1 citations · 2 across the 18 of their papers we have counts for
20 papers
Carryover Drafting: Recycling Rejected States for Speculative Decoding
Jahyun Koo, Sunghyeon Woo, Jaeeun Kil +4
Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept several tokens. By construction, ve…
PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations
Hyojeong Yu, Hyukhun Koh, Minsung Kim +2
Large language models (LLMs) are increasingly deployed as personalized assistants that interact with users over extended periods of time. As conversations grow longer, relying on f…
Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs
Jiwon Moon, Yerin Hwang, Kyomin Jung
Instruction hierarchy (IH) requires models to prioritize instructions by source, ensuring that higher-priority instructions override lower-priority ones. Despite its importance for…
Casual as an Anchor: Resolving Supervision Misalignment in Formality Transfer Dataset
Hyojeong Yu, Hyukhun Koh, Minsung Kim +1
Formality transfer is commonly framed as a symmetric bidirectional task between informal and formal registers. We argue that this framing conceals a supervision design flaw in exis…
When Wording Steers the Evaluation: Framing Bias in LLM judges
Yerin Hwang, Dongryeol Lee, Taegwan Kang +2
Large language models (LLMs) are known to produce varying responses depending on prompt phrasing, indicating that subtle guidance in phrasing can steer their answers. However, the…
Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation
Dongryeol Lee, Yerin Hwang, Taegwan Kang +3
While large language models (LLMs) are increasingly used as automatic judges for question answering (QA) and other reference-conditioned evaluation tasks, little is known about the…
Program Synthesis via Test-Time Transduction
Kang-il Lee, Jahyun Koo, Seunghyun Yoon +4
We introduce transductive program synthesis, a new formulation of the program synthesis task that explicitly leverages test inputs during synthesis. While prior approaches to progr…
Black-Box Hallucination Detection via Consistency Under the Uncertain Expression
Seongho Joo, Kyungmin Min, Jahyun Koo +1
Despite the great advancement of Language modeling in recent days, Large Language Models (LLMs) such as GPT3 are notorious for generating non-factual responses, so-called "hallucin…
Public Data Assisted Differentially Private In-Context Learning
Seongho Joo, Hyukhun Koh, Kyomin Jung
In-context learning (ICL) in Large Language Models (LLMs) has shown remarkable performance across various tasks without requiring fine-tuning. However, recent studies have highligh…
Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding
Seongho Joo, Hyukhun Koh, Kyomin Jung
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but their potential misuse for harmful purposes remains a significant concern. To stren…
Can You Trick the Grader? Adversarial Persuasion of LLM Judges
Yerin Hwang, Dongryeol Lee, Taegwan Kang +2
As large language models take on growing roles as automated evaluators in practical settings, a critical question arises: Can individuals persuade an LLM judge to assign unfairly h…
Don't Judge Code by Its Cover: Exploring Biases in LLM Judges for Code Evaluation
Jiwon Moon, Yerin Hwang, Dongryeol Lee +3
With the growing use of large language models(LLMs) as evaluators, their application has expanded to code evaluation tasks, where they assess the correctness of generated code with…
Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation
Yerin Hwang, Dongryeol Lee, Kyungmin Min +3
Recently, large vision-language models (LVLMs) have emerged as the preferred tools for judging text-image alignment, yet their robustness along the visual modality remains underexp…
Generating Diverse Hypotheses for Inductive Reasoning
Kang-il Lee, Hyukhun Koh, Dongryeol Lee +3
Inductive reasoning - the process of inferring general rules from a small number of observations - is a fundamental aspect of human intelligence. Recent works suggest that large la…
Conditional [MASK] Discrete Diffusion Language Model
Hyukhun Koh, Minha Jhang, Dohyung Kim +2
Although auto-regressive models excel in natural language processing, they often struggle to generate diverse text and provide limited controllability. Non-auto-regressive methods…
Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation
Dongryeol Lee, Yerin Hwang, Yongil Kim +2
In line with the principle of honesty, there has been a growing effort to train large language models (LLMs) to generate outputs containing epistemic markers. However, evaluation i…
Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
Kyungmin Min, Minbeom Kim, Kang-il Lee +2
Large Vision-Language Models (LVLMs) demonstrate impressive capabilities in generating detailed and coherent responses from visual inputs. However, they are prone to generate hallu…
Fine-grained Gender Control in Machine Translation with Large Language Models
Minwoo Lee, Hyukhun Koh, Minsung Kim +1
In machine translation, the problem of ambiguously gendered input has been pointed out, where the gender of an entity is not available in the source sentence. To address this ambig…
VLind-Bench: Measuring Language Priors in Large Vision-Language Models
Kang-il Lee, Minbeom Kim, Seunghyun Yoon +4
Large Vision-Language Models (LVLMs) have demonstrated outstanding performance across various multimodal tasks. However, they suffer from a problem known as language prior, where r…
Return of EM: Entity-driven Answer Set Expansion for QA Evaluation
Dongryeol Lee, Minwoo Lee, Kyungmin Min +2
Recently, directly using large language models (LLMs) has been shown to be the most reliable method to evaluate QA models. However, it suffers from limited interpretability, high c…