9 papers
Know-Thy-Not: Training-Free Targeted Negation in Dual-Encoder Vision-Language Models
DoYoung Kim, Changkyu Choi, Adín Ramírez Rivera +2
Dual-encoder vision-language models systematically fail at negation, scoring ''a cat without a dog'' nearly identically to ''a cat with a dog.'' We show that this failure is inhere…
EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQL
Jaehoon Lee, CheolWon Na, Suyoung Bae +4
Text-to-SQL enables users to query databases using natural language by generating executable SQL queries. Recent methods have increasingly adopted Large Language Models based reinf…
Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation
Suyoung Bae, Jaehoon Lee, Changkyu Choi +2
Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agents rely on to navigate large…
ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization
Suyoung Bae, CheolWon Na, Jaehoon Lee +3
As Large Language Models (LLMs) have become capable of generating long and descriptive code summaries, accurate and reliable evaluation of factual consistency has become a critical…
TAG: A Simple Yet Effective Temporal-Aware Approach for Zero-Shot Video Temporal Grounding
Jin-Seop Lee, SungJoon Lee, Jaehan Ahn +2
Video Temporal Grounding (VTG) aims to extract relevant video segments based on a given natural language query. Recently, zero-shot VTG methods have gained attention by leveraging…
DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph
Jihyung Lee, Jin-Seop Lee, Jaehoon Lee +2
Text-to-SQL, which translates a natural language question into an SQL query, has advanced with in-context learning of Large Language Models (LLMs). However, existing methods show l…
Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation
CheolWon Na, YunSeok Choi, Jee-Hyong Lee
Many adversarial attack approaches are proposed to verify the vulnerability of language models. However, they require numerous queries and the information on the target model. Even…
SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data
Suyoung Bae, Hyojun Kim, YunSeok Choi +1
In various natural language processing (NLP) tasks, fine-tuning Pre-trained Language Models (PLMs) often leads to the issue of spurious correlations, which negatively impacts perfo…
DeCAP: Context-Adaptive Prompt Generation for Debiasing Zero-shot Question Answering in Large Language Models
Suyoung Bae, YunSeok Choi, Jee-Hyong Lee
While Large Language Models (LLMs) excel in zero-shot Question Answering (QA), they tend to expose biases in their internal knowledge when faced with socially sensitive questions,…