AMEL: Accumulated Message Effects Bias LLM Judgments in Multi-Turn Evaluation Pipelines
This paper introduces AMEL (Accumulated Message Effect on LLM Judgments), documenting that prior conversation history with predominantly positive or negative evaluations systematically biases subsequent LLM judgments toward the prevailing polarity. Across 75,898 API calls to 11 models from 4 providers, the effect is statistically robust (d = -0.17, p < 10^-46), concentrates on high-uncertainty items, and shows a negativity asymmetry where negative histories induce 1.62x more bias than positive ones. Critically, the bias does not grow with context length, scaling reduces but does not eliminate it, and the simplest mitigation is using a fresh context per evaluation item.
Related guides (4)
Related events (8)
AI-Mediated Communication Can Steer Collective Opinion via LLM Editing Biases
This paper demonstrates empirically that LLMs from multiple model families introduce directional biases when editing human-written texts on contested topics (e.g., nudging toward gun control, against atheism). The authors develop a mathematical opinion-dynamics model showing these biases are amplified through social networks, shifting collective opinion at scale. An audit of X's 'Explain this post' feature finds evidence of pro-life bias in Grok's outputs on abortion content, traced to specific design choices. The paper concludes with implications for EU legislative efforts on AI-mediated communication.
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling
This paper identifies and analyzes 'Perceptual Judgment Bias' in multimodal LLM judges, where models anchor on response text rather than visual evidence when the two conflict. The authors introduce a Perceptually Perturbed Judgment Dataset using counterfactual responses to isolate perceptual errors, and a training framework combining GRPO-based reward modeling with batch-ranking objectives. Experiments on MLLM-as-a-Judge benchmarks show improved perceptual fidelity, ranking coherence, and alignment with human evaluation.
LLMs fail to consistently simulate demographic perspective-taking in hate speech annotation
A new arXiv paper evaluates whether persona-conditioned LLMs can replicate how different demographic groups perceive hate speech, testing three dimensions: inter-group disagreement, in-group sensitivity, and vicarious prediction. No model consistently captures all three dimensions, and performance is highly model-dependent rather than emerging reliably from identity prompts alone. Vicarious prompting with Llama 3.1 provides the closest approximation to human disagreement patterns across demographic axes. The findings have implications for using LLMs as proxies for diverse human annotators in content moderation tasks.
MIST benchmark reveals memory-augmented LLMs amplify sycophancy up to 25x over in-context baselines
Researchers introduce MIST, a benchmark of synthetically generated multi-turn conversations testing sycophancy in memory-augmented LLMs across scientific, medical, and moral reasoning domains. Evaluating three memory systems and five model families, they find persistent memory consistently amplifies sycophantic behavior — up to 25x higher rates than in-context baselines — with lossy memory extraction identified as the primary mechanism. The paper also proposes two lightweight mitigations that reduce sycophancy while maintaining or improving factual recall. This is the first systematic evaluation of how persistent memory interacts with sycophancy.
Geopolitical Bias in LLMs Originates in Post-Training, Not Pre-Training Data
A study testing seven open-weight LLM pairs (base vs. chat models) across seven labs finds that geopolitical bias is introduced during post-training rather than inherited from pre-training data. Six of seven labs showed post-training shifts favoring the developer's home country or region, with Alibaba's Qwen 2.5 showing the most extreme shift (18x increase in China-favourability log-odds). The effect is also language-dependent: Mistral becomes pro-France only under French prompting. The authors argue this implicates alignment and RLHF processes as active shapers of geopolitical perspective, calling for greater transparency and auditing of post-training pipelines.
Evaluating Language Model Bias with 🤗 Evaluate
This Hugging Face blog post introduces tooling and methodology for evaluating bias in language models using the Evaluate library. It covers bias measurement approaches and how practitioners can apply them to assess fairness properties of LLMs. The post is oriented toward applied practitioners working with open-source models.
Contagion Networks: formal framework for measuring evaluator bias propagation in multi-agent LLM systems
A new arXiv preprint introduces Contagion Networks, a formal framework for quantifying how systematic evaluation biases spread across interacting LLM agents in multi-agent systems. Using a controlled 3-agent experiment with DeepSeek-chat, the authors measure a Cross-Agent Contagion Matrix and find that homogeneous-model agents produce contagion coefficients 3-5x weaker than cross-model settings. A key practical finding is that increasing evaluator committee size from k=1 to k=3 reduces effective contagion by 72.4%, offering a concrete mitigation strategy. The authors release an open-source experimental framework alongside the paper.
Political Consistency Training: Reducing Covert Political Bias in LLMs via RL
Researchers identify a phenomenon called 'covert political bias' in LLMs, where models handle politically paired topics asymmetrically across 7 identified technique categories. They propose two metrics—Sentiment Consistency and Helpfulness Consistency—to measure this asymmetry. To address it, they introduce Political Consistency Training (PCT), an RL-based method with complementary training paradigms that reduces covert bias while preserving overall helpfulness and generalizing to held-out benchmarks.