Evaluating Language Model Bias with 🤗 Evaluate

Evaluating large language models trained on code

GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models

The paper introduces GPTBIAS, a framework that uses powerful large language models like GPT‑4 to evaluate bias in other LLMs. It employs specially crafted prompts called Bias Attack Instructions to probe for bias and outputs a bias score along with detailed information such as bias types, affected demographics, keywords, reasons, and improvement suggestions. Extensive experiments demonstrate the framework’s effectiveness and usability.

Very Large Language Models and How to Evaluate Them

Lower-Resource, Higher Scores: Language Bias in LLM Evaluators

The paper demonstrates that large language model (LLM) evaluators, whether reward‑model based or prompted LLM‑as‑a‑Judge, exhibit significant language bias in multilingual settings. Experiments with semantically identical instruction‑response pairs across 23 languages reveal that lower‑resource languages receive higher scores, a bias that persists across eight open‑weight evaluators and is not detectable by standard pairwise accuracy metrics. The authors link the bias to model uncertainty and language identity, showing it cannot be explained by content difficulty alone.

Sleight of Word Benchmark: Can Language Models Notice If Their Own Output Was Tampered With?

arXiv:2608.29921v1 Announce Type: cross Abstract: The output of a Language Model can be tampered with \emph{while} the model is writing it. A simple test can thus be constructed by evaluating the mod...

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

arXiv:2607. 02235v1 Announce Type: cross Abstract: LLM-as-a-Judge has become the dominant evaluation paradigm for many natural language generation tasks, due to shortcomings of conventional metrics and high correlations with human judgment, albeit mostly in English.

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

arXiv:2607.02235v2 Announce Type: replace-cross Abstract: LLM-as-a-Judge has become the dominant evaluation paradigm for many natural language generation tasks (albeit mostly in English) due to short...

EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models

EvalDetectBench is an open pipeline and benchmark designed to measure evaluation awareness in frontier large language models, enabling practitioners to test models against any Inspect-compatible evaluation. It includes a curated transcript suite from current frontier system-card evaluations and diverse deployment sources, and it assesses both how reliably models recognize they are being evaluated and how detectable individual benchmarks are. The benchmark addresses systematic bias by calibrating probes per model and harmonizing generator selection to correct for variance caused by model identity and prompt choice.

Beyond the Name: Demographic Leakage in De-Identified R\'esum\'es and Evaluation Artifacts in LLM Bias Audits

The paper examines whether removing declared language fields from de‑identified résumés eliminates demographic leakage in large language models. By keeping language attributes identical and varying only unstructured prose across five ethnocultural groups and three cue‑salience levels, the authors find that non‑language text still allows target‑group recovery (average 0.757, reaching 1.000 under high salience). They also show that evaluation design—such as allowing or forbidding ties—dramatically affects LLM‑as‑a‑judge outcomes, underscoring the importance of evaluation protocol in bias audits.

LLJ Cards: Best practices for the Use of LLMs as Judges

arXiv:2609.24516v1 Announce Type: new Abstract: In recent years, large language models (LLMs) have emerged as a popular alternative for evaluation. Often referred to as LLMs as judges (LLJs), these s...

PADM\'E: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators

PADM'E is a method for synthesizing preference‑aligned data to meta‑evaluate language‑model (LM) evaluators of agentic behaviors. It reframes meta‑evaluation as a preference judgment problem, generating criterion‑based data with small LMs and no human involvement. In a prototype, PADM'E produced 1,000 samples across four domains and three criteria, and human validation showed agreement with human judgment rising from 73% to 85% compared to a naive baseline.

EviSI: An Evidence-Based Evaluation Agent for Simultaneous Interpreting

EviSI is an evidence‑based evaluation agent for low‑latency simultaneous speech‑to‑speech translation. It combines Multidimensional Quality Metrics with interpreter‑developed criteria, using shared source evidence to assess four dimensions—Anchor, Event, Logic, and Fluency—while deduplicating verified errors before scoring. On English‑to‑Chinese and Chinese‑to‑English data, EviSI’s rankings correlate strongly with human judgments, outperforming BLEU and COMET, and its multilingual extension maintains these correlations across five language directions.