Enhancing Generalization in Chain of Thought Reasoning for Smaller Models

• URL: http://arxiv.org/abs/2501.09804v1
• Date: Thu, 16 Jan 2025 19:23:11 GMT
• Title: Enhancing Generalization in Chain of Thought Reasoning for Smaller Models
• Authors: Maxwell J. Yin, Dingyi Jiang, Yongbing Chen, Boyu Wang, Charles Ling,
• Abstract summary: Chain-of-Thought (CoT) reasoning in smaller language models is a challenging natural language process problem.<n>Existing CoT knowledge distillation methods often suffer from overly conservative adaptability in smaller LLMs.<n>We propose PRADA, a principled fine-tuning framework that integrates diverse CoT domains.
• Score: 5.297025364137428
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chain-of-Thought (CoT) reasoning in smaller language models is a challenging natural language process problem yet highly desirable in many real-life applications. Existing CoT knowledge distillation methods often suffer from overly conservative memorization in smaller LLMs, leading to low generalization confidence. As fully preserving the CoT ability of teacher model is impossible, we hypothesize that adversarial CoT fine-tuning is crucial for developing smaller LLM with robust CoT generalization. To this end, we propose \textit{PRompt-Assisted Domain-Adversarial fine-tuning} (PRADA), a principled fine-tuning framework that integrates diverse CoT domains. Specifically, PRADA pioneers two CoT improvements in smaller LLM: (1) Recovering the domain-invariant feature insight which typically lost during distillation with domain adversarial fine-tuning; (2) Enhancing the domain adaptability of CoT prompt engineering by employing domain-adversarial approaches. We theoretically demonstrate the effectiveness of our approach and empirically show that it significantly outperforms the state of the arts in a wide range of tasks. Moreover, our empirical findings reveal that the smaller LLM, when leveraging PRADA, aligns closely with domain knowledge, thereby improving the explainability of our approach.

Related papers

• No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs [65.783709850324]
  This work stems from prior complementary observations on the dynamics of Chain-of-Thought (CoT): Large Language Models (LLMs)<n>LLMs are shown latent planning of subsequent reasoning prior to CoT emergence, thereby diminishing the significance of explicit CoT.<n>We investigate the latent planning strength of LLMs, through our probing method, Tele-Lens, applying to hidden states across diverse task domains.
  arXiv  Detail & Related papers  (2026-02-02T13:46:56Z)
• Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning [9.97195966127976]
  Large language models (LLMs) demonstrate impressive generalization abilities, yet adapting them effectively across multiple heterogeneous domains remains challenging.<n>We propose a partition-based multi-stage fine-tuning framework designed to exploit inter-domain synergies while minimizing negative transfer.<n>Our approach strategically partitions domains into subsets (stages) by balancing domain discrepancy, synergy, and model capacity constraints.
  arXiv  Detail & Related papers  (2025-11-10T15:27:26Z)
• SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs [53.77646961962239]
  Supervised Fine-Tuning (SFT) is a common approach to adapt Large Language Models (LLMs) to specialized tasks.<n>We show that SFT does not always hurt: using a smaller learning rate can substantially mitigate general performance degradation.
  arXiv  Detail & Related papers  (2025-09-25T05:28:22Z)
• ReFineG: Synergizing Small Supervised Models and LLMs for Low-Resource Grounded Multimodal NER [16.046325222014385]
  Grounded Multimodal Named Entity Recognition (GMNER) extends traditional NER by jointly detecting textual mentions and grounding them to visual regions.<n>We propose ReFineG, a three-stage collaborative framework that integrates small supervised models with frozen MLLMs for low-resource GMNER.<n>In the CCKS2025 GMNER Shared Task, ReFineG ranked second with an F1 score of 0.6461 on the online leaderboard, demonstrating its effectiveness with limited annotations.
  arXiv  Detail & Related papers  (2025-09-13T20:32:12Z)
• CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning [25.142128256576985]
  We propose a Contrastive learning with annotated CoT-based Reinforced Fine-Tuning approach, i.e., TheName, to enhance the reasoning performance of Large Language Models.<n>Our approach not only fully exploits the available annotated CoT but also stabilizes the fine-tuning procedure by incorporating an additional unsupervised learning signal.
  arXiv  Detail & Related papers  (2025-08-21T00:20:47Z)
• ReaLM: Reflection-Enhanced Autonomous Reasoning with Small Language Models [76.28894983518164]
  Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs)<n>They often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers.<n>We introduce ReaLM, a reinforcement learning framework for robust and self-sufficient reasoning in vertical domains.
  arXiv  Detail & Related papers  (2025-08-17T14:50:23Z)
• Compressing Chain-of-Thought in LLMs via Step Entropy [12.576398947428988]
  Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting excel at complex reasoning but generate thought processes with considerable redundancy, leading to increased inference costs and reduced efficiency.<n>We introduce a novel CoT compression framework based on step entropy, a metric that quantifies the informational contribution of individual reasoning steps to identify redundancy.
  arXiv  Detail & Related papers  (2025-08-05T11:48:18Z)
• CTRLS: Chain-of-Thought Reasoning via Latent State-Transition [57.51370433303236]
  Chain-of-thought (CoT) reasoning enables large language models to break down complex problems into interpretable intermediate steps.<n>We introduce groundingS, a framework that formulates CoT reasoning as a Markov decision process (MDP) with latent state transitions.<n>We show improvements in reasoning accuracy, diversity, and exploration efficiency across benchmark reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-10T21:32:18Z)
• Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering [59.34894142132706]
  Existing work finds that the capability of long CoT reasoning can be efficiently elicited by tuning on only a few examples. This motivates us to investigate whether long CoT reasoning is a general capability for LLMs. We propose GLoRE, a novel representation engineering method to unleash the general long CoT reasoning capabilities of LLMs.
  arXiv  Detail & Related papers  (2025-03-14T11:30:37Z)
• A Survey on Post-training of Large Language Models [185.51013463503946]
  Large Language Models (LLMs) have fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration. These challenges necessitate advanced post-training language models (PoLMs) to address shortcomings, such as restricted reasoning capacities, ethical uncertainties, and suboptimal domain-specific performance. This paper presents the first comprehensive survey of PoLMs, systematically tracing their evolution across five core paradigms.
  arXiv  Detail & Related papers  (2025-03-08T05:41:42Z)
• When More is Less: Understanding Chain-of-Thought Length in LLMs [53.77747102201451]
  Chain-of-thought (CoT) reasoning enhances the multi-step reasoning capabilities of large language models (LLMs) However, for most models and tasks, does an increase in CoT length consistently lead to improved reasoning accuracy? In this paper, we observe a nuanced relationship: as the number of reasoning steps increases, performance initially improves but eventually decreases.
  arXiv  Detail & Related papers  (2025-02-11T05:28:59Z)
• Efficient Reasoning with Hidden Thinking [48.96945580741641]
  Chain-of-Thought (CoT) reasoning has become a powerful framework for improving complex problem-solving capabilities. We propose $textbfHeima$ (as hidden llama), an efficient reasoning framework that leverages reasoning CoTs at hidden latent space. Heima model achieves higher generation efficiency while maintaining or even better zero-shot task accuracy.
  arXiv  Detail & Related papers  (2025-01-31T15:10:29Z)
• Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs [64.83462841029089]
  We introduce an efficient merging-based alignment method called textscMergeAlign that interpolates the domain and alignment vectors, creating safer domain-specific models. We apply textscMergeAlign on Llama3 variants that are experts in medicine and finance, obtaining substantial alignment improvements with minimal to no degradation on domain-specific benchmarks.
  arXiv  Detail & Related papers  (2024-11-11T09:32:20Z)
• Exploring Language Model Generalization in Low-Resource Extractive QA [57.14068405860034]
  We investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift.<n>We devise a series of experiments to explain the performance gap empirically.
  arXiv  Detail & Related papers  (2024-09-27T05:06:43Z)
• Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs [63.36637269634553]
  We introduce a novel approach where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.<n>We show that fine-tuning on DCoT improves performance over the CoT baseline across model families and scales.<n>Our work is also significant because both quantitative analyses and manual evaluations reveal the observed gains stem from the models' ability to refine an initial reasoning chain.
  arXiv  Detail & Related papers  (2024-07-03T15:01:18Z)
• On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models [25.029579061612456]
  Large Language Models (LLMs) are increasingly being employed in real-world applications in critical domains such as healthcare. It is important to ensure that the Chain-of-Thought (CoT) reasoning generated by these models faithfully captures their underlying behavior.
  arXiv  Detail & Related papers  (2024-06-15T13:16:44Z)
• On the Convergence of Zeroth-Order Federated Tuning for Large Language Models [36.277423093218275]
  Federated Learning and Large Language Models (LLMs) are ushering in a new era in privacy-preserving natural language processing. Memory-efficient Zeroth-Order Optimization is a synergy we term as FedMeZO. Our study is the first to examine the theoretical underpinnings of FedMeZO in the context of LLMs.
  arXiv  Detail & Related papers  (2024-02-08T18:56:40Z)
• Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection [73.31406286956535]
  We introduce the Ladder-of-Thought (LoT) for the stance detection task. LoT directs the small LMs to assimilate high-quality external knowledge, refining the intermediate rationales produced. Our empirical evaluations underscore LoT's efficacy, marking a 16% improvement over GPT-3.5 and a 10% enhancement compared to GPT-3.5 with CoT on stance detection task.
  arXiv  Detail & Related papers  (2023-08-31T14:31:48Z)
• Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization [101.08992036691673]
  This paper explores a realistic unsupervised fine-tuning scenario, considering the presence of out-of-distribution samples from unknown classes. In particular, we focus on simultaneously enhancing out-of-distribution detection and the recognition of instances associated with known classes. We present a simple, efficient, and effective approach called Universal Entropy Optimization (UEO)
  arXiv  Detail & Related papers  (2023-08-24T16:47:17Z)
• Constrained Maximum Cross-Domain Likelihood for Domain Generalization [14.91361835243516]
  Domain generalization aims to learn a generalizable model on multiple source domains, which is expected to perform well on unseen test domains. In this paper, we propose a novel domain generalization method, which minimizes the KL-divergence between posterior distributions from different domains. Experiments on four standard benchmark datasets, i.e., Digits-DG, PACS, Office-Home and miniDomainNet, highlight the superior performance of our method.
  arXiv  Detail & Related papers  (2022-10-09T03:41:02Z)
• Domain-Specific Risk Minimization for Out-of-Distribution Generalization [104.17683265084757]
  We first establish a generalization bound that explicitly considers the adaptivity gap. We propose effective gap estimation methods for guiding the selection of a better hypothesis for the target. The other method is minimizing the gap directly by adapting model parameters using online target samples.
  arXiv  Detail & Related papers  (2022-08-18T06:42:49Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)
• Learning to Learn Single Domain Generalization [18.72451358284104]
  We propose a new method named adversarial domain augmentation to solve this Out-of-Distribution (OOD) generalization problem. The key idea is to leverage adversarial training to create "fictitious" yet "challenging" populations. To facilitate fast and desirable domain augmentation, we cast the model training in a meta-learning scheme and use a Wasserstein Auto-Encoder (WAE) to relax the widely used worst-case constraint.
  arXiv  Detail & Related papers  (2020-03-30T04:39:53Z)

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.