Aligning to What? Limits to RLHF Based Alignment

• URL: http://arxiv.org/abs/2503.09025v1
• Date: Wed, 12 Mar 2025 03:24:44 GMT
• Title: Aligning to What? Limits to RLHF Based Alignment
• Authors: Logan Barnhart, Reza Akbarian Bafghi, Stephen Becker, Maziar Raissi,
• Abstract summary: Reinforcement Learning from Human Feedback (RLHF) is increasingly used to align large language models with human preferences.<n>This study investigates the relationship between RLHF and both covert and overt biases in large language models.
• Score: 2.624902795082451
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) is increasingly used to align large language models (LLMs) with human preferences. However, the effectiveness of RLHF in addressing underlying biases remains unclear. This study investigates the relationship between RLHF and both covert and overt biases in LLMs, particularly focusing on biases against African Americans. We applied various RLHF techniques (DPO, ORPO, and RLOO) to Llama 3 8B and evaluated the covert and overt biases of the resulting models using matched-guise probing and explicit bias testing. We performed additional tests with DPO on different base models and datasets; among several implications, we found that SFT before RLHF calcifies model biases. Additionally, we extend the tools for measuring biases to multi-modal models. Through our experiments we collect evidence that indicates that current alignment techniques are inadequate for nebulous tasks such as mitigating covert biases, highlighting the need for capable datasets, data curating techniques, or alignment tools.

Related papers

• How far can bias go? -- Tracing bias from pretraining data to alignment [54.51310112013655]
  This study examines the correlation between gender-occupation bias in pre-training data and their manifestation in LLMs.<n>Our findings reveal that biases present in pre-training data are amplified in model outputs.
  arXiv  Detail & Related papers  (2024-11-28T16:20:25Z)
• How to Evaluate Reward Models for RLHF [51.31240621943791]
  We introduce a new benchmark for reward models that quantifies their ability to produce strong language models through RLHF (Reinforcement Learning from Human Feedback) We build a predictive model of downstream LLM performance by evaluating the reward model on proxy tasks. We launch an end-to-end RLHF experiment on a large-scale crowdsourced human preference platform to view real reward model downstream performance as ground truth.
  arXiv  Detail & Related papers  (2024-10-18T21:38:21Z)
• Measuring memorization in RLHF for code completion [18.3607188787591]
  Reinforcement learning with human feedback (RLHF) has become the dominant method to align large models to user preferences. We analyze how training data memorization can surface and propagate through each phase of RLHF and direct preference learning. Our work suggests that RLHF, as opposed to direct preference learning, is a safer way to mitigate the risk of regurgitating sensitive preference data when aligning large language models.
  arXiv  Detail & Related papers  (2024-06-17T16:33:35Z)
• Preference Learning Algorithms Do Not Learn Preference Rankings [62.335733662381884]
  We study the conventional wisdom that preference learning trains models to assign higher likelihoods to more preferred outputs than less preferred outputs. We find that most state-of-the-art preference-tuned models achieve a ranking accuracy of less than 60% on common preference datasets.
  arXiv  Detail & Related papers  (2024-05-29T21:29:44Z)
• On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization [33.331389392270665]
  preference matching (PM) RLHF is a novel approach that aligns large language models with the preference distribution of the reward model under the Bradley--Terry--Luce/Plackett--Luce model. Central to our approach is a PM regularizer that takes the form of the negative logarithm of the LLM's policy probability distribution over responses. For practical implementation, we introduce a conditional variant of PM RLHF that is tailored to natural language generation.
  arXiv  Detail & Related papers  (2024-05-26T07:00:05Z)
• Disentangling Length from Quality in Direct Preference Optimization [93.74831404396174]
  Reinforcement Learning from Human Feedback (RLHF) has been a crucial component in the recent success of Large Language Models. RLHF is know to exploit biases in human preferences, such as verbosity. We develop a principled but simple regularization strategy that prevents length exploitation, while still maintaining improvements in model quality.
  arXiv  Detail & Related papers  (2024-03-28T06:03:47Z)
• Understanding the Effects of RLHF on LLM Generalisation and Diversity [26.56388427640671]
  Large language models (LLMs) fine-tuned with reinforcement learning from human feedback (RLHF) have been used in some of the most widely deployed AI models to date. We present an analysis of how each stage of the process affects two key properties: out-of-distribution (OOD) generalisation and output diversity.
  arXiv  Detail & Related papers  (2023-10-10T09:25:44Z)
• A Long Way to Go: Investigating Length Correlations in RLHF [59.49656695716066]
  This paper demonstrates, on three diverse settings, that optimizing for response length is a significant factor behind RLHF. We find improvements in reward to largely be driven by increasing response length, instead of other features. Even a purely length-based reward reproduces most downstream RLHF improvements over supervised fine-tuned models.
  arXiv  Detail & Related papers  (2023-10-05T17:38:28Z)
• UltraFeedback: Boosting Language Models with Scaled AI Feedback [99.4633351133207]
  We present textscUltraFeedback, a large-scale, high-quality, and diversified AI feedback dataset. Our work validates the effectiveness of scaled AI feedback data in constructing strong open-source chat language models.
  arXiv  Detail & Related papers  (2023-10-02T17:40:01Z)
• Mitigating the Alignment Tax of RLHF [76.4300447532456]
  aligning LLMs under Reinforcement Learning with Human Feedback can lead to forgetting pretrained abilities, also known as the alignment tax. We propose model averaging to maximize alignment performance while incurring minimal alignment tax. We validate HMA's performance across a range of RLHF algorithms over OpenLLaMA-3B and further extend our findings to Mistral-7B.
  arXiv  Detail & Related papers  (2023-09-12T14:16:54Z)
• RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback [5.3113139864044046]
  Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but gathering high-quality preference labels is expensive. RLAIF offers a promising alternative that trains the reward model (RM) on preferences generated by an off-the-shelf LLM. Our results suggest that RLAIF can achieve performance on-par with using human feedback, offering a potential solution to the scalability limitations of RLHF.
  arXiv  Detail & Related papers  (2023-09-01T05:53:33Z)
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model [119.65409513119963]
  We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
  arXiv  Detail & Related papers  (2023-05-29T17:57:46Z)

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.