Papers by Jinlin Wang

6 papers
Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach: They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome: The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.
KG-FPQ: Evaluating Factuality Hallucination in LLMs with Knowledge Graph-based False Premise Questions (2025.coling-main)

Copied to clipboard

Challenge: Existing benchmarks that assess this vulnerability rely on manual construction, resulting in limited size and lack of expandability.
Approach: They propose a method to generate false premise questions based on knowledge graphs . they modify true triplets extracted from KGs to create false premises .
Outcome: The proposed method generates semantically rich FPQs using state-of-the-art GPTs.
RAV: Retrieval-Augmented Voting for Tactile Descriptions Without Training (2025.emnlp-main)

Copied to clipboard

Challenge: Conventional approaches relying on extensive parameter learning for multimodal perception are rigid and computationally inefficient.
Approach: They propose a parameter-free method that constructs visual-tactile cross-modal knowledge directly by retrieving similar visual-touch data for given visual and tactile inputs and generating tactile descriptions through a voting mechanism.
Outcome: The proposed method achieves comparable performance to large-scale cross-modal models without training across a wide range of datasets.
FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are proficient at retrieving single facts from extended contexts, but struggle with tasks requiring simultaneous retrieval of multiple facts.
Approach: They propose a method that refines context through successive rounds of rewriting to address this problem by finding all Crucial Texts (FACT)
Outcome: The proposed method improves multi-fact retrieval performance across tasks, though improvements are less notable in general-purpose QA scenarios.
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing LLMs demonstrate powerful capabilities between tasks, but can they make sequential decisions?
Approach: They propose to evaluate sequential decision-making capability of large language models (LLMs) using novel metrics based Monte Carlo methods.
Outcome: The proposed benchmark improves sequential decision-making performance compared to the vanilla LLM player.
Improving Context Fidelity via Native Retrieval-Augmented Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to fidelity to contexts rely on expensive supervised fine-tuning to generate evidence post-answer or train models to perform web searches without improving utilization of the given context.
Approach: They propose a native retrieval-augmented reasoning framework that integrates in-context evidence with the model’s own retrieval capabilities.
Outcome: The proposed approach outperforms supervised fine-tuning, retrieval-augmented generation methods, and external retrieval solutions on multiple real-world and counterfactual QA benchmarks.

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