Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking
Mirrored from arXiv — NLP / Computation & Language for archival readability. Support the source by reading on the original site.
Computer Science > Computation and Language
arXiv:2605.27914 (cs)
[Submitted on 27 May 2026]
Title:Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking
View a PDF of the paper titled Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking, by Yuming (Rapheal) Huang and 3 other authors
View PDF
HTML (experimental)
Abstract:Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities saturates near rho ~ 0.45, and an LLM-as-judge proxy alone risks circularity: a judge sharing the target's training cohort cannot independently verify it. Anchoring validity to a single human-rater consensus does not extend to capabilities where humans themselves disagree.
We propose a replication-first paradigm: instead of anchoring on one rater group, we certify the instrument via four orthogonal properties -- reliability across K runs, cross-instrument replication across architecturally distinct judges, historical-footprint calibration via judges from earlier training cohorts, and pre-registered prediction. We test it on emotional accompaniment by letting the rubric self-evolve data-driven across iterations: the dimensions are not pre-stipulated and the procedure stabilizes to a 9-dimension set. Pre-registration applies to 10 falsifiable hypotheses and 11 forward predictions, committed before any test data was collected.
Applied to 49 models across 8 families, the paradigm surfaces what aggregate scores hide. On advice-restraint -- whether a model refrains from giving unsolicited solutions in empathic contexts -- gpt-5 falls 1.87 points from gpt-4.1 and Opus-4.7 falls 0.629 from Opus-4.6, while aggregate scores stay flat. The regression survives three user-proxy swaps (95% of magnitude), replicates across a 5-family judge stack and a 17-month cohort gap, and persists on 74 held-out real ESConv conversations (rho in [0.749, 0.850]); the instrument reaches ordinal Krippendorff alpha = 0.91. As a by-product, the paradigm acts as a saturation-source diagnostic, separating instrumental ceilings (breakable by rubric refinement) from structural ceilings (needing scenario or roster intervention).
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.27914 [cs.CL] |
| (or arXiv:2605.27914v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.27914
arXiv-issued DOI via DataCite (pending registration)
|
Submission history
From: Rapheal (Yuming) Huang [view email][v1] Wed, 27 May 2026 03:41:11 UTC (732 KB)
Full-text links:
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
View a PDF of the paper titled Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking, by Yuming (Rapheal) Huang and 3 other authors
References & Citations
Loading...
Bookmark
Bibliographic Tools
Code, Data, Media
Demos
Related Papers
About arXivLabs
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — NLP / Computation & Language
-
GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity
Jul 2
-
Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds
Jul 2
-
EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems
Jul 2
-
Mapping the Evaluation Frontier: An Empirical Survey of the Bias-Reliability Tradeoff Across Eleven Evaluator-Agent Conditions
Jul 2
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.