arXiv subjects

Sangdo Han

Publications and source records attributed to Sangdo Han.

6 recordsLinked to original sources

arXiv2026

Swapping the Judge Changes the Ranking: A Preregistered Study of Cross-Provider Replication in LLM-Judged System Comparisons

Practitioners who compare systems with an LLM judge and have no human labels often check a conclusion by repeating it with a judge from another provider. We test how far that check can be trusted. In a preregistered study (with a disclosed post-registration reduction of the judge set), five judge models from three providers re-judged 4,000 Chatbot Arena battles (nine systems, 33 system pairs) that carry human votes, each in both response orders. Agreement with the human vote was low at the verdict level (median Cohen's kappa = 0.22), and system rankings did not survive a change of judge: Kendall's tau with the human ranking ranged from 0.17 to 0.89 (median 0.67), so the preregistered hypothesis that rankings remain stable was not supported. Conclusions replicated by two low-cost judges from different providers matched the human conclusion more often than single-judge conclusions (+0.10 precision), but the gain came from filtering out one poorly aligned judge, and replication involving that judge left a conclusion for only 35% of comparisons. Judges that agreed with humans reached a stable conclusion with no more verdicts than human votes required; the others failed to converge on 26-70% of system pairs at the sample sizes tested (up to 100 verdicts per pair). Disagreements with the human vote co-occurred across judges far more often than independence predicts, although a single human vote per battle cannot separate shared judge bias from voter noise.

cs.CL↗

arXiv2026

Same Rule, Different Verdicts: Rubric Language and Clause Structure in LLM Judges for Korean Support Dialogues

Services that operate in Korean often write their evaluation rubrics in Korean and hand them to an LLM judge. We test whether a judge's verdict depends on the language of the rubric and on how a rubric item is phrased. We write 12 criteria for support dialogues in four clause structures (affirmative, negated, conditional, exception) such that two pairs of structures have the same meaning, and we give each item in Korean and in English. Six low-cost models from three providers, plus one reference model, judge 60 translated ESConv dialogues and 144 constructed boundary cases under every combination (51,744 requests across the seven models). The analysis plan was fixed and committed before data collection. Cross-provider agreement is lower with Korean rubrics than with English rubrics (Cohen's kappa 0.687 vs. 0.745; difference -0.058, 95% CI [-0.072,-0.045]). Disagreement concentrates in negated, conditional, and exception items (odds ratio 5.6 relative to affirmative items). A single model changes its verdict between two items with the same meaning in 11-15% of cases. Two hypotheses are not supported: models from the same provider do not agree more than models from different providers, and adding paired examples does not reduce the language gap. We measure consistency only; no human labels are used, and all materials were drafted by an LLM.

cs.CL↗

arXiv2026

Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered Study

Prompt optimizers rewrite a prompt to raise one target metric, but prompts also state requirements the metric does not score, such as an output format, citations, or abstention. In a preregistered study, we run GEPA, MIPROv2, and TextGrad on HotpotQA, SQuAD 2.0, and IFEval and count per-item violations of unscored requirements with deterministic checks. By the preregistered criterion, all three optimizers produce regressions, substantially on HotpotQA, where net regression in citation validity reaches 10.7 to 41.6 points while exact match rises by 21 to 34 points. A post-hoc decomposition changes this reading. The optimized prompts elicit reasoning before the required JSON object, and under the 200-token output cap used throughout, 13.9% to 47.0% of responses end before any answer appears. Among parseable outputs, net regression is within 3 points of zero. With a 1,024-token cap, extraction failures disappear, content regression stays below 1 point, and exact match rises further. Two simple gates fail the preregistered criterion. The side effect is narrower than hypothesized: optimized prompts are more accurate and break an explicit output contract, and a lenient target metric does not show the cost.

cs.CL↗

arXiv2026

Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with Humans

LLM judges are increasingly deployed as panels, and disagreement among panel members is often read as a symptom of an unclear rubric. We test a label-free procedure that turns this disagreement into rubric repairs. The procedure decomposes each rubric into sub-criteria, ranks them by cross-judge disagreement on a development split, and has an editor model rewrite only the most contested ones. An additional stage that moves text-checkable sub-criteria to deterministic checkers transferred none in our evaluation. Human labels are never used to select or edit clauses; they are used only to evaluate the outcome. We pre-specified four hypotheses in a version-controlled protocol and evaluated six rubric conditions with a panel of five judges from three providers on SummEval, the HealthBench meta-evaluation, and USR Topical-Chat, for a total of 129,770 judge requests, excluding retries. On SummEval, the procedure raised inter-judge Krippendorff's $α$ by 0.069 (95% CI 0.046 to 0.092) over the original rubric and by 0.074 over a control that applied the same edits to an equal number of randomly chosen clauses that were not selected. Agreement with expert ratings showed no detectable change (Kendall $τ$ difference -0.007, 95% CI -0.037 to 0.021). On HealthBench and USR, neither inter-judge agreement nor human agreement met the preregistered effect criteria. In a preregistered secondary comparison, human agreement after editing the contested clauses was lower than after editing the control clauses on all three datasets in point estimate, although no interval excluded zero. Selecting clauses by disagreement makes judges agree with each other more than editing arbitrary clauses does, but in our setting the added consensus did not bring the judges closer to human annotators. We will release code, frozen rubrics, item identifiers, and judge scores.

cs.CL↗

arXiv2025

CL3DOR: Contrastive Learning for 3D Large Multimodal Models via Odds Ratio on High-Resolution Point Clouds

Recent research has demonstrated that Large Language Models (LLMs) are not limited to text-only tasks but can also function as multimodal models across various modalities, including audio, images, and videos. In particular, research on 3D Large Multimodal Models (3D LMMs) is making notable strides, driven by the potential of processing higher-dimensional data like point clouds. However, upon closer examination, we find that the visual and textual content within each sample of existing training datasets lacks both high informational granularity and clarity, which serve as a bottleneck for precise cross-modal understanding. To address these issues, we propose CL3DOR, Contrastive Learning for 3D large multimodal models via Odds ratio on high-Resolution point clouds, designed to ensure greater specificity and clarity in both visual and textual content. Specifically, we increase the density of point clouds per object and construct informative hard negative responses in the training dataset to penalize unwanted responses. To leverage hard negative responses, we incorporate the odds ratio as an auxiliary term for contrastive learning into the conventional language modeling loss. CL3DOR achieves state-of-the-art performance in 3D scene understanding and reasoning benchmarks. Additionally, we demonstrate the effectiveness of CL3DOR's key components through extensive experiments.

cs.CV↗

arXiv2022

Cross-lingual Transfer Learning for Fake News Detector in a Low-Resource Language

Development of methods to detect fake news (FN) in low-resource languages has been impeded by a lack of training data. In this study, we solve the problem by using only training data from a high-resource language. Our FN-detection system permitted this strategy by applying adversarial learning that transfers the detection knowledge through languages. To assist the knowledge transfer, our system judges the reliability of articles by exploiting source information, which is a cross-lingual feature that represents the credibility of the speaker. In experiments, our system got 3.71% higher accuracy than a system that uses a machine-translated training dataset. In addition, our suggested cross-lingual feature exploitation for fake news detection improved accuracy by 3.03%.

cs.CL↗