28 citations · 51 across the 11 of their papers we have counts for
9 papers · 1 filter
A Multifaceted Analysis of Negative Bias in Large Language Models through the Lens of Parametric Knowledge
Jongyoon Song, Sangwon Yu, Sungroh Yoon
Negative bias refers to the tendency of large language models (LLMs) to excessively generate negative responses in binary decision tasks (e.g., yes-no question answering). Previous…
TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant?
Jiho Park, Jongyoon Song, Minjin Choi +3
Large language models (LLMs) are increasingly integral as productivity assistants, but existing benchmarks fall short in rigorously evaluating their real-world instruction-followin…
Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
Sangwon Yu, Ik-hwan Kim, Jongyoon Song +3
Multi-hop reasoning, which requires multi-step reasoning based on the supporting documents within a given context, remains challenging for large language models (LLMs). LLMs often…
Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment
Sangwon Yu, Jongyoon Song, Bongkyu Hwang +7
A binary decision task, like yes-no questions or answer verification, reflects a significant real-world scenario such as where users look for confirmation about the correctness of…
Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination
Jongyoon Song, Sangwon Yu, Sungroh Yoon
In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content…
Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models
Jongyoon Song, Nohil Park, Bongkyu Hwang +4
Abstractive summarization models often generate factually inconsistent content particularly when the parametric knowledge of the model conflicts with the knowledge in the input doc…
AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate
Jongyoon Song, Sungwon Kim, Sungroh Yoon
Non-autoregressive neural machine translation (NART) models suffer from the multi-modality problem which causes translation inconsistency such as token repetition. Most recent appr…
Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings
Sangwon Yu, Jongyoon Song, Heeseung Kim +3
Recent studies have determined that the learned token embeddings of large-scale neural language models are degenerated to be anisotropic with a narrow-cone shape. This phenomenon,…
Building a Neural Machine Translation System Using Only Synthetic Parallel Data
Jaehong Park, Jongyoon Song, Sungroh Yoon
Recent works have shown that synthetic parallel data automatically generated by translation models can be effective for various neural machine translation (NMT) issues. In this stu…