llm-as-a-judge

Tag

Cards List
#llm-as-a-judge

The Lifecycle of LLM-as-a-Judge for Large-Scale Recommendation Explanations

arXiv cs.AI · yesterday Cached

This paper presents a lifecycle framework for using LLMs as judges to evaluate recommendation explanations at Netflix, covering phases from development to deployment and monitoring, with positive A/B test results showing improved user engagement.

0 favorites 0 likes
#llm-as-a-judge

Mitigating Scoring Bias in LLM-as-a-Judge via Random Number Generation

arXiv cs.CL · 2026-08-07 Cached

This paper proposes a novel method to mitigate scoring bias in LLM-as-a-Judge by having LLMs randomly generate numbers to measure their latent numerical bias, then rectifying token generation probabilities accordingly. Experiments across four tasks show the method outperforms baselines and reveals that scoring bias varies across models, tasks, and score ranges.

0 favorites 0 likes
#llm-as-a-judge

SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI

arXiv cs.AI · 2026-07-22 Cached

This paper introduces SysAdmin, a benchmark that positions frontier language models as autonomous system administrators in a high-fidelity Linux sandbox to measure power-seeking propensity. Across 2800 tasks, the authors find minimal spontaneous power-seeking (0-5% after bias correction) but identify other failure modes such as specification gaming and resistance to goal modification.

0 favorites 0 likes
#llm-as-a-judge

@freeCodeCamp: AI agents can behave differently from one run to the next, which makes regressions hard to catch. In this tutorial, Dar…

X AI KOLs Following · 2026-07-21 Cached

This tutorial demonstrates how to build a repeatable evaluation harness for AI agents using rule-based checks and an LLM-as-a-judge, leveraging LangChain, Ollama, and Qwen to test local agents with clear pass/fail results.

0 favorites 0 likes
#llm-as-a-judge

Operationalising Multi-Dimensional Evaluation for Conversational Agents: A Scalable, Governed Pipeline with Selective Re-evaluation and Model Benchmarking

arXiv cs.AI · 2026-07-15 Cached

This paper introduces GenAI Evaluation, a governed and configuration-driven pipeline for scalable multi-dimensional evaluation of retail conversational agents. It achieves high accuracy using LLM-as-a-judge scoring with selective re-evaluation, validated against human-labeled data.

0 favorites 0 likes
#llm-as-a-judge

Eval-Pair Matrix: Answer-Paired Meta-Evaluation of LLM Judges for Grounded RAG

arXiv cs.CL · 2026-07-14 Cached

Introduces Eval-Pair Matrix, a controlled meta-evaluation protocol for source-grounded RAG that induces hidden contradictions to detect self-leniency in LLM judges. The study finds minimal same-model effects and emphasizes methodological improvements for RAG judge studies.

0 favorites 0 likes
#llm-as-a-judge

Challenges and Recommendations for LLMs-as-a-Judge in Multilingual Settings and Low-Resource Languages

arXiv cs.CL · 2026-07-03 Cached

This paper analyzes the use of LLM-as-a-Judge in multilingual and low-resource settings, finding inconsistent evaluation outcomes and overtrust in LLM judgments, and provides recommendations for better practices.

0 favorites 0 likes
#llm-as-a-judge

@omarsar0: LLM-as-a-Judge explained in ~10 mins. Knowing how to build AI verifiers and judges is one of the most important emergin…

X AI KOLs Following · 2026-06-29 Cached

A quick introduction to the LLM-as-a-Judge concept, explaining how to build AI verifiers and judges, and pointing to resources to learn more.

0 favorites 0 likes
#llm-as-a-judge

Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA

arXiv cs.CL · 2026-06-29 Cached

This paper tests the assumption that LLMs judge better than they generate in in-context QA, finding generation accuracy exceeds self-evaluation on most benchmarks, with evaluation attending less to context. The findings challenge core assumptions in self-evaluation pipelines.

0 favorites 0 likes
#llm-as-a-judge

The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation

arXiv cs.CL · 2026-06-15 Cached

This paper investigates the run-to-run reliability of LLM-as-a-Judge evaluations, finding that pairwise preferences flip 13.6% of the time on average, with significant first-position bias in GPT-4o-mini, and recommends multi-trial aggregation and position randomization.

0 favorites 0 likes
#llm-as-a-judge

Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

Hugging Face Daily Papers · 2026-06-03

This paper introduces CHERRL, a controllable environment for studying reward hacking in rubric-based reinforcement learning, where LLM-as-a-Judge biases can be injected to reproduce and analyze hacking behaviors. The authors also explore an agent-based system for automatically detecting reward hacking onset from training logs.

0 favorites 0 likes
#llm-as-a-judge

Generating and Refining Dynamic Evaluation Rubrics for LLM-as-a-Judge

arXiv cs.CL · 2026-06-01 Cached

This paper proposes a training-free method to automatically generate fine-grained evaluation rubrics for LLM-as-a-judge without human annotation, and further introduces an iterative fine-tuning strategy for a rubric generator that outperforms larger proprietary models.

0 favorites 0 likes
#llm-as-a-judge

Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs

arXiv cs.CL · 2026-06-01 Cached

This paper evaluates whether wrapping untrusted content in mock tool calls improves LLM robustness against adversarial inputs, finding it does not broadly help and sometimes increases attack success rates.

0 favorites 0 likes
#llm-as-a-judge

RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator

arXiv cs.CL · 2026-05-22 Cached

RankJudge is a benchmark generator that creates paired multi-turn conversations with injected flaws to evaluate LLM judges on their ability to correctly identify better and worse responses in complex dialogues.

0 favorites 0 likes
#llm-as-a-judge

Judge Circuits

arXiv cs.CL · 2026-05-18 Cached

This paper investigates the internal mechanisms of LLM-as-a-judge, finding a shared Latent Evaluator sub-graph in mid-to-late MLPs across models that handles abstract judging, while format-specific terminal branches map the judgment to output tokens, revealing the cause of format-induced inconsistency.

0 favorites 0 likes
#llm-as-a-judge

Magis-Bench: Evaluating LLMs on Magistrate-Level Legal Tasks

arXiv cs.CL · 2026-05-12 Cached

This article introduces Magis-Bench, a benchmark for evaluating large language models on magistrate-level legal tasks such as judicial reasoning and sentence drafting, using data from Brazilian judicial exams.

0 favorites 0 likes
#llm-as-a-judge

@ArizePhoenix: Who judges the evaluators? When you use LLM-as-a-judge, you’re trusting a model to decide whether your agent, workflow,…

X AI KOLs Following · 2026-05-07

The article discusses the challenges of debugging and evaluating LLM judges using Arize Phoenix, which traces evaluator runs via OpenTelemetry to inspect decision logic, costs, and potential biases.

0 favorites 0 likes
← Back to home

Submit Feedback