Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

• URL: http://arxiv.org/abs/2404.04475v1
• Date: Sat, 6 Apr 2024 02:29:02 GMT
• Title: Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
• Authors: Yann Dubois, Balázs Galambosi, Percy Liang, Tatsunori B. Hashimoto,
• Abstract summary: We propose a simple regression analysis approach for controlling biases in auto-evaluations. As a real case study, we focus on reducing the length bias of AlpacaEval, a benchmark for chat LLMs. We introduce a length-controlled AlpacaEval that aims to answer the counterfactual question: "What would the preference be if the model's and baseline's output had the same length?"
• Score: 59.48172585509628
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM-based auto-annotators have become a key component of the LLM development process due to their cost-effectiveness and scalability compared to human-based evaluation. However, these auto-annotators can introduce complex biases that are hard to remove. Even simple, known confounders such as preference for longer outputs remain in existing automated evaluation metrics. We propose a simple regression analysis approach for controlling biases in auto-evaluations. As a real case study, we focus on reducing the length bias of AlpacaEval, a fast and affordable benchmark for chat LLMs that uses LLMs to estimate response quality. Despite being highly correlated with human preferences, AlpacaEval is known to favor models that generate longer outputs. We introduce a length-controlled AlpacaEval that aims to answer the counterfactual question: "What would the preference be if the model's and baseline's output had the same length?". To achieve this, we first fit a generalized linear model to predict the biased output of interest (auto-annotator preferences) based on the mediators we want to control for (length difference) and other relevant features. We then obtain length-controlled preferences by predicting preferences while conditioning the GLM with a zero difference in lengths. Length-controlling not only improves the robustness of the metric to manipulations in model verbosity, we also find that it increases the Spearman correlation with LMSYS' Chatbot Arena from 0.94 to 0.98. We release the code and leaderboard at https://tatsu-lab.github.io/alpaca_eval/ .

Related papers

• CREAM: Consistency Regularized Self-Rewarding Language Models [34.325289477993586]
  Self-rewarding large language models (LLM) have successfully applied LLM-as-a-Judge to improve the alignment performance without the need of human annotations for preference data. However, there is no guarantee of accuracy in the rewarding and ranking, which is critical for ensuring accurate rewards and high-quality preference data. We propose a Consistency Regularized sElf-rewarding lAnguage Model (CREAM) that leverages the rewarding consistency across different iterations to regularize the self-rewarding training.
  arXiv  Detail & Related papers  (2024-10-16T16:51:01Z)
• Post-hoc Reward Calibration: A Case Study on Length Bias [28.266675778940133]
  Reward models (RMs) can develop biases by exploiting spurious correlations in their training data. These biases can lead to incorrect output rankings, sub-optimal model evaluations, and the amplification of undesirable behaviours. This paper addresses the challenge of correcting such biases without additional data and training.
  arXiv  Detail & Related papers  (2024-09-25T22:30:42Z)
• Aligning Large Language Models with Self-generated Preference Data [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models (LLMs) with human preferences. Our key idea is leveraging the human prior knowledge within the small (seed) data. We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Aligning Large Language Models via Fine-grained Supervision [20.35000061196631]
  Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human feedback to improve model alignment. We propose a method to enhance LLM alignment through fine-grained token-level supervision.
  arXiv  Detail & Related papers  (2024-06-04T20:21:45Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• Self-Play Preference Optimization for Language Model Alignment [75.83359213697854]
  Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences. We propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game. Our approach, dubbed Self-Play Preference Optimization (SPPO), utilizes iterative policy updates to provably approximate the Nash equilibrium.
  arXiv  Detail & Related papers  (2024-05-01T17:59:20Z)
• Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement [75.7148545929689]
  Large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We formally define LLM's self-bias - the tendency to favor its own generation. We analyze six LLMs on translation, constrained text generation, and mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2024-02-18T03:10:39Z)
• Dissecting Human and LLM Preferences [80.55271307662365]
  We find that humans are less sensitive to errors, favor responses that support their stances, and show clear dislike when models admit their limits. advanced LLMs like GPT-4-Turbo emphasize correctness, clarity, and harmlessness more. We show that preference-based evaluation can be intentionally manipulated.
  arXiv  Detail & Related papers  (2024-02-17T14:34:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.