TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge

• URL: http://arxiv.org/abs/2503.04381v1
• Date: Thu, 06 Mar 2025 12:33:20 GMT
• Title: TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge
• Authors: Cheng-Han Chiang, Hung-yi Lee, Michal Lukasik,
• Abstract summary: TRACT (Two-stage Regression-Aware fine-tuning with CoT) is a method combining CoT reasoning with regression-aware training.<n>Experiments across four LLM-as-a-judge datasets and two LLMs show that TRACT significantly outperforms existing methods.
• Score: 59.57934574562651
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The LLM-as-a-judge paradigm uses large language models (LLMs) for automated text evaluation, where a numerical assessment is assigned by an LLM to the input text following scoring rubrics. Existing methods for LLM-as-a-judge use cross-entropy (CE) loss for fine-tuning, which neglects the numeric nature of score prediction. Recent work addresses numerical prediction limitations of LLM fine-tuning through regression-aware fine-tuning, which, however, does not consider chain-of-thought (CoT) reasoning for score prediction. In this paper, we introduce TRACT (Two-stage Regression-Aware fine-tuning with CoT), a method combining CoT reasoning with regression-aware training. TRACT consists of two stages: first, seed LLM is fine-tuned to generate CoTs, which serve as supervision for the second stage fine-tuning. The training objective of TRACT combines the CE loss for learning the CoT reasoning capabilities, and the regression-aware loss for the score prediction. Experiments across four LLM-as-a-judge datasets and two LLMs show that TRACT significantly outperforms existing methods. Extensive ablation studies validate the importance of each component in TRACT.

Related papers

• Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training [57.03005244917803]
  Large language models (LLMs) often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training.<n>Here, we aim to mitigate such spurious correlations through causality-aware post-training (CAPT)<n> Experiments on the formal causal inference benchmark CLadder and the logical reasoning dataset PrOntoQA show that 3B-scale language models fine-tuned with CAPT can outperform both traditional SFT and larger LLMs on in-distribution (ID) and OOD tasks.
  arXiv  Detail & Related papers  (2025-06-11T06:30:28Z)
• Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning [47.058298511243386]
  We propose Behavior Constrained Policy Gradient with Negative Sample Augmentation (BCPG-NSA)<n>BCPG-NSA is a fine-grained offline framework that encompasses three stages: 1) sample segmentation, 2) consensus-based step correctness assessment combining LLM and PRM judgers, and 3) policy optimization with NSA designed to effectively mine positive steps within negative samples.<n> Experimental results show that BCPG-NSA outperforms baselines on several challenging math/coding reasoning benchmarks using the same training dataset.
  arXiv  Detail & Related papers  (2025-05-20T14:16:49Z)
• ULFine: Unbiased Lightweight Fine-tuning for Foundation-Model-Assisted Long-Tailed Semi-Supervised Learning [27.467732819969935]
  This paper attempts to explore the impact of large-scale visual foundation models on Long-Tailed Semi-Supervised Learning (LTSSL)<n>We employ three strategies: Linear Probing (LP), Lightweight Fine-Tuning (LFT), and Full Fine-Tuning (FFT)<n>Our analysis presents the following insights: i) Compared to LTSSL algorithms trained from scratch, FFT results in a decline in model performance, whereas LP and LFT, although boosting overall model performance, exhibit negligible benefits to tail classes.<n>We propose a Unbiased Lightweight Fine-tuning strategy, textbfULFine
  arXiv  Detail & Related papers  (2025-05-08T08:54:57Z)
• Decoding Recommendation Behaviors of In-Context Learning LLMs Through Gradient Descent [15.425423867768163]
  We propose a theoretical model, the LLM-ICL Recommendation Equivalent Gradient Descent model (LRGD) in this paper. We demonstrate that the ICL inference process in LLM aligns with the training procedure of its dual model, producing token predictions equivalent to the dual model's testing outputs. To further improve demonstration effectiveness, prevent performance collapse, and ensure long-term adaptability, we also propose a two-stage optimization process in practice.
  arXiv  Detail & Related papers  (2025-04-06T06:36:45Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models [95.32315448601241]
  We propose an algorithm named Rotated Straight-Through-Estimator (RoSTE)<n>RoSTE combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy to reduce activation outliers.<n>Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration.
  arXiv  Detail & Related papers  (2025-02-13T06:44:33Z)
• Scaling Laws for Predicting Downstream Performance in LLMs [75.28559015477137]
  This work focuses on the pre-training loss as a more-efficient metric for performance estimation. We extend the power law analytical function to predict domain-specific pre-training loss based on FLOPs across data sources. We employ a two-layer neural network to model the non-linear relationship between multiple domain-specific loss and downstream performance.
  arXiv  Detail & Related papers  (2024-10-11T04:57:48Z)
• Can Many-Shot In-Context Learning Help LLMs as Evaluators? A Preliminary Empirical Study [19.461541208547136]
  This paper studies the impact of increasing the number of in-context examples on the consistency and quality of the evaluation results.<n> Experimental results show that advanced LLMs, such as GPT-4o, perform better in the many-shot regime than in the zero-shot and few-shot regimes.
  arXiv  Detail & Related papers  (2024-06-17T15:11:58Z)
• CALRec: Contrastive Alignment of Generative LLMs for Sequential Recommendation [18.986613405565514]
  Large Language Models (LLMs) are pretrained on vast corpora of text for sequential recommendation. We propose a two-stage LLM finetuning framework that finetunes a pretrained LLM in a two-tower fashion using a mixture of two contrastive losses and a language modeling loss. Our model significantly outperforms many state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-05-03T18:51:19Z)
• TeLeS: Temporal Lexeme Similarity Score to Estimate Confidence in End-to-End ASR [1.8477401359673709]
  Class-probability-based confidence scores do not accurately represent quality of overconfident ASR predictions. We propose a novel Temporal-Lexeme Similarity (TeLeS) confidence score to train Confidence Estimation Model (CEM) We conduct experiments with ASR models trained in three languages, namely Hindi, Tamil, and Kannada, with varying training data sizes.
  arXiv  Detail & Related papers  (2024-01-06T16:29:13Z)
• TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
  Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
  arXiv  Detail & Related papers  (2023-10-10T16:38:49Z)
• On Language Model Integration for RNN Transducer based Speech Recognition [49.84285563767935]
  We study various ILM correction-based LM integration methods formulated in a common RNN-T framework. We provide a decoding interpretation on two major reasons for performance improvement with ILM correction. We also propose an exact-ILM training framework by extending the proof given in the hybrid autoregressive transducer.
  arXiv  Detail & Related papers  (2021-10-13T16:30:46Z)

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.