Like Father, Like Son: Kinship-Aware Preference Mapping (KARMA) for Automatic Alignment in Large Language Models
- URL: http://arxiv.org/abs/2502.18744v1
- Date: Wed, 26 Feb 2025 01:36:40 GMT
- Title: Like Father, Like Son: Kinship-Aware Preference Mapping (KARMA) for Automatic Alignment in Large Language Models
- Authors: Jeesu Jung, Chanjun Park, Sangkeun Jung,
- Abstract summary: Kinship-Aware pReference MApping (KARMA) is a novel framework that pairs responses from models with comparable competencies.<n>By constraining preference comparisons to outputs of similar complexity and quality, KARMA enhances the informativeness of preference data.<n> Empirical evaluations demonstrate that our kinship-aware approach leads to more consistent and interpretable alignment outcomes.
- Score: 2.970904425631548
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Recent advancements in Large Language Model (LLM) alignment have sought to mitigate the cost of human annotations by leveraging pretrained models to generate preference data. However, existing methods often compare responses from models with substantially different capabilities, yielding superficial distinctions that fail to provide meaningful guidance on what constitutes a superior response. To address this limitation, we propose Kinship-Aware pReference MApping (KARMA), a novel framework that systematically pairs responses from models with comparable competencies. By constraining preference comparisons to outputs of similar complexity and quality, KARMA enhances the informativeness of preference data and improves the granularity of alignment signals. Empirical evaluations demonstrate that our kinship-aware approach leads to more consistent and interpretable alignment outcomes, ultimately facilitating a more principled and reliable pathway for aligning LLM behavior with human preferences.
Related papers
- Leveraging Reasoning Model Answers to Enhance Non-Reasoning Model Capability [16.441081996257576]
We propose leveraging reasoning-intensive models to improve less computationally demanding, non-reasoning models.
We demonstrate consistent improvements across various benchmarks, underscoring the potential of this approach for advancing the ability of models to answer questions directly.
arXiv Detail & Related papers (2025-04-13T16:26:56Z) - Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric [99.56567010306807]
Large Language Models (LLMs) have become indispensable across academia, industry, and daily applications.<n>One core challenge of evaluation in the large language model (LLM) era is the generalization issue.<n>We propose Model Utilization Index (MUI), a mechanism interpretability enhanced metric that complements traditional performance scores.
arXiv Detail & Related papers (2025-04-10T04:09:47Z) - IPO: Your Language Model is Secretly a Preference Classifier [1.8921784053120494]
Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models with human preferences.<n>We propose generative LLMs as preference classifiers, thereby reducing the dependence on external human feedback or reward models to obtain preferences.<n>Our findings demonstrate that models trained through IPO achieve performance comparable to those utilizing state-of-the-art reward models for obtaining preferences.
arXiv Detail & Related papers (2025-02-22T10:59:11Z) - Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling [87.17041933863041]
We introduce a Response-conditioned Bradley-Terry (Rc-BT) model that enhances the reward model's capability in length bias mitigating and length instruction following.
We also propose the Rc-DPO algorithm to leverage the Rc-BT model for direct policy optimization (DPO) of large language models.
arXiv Detail & Related papers (2025-02-02T14:50:25Z) - Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy [104.48511402784763]
Performance Law for SR models aims to theoretically investigate and model the relationship between model performance and data quality.
We propose Approximate Entropy (ApEn) to assess data quality, presenting a more nuanced approach compared to traditional data quantity metrics.
arXiv Detail & Related papers (2024-11-30T10:56:30Z) - Ordinal Preference Optimization: Aligning Human Preferences via NDCG [28.745322441961438]
We develop an end-to-end preference optimization algorithm by approxing NDCG with a differentiable surrogate loss.
OPO outperforms existing pairwise and listwise approaches on evaluation sets and general benchmarks like AlpacaEval.
arXiv Detail & Related papers (2024-10-06T03:49:28Z) - Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback [64.67540769692074]
Large language models (LLMs) fine-tuned with alignment techniques, such as reinforcement learning from human feedback, have been instrumental in developing some of the most capable AI systems to date.
We introduce an approach called Margin Matching Preference Optimization (MMPO), which incorporates relative quality margins into optimization, leading to improved LLM policies and reward models.
Experiments with both human and AI feedback data demonstrate that MMPO consistently outperforms baseline methods, often by a substantial margin, on popular benchmarks including MT-bench and RewardBench.
arXiv Detail & Related papers (2024-10-04T04:56:11Z) - Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss.
The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
arXiv Detail & Related papers (2024-09-26T12:37:26Z) - TSO: Self-Training with Scaled Preference Optimization [14.3799656174528]
We propose TSO, a framework for preference optimization that conducts self-training preference learning without training an additional reward model.
TSO enhances the diversity of responses by constructing a model matrix and incorporating human preference responses.
Experimental results demonstrate that TSO outperforms existing mainstream methods on various alignment evaluation benchmarks.
arXiv Detail & Related papers (2024-08-31T05:37:01Z) - Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC.<n>We increase the consistency and informativeness of the pairwise preference signals through targeted modifications.<n>We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
arXiv Detail & Related papers (2024-08-14T11:29:47Z) - Multi-Reference Preference Optimization for Large Language Models [56.84730239046117]
We introduce a novel closed-form formulation for direct preference optimization using multiple reference models.
The resulting algorithm, Multi-Reference Preference Optimization (MRPO), leverages broader prior knowledge from diverse reference models.
Our experiments demonstrate that LLMs finetuned with MRPO generalize better in various preference data, regardless of data scarcity or abundance.
arXiv Detail & Related papers (2024-05-26T00:29:04Z) - Prior Constraints-based Reward Model Training for Aligning Large Language Models [58.33118716810208]
This paper proposes a Prior Constraints-based Reward Model (namely PCRM) training method to mitigate this problem.
PCRM incorporates prior constraints, specifically, length ratio and cosine similarity between outputs of each comparison pair, during reward model training to regulate optimization magnitude and control score margins.
Experimental results demonstrate that PCRM significantly improves alignment performance by effectively constraining reward score scaling.
arXiv Detail & Related papers (2024-04-01T07:49:11Z) - Evaluating and Explaining Large Language Models for Code Using Syntactic
Structures [74.93762031957883]
This paper introduces ASTxplainer, an explainability method specific to Large Language Models for code.
At its core, ASTxplainer provides an automated method for aligning token predictions with AST nodes.
We perform an empirical evaluation on 12 popular LLMs for code using a curated dataset of the most popular GitHub projects.
arXiv Detail & Related papers (2023-08-07T18:50:57Z) - Bring Your Own Data! Self-Supervised Evaluation for Large Language
Models [52.15056231665816]
We propose a framework for self-supervised evaluation of Large Language Models (LLMs)
We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence.
We find strong correlations between self-supervised and human-supervised evaluations.
arXiv Detail & Related papers (2023-06-23T17:59:09Z) - Think Twice: Measuring the Efficiency of Eliminating Prediction
Shortcuts of Question Answering Models [3.9052860539161918]
We propose a simple method for measuring a scale of models' reliance on any identified spurious feature.
We assess the robustness towards a large set of known and newly found prediction biases for various pre-trained models and debiasing methods in Question Answering (QA)
We find that while existing debiasing methods can mitigate reliance on a chosen spurious feature, the OOD performance gains of these methods can not be explained by mitigated reliance on biased features.
arXiv Detail & Related papers (2023-05-11T14:35:00Z) - Evaluating Representations with Readout Model Switching [19.907607374144167]
In this paper, we propose to use the Minimum Description Length (MDL) principle to devise an evaluation metric.
We design a hybrid discrete and continuous-valued model space for the readout models and employ a switching strategy to combine their predictions.
The proposed metric can be efficiently computed with an online method and we present results for pre-trained vision encoders of various architectures.
arXiv Detail & Related papers (2023-02-19T14:08:01Z) - Improving Data Quality with Training Dynamics of Gradient Boosting
Decision Trees [1.5605040219256345]
We propose a method based on metrics from training dynamics of Gradient Boosting Decision Trees (GBDTs) to assess the behavior of each training example.
We show results on detecting noisy labels in order clean datasets, improving models' metrics in synthetic and real public datasets, as well as on a industry case in which we deployed a model based on the proposed solution.
arXiv Detail & Related papers (2022-10-20T15:02:49Z) - Interpretable and Low-Resource Entity Matching via Decoupling Feature
Learning from Decision Making [22.755892575582788]
Entity Matching aims at recognizing entity records that denote the same real-world object.
We propose a novel EM framework that consists of Heterogeneous Information Fusion (HIF) and Key Attribute Tree (KAT) Induction.
Our method is highly efficient and outperforms SOTA EM models in most cases.
arXiv Detail & Related papers (2021-06-08T08:27:31Z) - Explaining and Improving Model Behavior with k Nearest Neighbor
Representations [107.24850861390196]
We propose using k nearest neighbor representations to identify training examples responsible for a model's predictions.
We show that kNN representations are effective at uncovering learned spurious associations.
Our results indicate that the kNN approach makes the finetuned model more robust to adversarial inputs.
arXiv Detail & Related papers (2020-10-18T16:55:25Z) - Interpretable Entity Representations through Large-Scale Typing [61.4277527871572]
We present an approach to creating entity representations that are human readable and achieve high performance out of the box.
Our representations are vectors whose values correspond to posterior probabilities over fine-grained entity types.
We show that it is possible to reduce the size of our type set in a learning-based way for particular domains.
arXiv Detail & Related papers (2020-04-30T23:58:03Z) - Evaluating Models' Local Decision Boundaries via Contrast Sets [119.38387782979474]
We propose a new annotation paradigm for NLP that helps to close systematic gaps in the test data.
We demonstrate the efficacy of contrast sets by creating them for 10 diverse NLP datasets.
Although our contrast sets are not explicitly adversarial, model performance is significantly lower on them than on the original test sets.
arXiv Detail & Related papers (2020-04-06T14:47:18Z)
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.