Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking

• URL: http://arxiv.org/abs/2510.14824v1
• Date: Thu, 16 Oct 2025 16:02:27 GMT
• Title: Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking
• Authors: Ziqi Dai, Xin Zhang, Mingxin Li, Yanzhao Zhang, Dingkun Long, Pengjun Xie, Meishan Zhang, Wenjie Li, Min Zhang,
• Abstract summary: For large language models (LLMs), classification via supervised fine-tuning (SFT) predicts ''yes'' (resp. ''no'') token for relevant (resp. irrelevant) pairs.<n>This divergence raises a central question: which objective is intrinsically better suited to LLM-based reranking, and what mechanism underlies the difference?<n>We conduct a comprehensive comparison and analysis between CL and SFT for reranking, taking the universal multimodal retrieval (UMR) as the experimental playground.
• Score: 56.46309219272326
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In information retrieval, training reranking models mainly focuses on two types of objectives: metric learning (e.g. contrastive loss to increase the predicted scores on relevant query-document pairs) and classification (binary label prediction of relevance vs. irrelevance). For BERT-style encoders, various studies have shown that contrastive learning (CL) can be more effective than discriminative (classification) learning. However, for large language models (LLMs), classification via supervised fine-tuning (SFT), which predicts ''yes'' (resp. ''no'') token for relevant (resp. irrelevant) pairs, appears more promising as it aligns well with the generative nature of LLMs. This divergence raises a central question: which objective is intrinsically better suited to LLM-based reranking, and what mechanism underlies the difference? In this work, we conduct a comprehensive comparison and analysis between CL and SFT for reranking, taking the universal multimodal retrieval (UMR) as the experimental playground. We first decompose the objectives into two components: weight, which controls the magnitude of those updates, and direction, which guides the model updates, then present a unified framework for understanding their interactions. Through probing experiments, we find that SFT provides a substantially stronger weighting scheme than CL, whereas the preferred scoring direction shows no clear winner. Taken together, these results point to a consistent advantage of SFT over CL for LLM reranking. To further validate our findings, we conduct large-scale training with SFT and present new state-of-the-art rerankers on the MRB benchmark. We also provide ablations on SFT settings and expect our findings to benefit future research and applications in this area.

Related papers

• Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning [30.751908700207185]
  SFT plays a crucial role across several scenarios.<n>SFT with only 2K achieves comparable or better reasoning performance to RL with 20K.<n>We identify a pervasive issue of deceptive rewards, where higher rewards fail to correlate with better reasoning accuracy in RL.
  arXiv  Detail & Related papers  (2025-12-14T13:46:42Z)
• Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm [16.78399933831573]
  We propose the Large Reasoning Embedding Model (LREM), which integrates reasoning processes into representation learning.<n>For difficult queries, LREM first conducts reasoning to achieve a deep understanding of the original query, and then produces a reasoning-augmented query embedding for retrieval.<n>This reasoning process effectively bridges the semantic gap between original queries and target items, significantly improving retrieval accuracy.
  arXiv  Detail & Related papers  (2025-10-16T05:37:39Z)
• Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them [25.324955028065887]
  Two popular approaches are reinforcement learning (RL) and supervised fine-tuning (SFT)<n>We find that RL yields minor in-domain gains on maths and slight degradation on knowledge-intensive benchmarks like MMLU.<n>SFT exhibits greater updates and also affects mid-layers query more, leading us to hypothesise that this may have caused the out-of-domain degradation.
  arXiv  Detail & Related papers  (2025-07-13T19:04:17Z)
• Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers [59.168391398830515]
  We evaluate 12 pre-trained LLMs and one specialized fact-verifier, using a collection of examples from 14 fact-checking benchmarks.<n>We highlight the importance of addressing annotation errors and ambiguity in datasets.<n> frontier LLMs with few-shot in-context examples, often overlooked in previous works, achieve top-tier performance.
  arXiv  Detail & Related papers  (2025-06-16T10:32:10Z)
• Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections [65.36449542323277]
  We present a unified theoretical framework bridgingSupervised Fine-Tuning (SFT) and preference learning in Large Language Model (LLM) post-training.<n>We propose a simple yet effective learning rate reduction approach that yields significant performance improvements.
  arXiv  Detail & Related papers  (2025-06-15T05:42:29Z)
• KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance [83.99974309930072]
  Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs)
  arXiv  Detail & Related papers  (2025-05-21T12:55:28Z)
• TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge [59.57934574562651]
  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.
  arXiv  Detail & Related papers  (2025-03-06T12:33:20Z)
• Towards Automated Fact-Checking of Real-World Claims: Exploring Task Formulation and Assessment with LLMs [32.45604456988931]
  This study establishes baseline comparisons for Automated Fact-Checking (AFC) using Large Language Models (LLMs)<n>We evaluate Llama-3 models of varying sizes on 17,856 claims collected from PolitiFact (2007-2024) using evidence retrieved via restricted web searches.<n>Our results show that larger LLMs consistently outperform smaller LLMs in classification accuracy and justification quality without fine-tuning.
  arXiv  Detail & Related papers  (2025-02-13T02:51:17Z)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks.<n>Existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks.<n>We propose Scalable Decoupled LoRA (SD-LoRA) for class incremental learning, which continually separates the learning of the magnitude and direction of LoRA components without rehearsal.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs [50.29035873837]
  Large language models (LLMs) can learn vast amounts of knowledge from diverse domains during pre-training.<n>Long-tail knowledge from specialized domains is often scarce and underrepresented, rarely appearing in the models' memorization.<n>We propose a reinforcement learning-based dynamic uncertainty ranking method for ICL that accounts for the varying impact of each retrieved sample on LLM predictions.
  arXiv  Detail & Related papers  (2024-10-31T03:42:17Z)

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.