Bugeun Kim

Junhyuk Choi, Sohhyung Park, Chanhee Cho et al.

While LLM-as-a-Judge is widely used in automated evaluation, existing validation practices primarily operate at the level of observed outputs, offering limited insight into whether LLM judges themselves function as stable and reliable measurement instruments. To address this limitation, we introduce a two-phase diagnostic framework for assessing reliability of LLM-as-a-Judge, grounded in Item Response Theory (IRT). The framework adopts Graded Response Model (GRM) of IRT and formalizes reliability along two complementary dimensions: (1) intrinsic consistency, defined as the stability of measurement behavior under prompt variations, and (2) human alignment, capturing correspondence with human quality assessments. We empirically examine diverse LLM judges with this framework, and show that leveraging IRT-GRM yields interpretable signals for diagnosing judgments systematically. These signals provide practical guidance for verifying reliablity of LLM-as-a-Judge and identifying potential causes of unreliability.

Byungjun Kim, Dayeon Seo, Minju Kim et al.

Recent studies have investigated whether large language models (LLMs) can support obscured communication, which is characterized by core aspects such as inferring subtext and evading suspicions. To conduct the investigation, researchers have used social deduction games (SDGs) as their experimental environment, in which players conceal and infer specific information. However, prior work has often overlooked how LLMs should be evaluated in such settings. Specifically, we point out two limitations with the evaluation methods they employed. First, metrics used in prior studies are coarse-grained as they are based on overall game outcomes that often fail to capture event-level behaviors; Second, error analyses have lacked structured methodologies capable of producing insights that meaningfully support evaluation outcomes. To address these limitations, we propose a microscopic and systematic approach to the investigation. Specifically, we introduce six fine-grained metrics that resolve the first issue. To tackle the second issue, we conducted a thematic analysis and identified four major reasoning failures that undermine LLMs' performance in obscured communication.

Ro-hoon Oh, Jihwan Seol, Bugeun Kim

Target speech extraction (TSE) aims to recover a target speaker's voice from a mixture. While recent text-prompted approaches have shown promise, most approaches assume fully overlapped mixtures, limiting insight into behavior across realistic overlap ratios. We introduce VorTEX (Various overlap ratio for Target speech EXtraction), a text-prompted TSE architecture with a Decoupled Adaptive Multi-branch (DAM) Fusion block that separates primary extraction from auxiliary regularization pathways. To enable controlled analysis, we construct PORTE, a two-speaker dataset spanning overlap ratios from 0% to 100%. We further propose Suppression Ratio on Energy (SuRE), a diagnostic metric that detects suppression behavior not captured by conventional measures. Experiments show that existing models exhibit suppression or residual interference under overlap, whereas VorTEX achieves the highest separation fidelity across 20-100% overlap (e.g., 5.50 dB at 20% and 2.04 dB at 100%) while maintaining zero SuRE, indicating robust extraction without suppression-driven artifacts.

Junhyuk Choi, Jeongyoun Kwon, Heeju Kim et al.

Multi-agent systems utilizing large language models often assign authoritative roles to improve performance, yet the impact of authority bias on agent interactions remains underexplored. We present the first systematic analysis of role-based authority bias in free-form multi-agent evaluation using ChatEval. Applying French and Raven's power-based theory, we classify authoritative roles into legitimate, referent, and expert types and analyze their influence across 12-turn conversations. Experiments with GPT-4o and DeepSeek R1 reveal that Expert and Referent power roles exert stronger influence than Legitimate power roles. Crucially, authority bias emerges not through active conformity by general agents, but through authoritative roles consistently maintaining their positions while general agents demonstrate flexibility. Furthermore, authority influence requires clear position statements, as neutral responses fail to generate bias. These findings provide key insights for designing multi-agent frameworks with asymmetric interaction patterns.

Junhyuk Choi, Yeseon Hong, Minju Kim et al.

Large Language Models (LLMs) show impressive conversational abilities but sometimes show identity drift problems, where their interaction patterns or styles change over time. As the problem has not been thoroughly examined yet, this study examines identity consistency across nine LLMs. Specifically, we (1) investigate whether LLMs could maintain consistent patterns (or identity) and (2) analyze the effect of the model family, parameter sizes, and provided persona types. Our experiments involve multi-turn conversations on personal themes, analyzed in qualitative and quantitative ways. Experimental results indicate three findings. (1) Larger models experience greater identity drift. (2) Model differences exist, but their effect is not stronger than parameter sizes. (3) Assigning a persona may not help to maintain identity. We hope these three findings can help to improve persona stability in AI-driven dialogue systems, particularly in long-term conversations.

Byungjun Kim, Minju Kim, Dayeon Seo et al.

We highlight two significant issues leading to the passivity of current merchant non-player characters (NPCs): pricing and communication. While immersive interactions with active NPCs have been a focus, price negotiations between merchant NPCs and players remain underexplored. First, passive pricing refers to the limited ability of merchants to modify predefined item prices. Second, passive communication means that merchants can only interact with players in a scripted manner. To tackle these issues and create an active merchant NPC, we propose a merchant framework based on large language models (LLMs), called MART, which consists of an appraiser module and a negotiator module. We conducted two experiments to explore various implementation options under different training methods and LLM sizes, considering a range of possible game environments. Our findings indicate that finetuning methods, such as supervised finetuning (SFT) and knowledge distillation (KD), are effective in using smaller LLMs to implement active merchant NPCs. Additionally, we found three irregular cases arising from the responses of LLMs.

Hyeonchu Park, Byungjun Kim, Bugeun Kim

As large language models (LLMs) generate more human-like texts, concerns about the side effects of AI-generated texts (AIGT) have grown. So, researchers have developed methods for detecting AIGT. However, two challenges remain. First, the performance of detecting black-box LLMs is low because existing models focus on probabilistic features. Second, most AIGT detectors have been tested on a single-candidate setting, which assumes that we know the origin of an AIGT and which may deviate from the real-world scenario. To resolve these challenges, we propose DART, which consists of four steps: rephrasing, semantic parsing, scoring, and multiclass classification. We conducted three experiments to test the performance of DART. The experimental result shows that DART can discriminate multiple black-box LLMs without probabilistic features and the origin of AIGT.

Junhyuk Choi, Jihwan Seol, Nayeon Kim et al.

Speech-aware Language Models (SpeechLMs) have fundamentally transformed human-AI interaction by enabling voice-based communication, yet they may exhibit acoustic-based gender differentiation where identical questions lead to different responses based on the speaker's gender. This paper propose a new dataset that enables systematic analysis of this phenomenon, containing 9,208 speech samples across three categories: Gender-Independent, Gender-Stereotypical, and Gender-Dependent. We further evaluated LLaMA-Omni series and discovered a paradoxical pattern; while overall responses seems identical regardless of gender, the pattern is far from unbiased responses. Specifically, in Gender-Stereotypical questions, all models consistently exhibited male-oriented responses; meanwhile, in Gender-Dependent questions where gender differentiation would be contextually appropriate, models exhibited responses independent to gender instead. We also confirm that this pattern does not result from neutral options nor perceived gender of a voice. When we allow neutral response, models tends to respond neutrally also in Gender-Dependent questions. The paradoxical pattern yet retains when we applied gender neutralization methods on speech. Through comparison between SpeechLMs with corresponding backbone LLMs, we confirmed that these paradoxical patterns primarily stem from Whisper speech encoders, which generates male-oriented acoustic tokens. These findings reveal that current SpeechLMs may not successfully remove gender biases though they prioritized general fairness principles over contextual appropriateness, highlighting the need for more sophisticated techniques to utilize gender information properly in speech technology.

Junhyuk Choi, Ro-hoon Oh, Jihwan Seol et al.

We introduce VoiceBBQ, a spoken extension of the BBQ (Bias Benchmark for Question Answering) - a dataset that measures social bias by presenting ambiguous or disambiguated contexts followed by questions that may elicit stereotypical responses. Due to the nature of speech, social bias in Spoken Language Models (SLMs) can emerge from two distinct sources: 1) content aspect and 2) acoustic aspect. The dataset converts every BBQ context into controlled voice conditions, enabling per-axis accuracy, bias, and consistency scores that remain comparable to the original text benchmark. Using VoiceBBQ, we evaluate two SLMs - LLaMA-Omni and Qwen2-Audio - and observe architectural contrasts: LLaMA-Omni resists acoustic bias while amplifying gender and accent bias, whereas Qwen2-Audio substantially dampens these cues while preserving content fidelity. VoiceBBQ thus provides a compact, drop-in testbed for jointly diagnosing content and acoustic bias across spoken language models.

Junhyuk Choi, Hyeonchu Park, Haemin Lee et al.

Recent advances in Large Language Models (LLMs) have generated significant interest in their capacity to simulate human-like behaviors, yet most studies rely on fictional personas rather than actual human data. We address this limitation by evaluating LLMs' ability to predict individual economic decision-making using Pay-What-You-Want (PWYW) pricing experiments with real 522 human personas. Our study systematically compares three state-of-the-art multimodal LLMs using detailed persona information from 522 Korean participants in cultural consumption scenarios. We investigate whether LLMs can accurately replicate individual human choices and how persona injection methods affect prediction performance. Results reveal that while LLMs struggle with precise individual-level predictions, they demonstrate reasonable group-level behavioral tendencies. Also, we found that commonly adopted prompting techniques are not much better than naive prompting methods; reconstruction of personal narrative nor retrieval augmented generation have no significant gain against simple prompting method. We believe that these findings can provide the first comprehensive evaluation of LLMs' capabilities on simulating economic behavior using real human data, offering empirical guidance for persona-based simulation in computational social science.

Byungjun Kim, Minju Kim, Hyeonchu Park et al.

As malicious users increasingly employ phonetic substitution to evade hate speech detection, researchers have investigated such strategies. However, two key challenges remain. First, existing studies have overlooked the Korean language, despite its vulnerability to phonetic perturbations due to its phonographic nature. Second, prior work has primarily focused on constructing datasets rather than developing architectural defenses. To address these challenges, we propose (1) PHonetic-Informed Substitution for Hangul (PHISH) that exploits the phonological characteristics of the Korean writing system, and (2) Mixed Encoding of Semantic-pHonetic features (MESH) that enhances the detector's robustness by incorporating phonetic information at the architectural level. Our experimental results demonstrate the effectiveness of our proposed methods on both perturbed and unperturbed datasets, suggesting that they not only improve detection performance but also reflect realistic adversarial behaviors employed by malicious users.

Junhyuk Choi, Minju Kim, Yeseon Hong et al.

As large vision language models(LVLMs) rapidly advance, concerns about their potential to learn and generate social biases and stereotypes are increasing. Previous studies on LVLM's stereotypes face two primary limitations: metrics that overlooked the importance of content words, and datasets that overlooked the effect of color. To address these limitations, this study introduces new evaluation metrics based on the Stereotype Content Model (SCM). We also propose BASIC, a benchmark for assessing gender, race, and color stereotypes. Using SCM metrics and BASIC, we conduct a study with eight LVLMs to discover stereotypes. As a result, we found three findings. (1) The SCM-based evaluation is effective in capturing stereotypes. (2) LVLMs exhibit color stereotypes in the output along with gender and race ones. (3) Interaction between model architecture and parameter sizes seems to affect stereotypes. We release BASIC publicly on [anonymized for review].

Junhyuk Choi, Yeseon Hong, Bugeun Kim

Large Language Models (LLMs) have been recently adopted in interactive systems requiring communication. As the false belief in a model can harm the usability of such systems, LLMs should not have cognitive biases that humans have. Psychologists especially focus on the False Consensus Effect (FCE), a cognitive bias where individuals overestimate the extent to which others share their beliefs or behaviors, because FCE can distract smooth communication by posing false beliefs. However, previous studies have less examined FCE in LLMs thoroughly, which needs more consideration of confounding biases, general situations, and prompt changes. Therefore, in this paper, we conduct two studies to examine the FCE phenomenon in LLMs. In Study 1, we investigate whether LLMs have FCE. In Study 2, we explore how various prompting styles affect the demonstration of FCE. As a result of these studies, we identified that popular LLMs have FCE. Also, the result specifies the conditions when FCE becomes more or less prevalent compared to normal usage.