text.
Outcome: The proposed approach builds executable probabilistic models from raw, free text.
CopySpec: Accelerating LLMs with Speculative Copy-and-Paste (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) suffer from slower inference as context size grows, but CopySpec leverages larger contexts to accelerate inference.
Approach: They propose a technique that speculates that the same tokens will follow repeated sequences in the model’s chat history or context and enables seamless copying without compromising output quality.
Outcome: The proposed technique can generate responses that closely resemble previous outputs or responses that can be verbatim extracted from context without compromising output quality and without requiring additional GPU memory.
Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy (2024.findings-emnlp)

Copied to clipboard

Challenge: Using dynamic slicing, large language models can be used to reduce computational burden and improve performance.
Approach: They propose a dynamic layer-specific pruning approach that leverages the newly proposed Layer Redundancy score to prune parts of individual layers based on redundancy.
Outcome: The proposed method maintains and enhances model performance over the SliceGPT baseline.
Towards Robust Neural Retrieval with Source Domain Synthetic Pre-Finetuning (2022.coling-1)

Copied to clipboard

Challenge: Existing neural IR systems rely on lexical matching for query-passage alignment, while masked language models use a dual encoder architecture to encode passages and questions into continuous vector representations.
Approach: They propose to enhance the out-of-domain generalization of Dense Passage Retrieval (DPR) through synthetic data augmentation only in the source domain.
Outcome: The proposed model outperforms existing models in in-domain and zero-shot evaluations on Wikipedia-based datasets.
Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs (2025.findings-acl)

Copied to clipboard

Challenge: a meta quantization approach quantizes different layers of a large language model at different bit levels.
Approach: They propose a meta quantization approach that quantizes different layers of a large language model at different bit levels.
Outcome: The proposed method quantizes the most important layers to higher bit precision and less important layers at lower bits.
Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering (D19-1)

Copied to clipboard

Challenge: Arras et al., 2017) suggest an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) .
Approach: They propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering that maximizes the relevance of the selected sentences, minimizes overlap between selected facts, and maximizes coverage of both question and answer.
Outcome: The proposed strategy improves state-of-the-art supervised QA model on two multi-hop QA datasets: AI2’s Reasoning Challenge (ARC) and Multi-Sentence Reading Comprehension (MultiRC).
Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Abstention Ability (AA) is a critical aspect of Large Language Model (LLM) reliability.
Approach: They propose a black-box evaluation approach and a new dataset, Abstain-QA, to rigorously assess AA across varied question types, domains, and task types.
Outcome: The proposed evaluation process and new dataset, Abstain-QA, are crafted to rigorously assess AA across varied question types, domains, and task types.
Enhancing Alignment using Curriculum Learning & Ranked Preferences (2024.findings-emnlp)

Copied to clipboard

Challenge: Direct Preference Optimization (DPO) is an effective technique that leverages pairwise preference data to align LLMs to human preferences.
Approach: They propose to use pairwise preference data to create multiple preference pairs for a given prompt.
Outcome: The proposed method outperforms standard DPO on MTbench, Vicuna bench, and WizardLM with a score of 7.43 on the test sets.
Diverse Multi-tool Aggregation with Large Language Models for Enhanced Math Reasoning (2025.findings-emnlp)

Copied to clipboard

Challenge: Multi-TAG uses multiple tools to solve complex math problems over multiple reasoning steps.
Approach: They propose a tool-based LLM framework that leverages multiple tools to solve math problems.
Outcome: The proposed framework outperforms baselines that use individual tools with the same number of runs and significantly outperformed standard baselines.
Alignment over Heterogeneous Embeddings for Question Answering (N19-1)

Copied to clipboard

Challenge: Existing approaches for non-factoid question answering are based on heterogeneous embeddings that model text at different levels of abstraction.
Approach: They propose a fast, mostly-unsupervised approach for non-factoid question answering called Alignment over Heterogeneous Embeddings (AHE) it aligns each word in the question and candidate answer with the most similar word in retrieved supporting paragraph and a meta-classifier that learns how much to trust the predictions over each representation.
Outcome: The proposed approach outperforms other supervised approaches on the AI2 Reasoning Challenge dataset and the WikiQA dataset.
ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models excel at complex tasks by breaking down problems into structured reasoning steps.
Approach: They propose a hyperparameter-free conciseness score to guide models toward generating correct reasoning traces.
Outcome: The proposed method reduces token usage by 31x on simple problems while improving accuracy by 7% on the hardest problems.

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