Related papers: Dialectical Behavior Therapy Approach to LLM Prompting

Related papers

Small Foundation Models of Human Cognition and Behaviour [45.88028371034407]
We train 14 models from 135M to 14B parameters across four architecture families on Psych-101.<n>Psych-101 is a dataset of 10.7 million trial-level choices from 160 experiments.<n>We show that small cognitively fine-tuned models show promise as noise ceiling estimators for psychological experiments.
arXiv Detail & Related papers (2026-08-05T11:34:20Z)
Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis [68.28714988482703]
Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs)<n>We present a study revealing that general-domain PRMs struggle to supervise data analysis agents.<n>We introduce DataPRM, a novel environment-aware generative process reward model.
arXiv Detail & Related papers (2026-04-27T09:00:30Z)
When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs [55.20230501807337]
We present the first systematic evaluation of 5 methods for improving prompt robustness within a unified experimental framework.<n>We benchmark these techniques on 8 models from Llama, Qwen and Gemma families across 52 tasks from Natural Instructions dataset.
arXiv Detail & Related papers (2025-08-15T10:32:50Z)
ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism [10.913346263482786]
We introduce an entropy-based mechanism to enhance the exploration-exploitation balance in test-time reinforcement learning.<n>Compared with the baseline, our approach enables Llama3.1-8B to achieve a 68 percent relative improvement in Pass at 1 metric.
arXiv Detail & Related papers (2025-08-15T09:49:14Z)
Dissecting Clinical Reasoning in Language Models: A Comparative Study of Prompts and Model Adaptation Strategies [4.299840769087444]
This study presents the first controlled evaluation of how prompt structure and efficient fine-tuning jointly shape model performance in clinical NLI.<n>We construct high-quality demonstrations using a frontier model to distil multi-step reasoning capabilities into smaller models via Low-Rank Adaptation (LoRA)<n>Across different language models fine-tuned on the NLI4CT benchmark, we found that prompt type alone accounts for up to 44% of the variance in macro-F1.<n>LoRA fine-tuning yields consistent gains of +8 to 12 F1, raises output alignment above 97%, and narrows the performance gap to GPT-4
arXiv Detail & Related papers (2025-07-05T19:43:54Z)
CLGRPO: Reasoning Ability Enhancement for Small VLMs [4.551310348498266]
Small Vision Language Models (SVLMs) generally refer to models with parameter sizes less than or equal to 2B.<n>This paper proposes a post-training optimization paradigm called the Incremental Training Strategy to enhance the reasoning ability of SVLMs.<n> Experimental results demonstrate that our method significantly improves the reasoning ability of 1B SVLM.
arXiv Detail & Related papers (2025-06-22T14:32:15Z)
Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning [19.426979775180797]
Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference.<n>We observe that reasoning-optimized models often produce less diverse outputs, which limits TTS effectiveness.<n>We propose ADAPT, a lightweight method that applies prefix tuning with a diversity-focused data strategy.
arXiv Detail & Related papers (2025-06-05T04:02:17Z)
A Method for the Architecture of a Medical Vertical Large Language Model Based on Deepseek R1 [6.589206192038366]
This paper presents an efficient lightweight medical large language model architecture that addresses knowledge acquisition, model compression, and computational enhancement challenges.<n>We design a knowledge transfer pipeline from DeepSeek-R1-Distill-70B to DeepSeek-R1-Distill-7B using Low-Rank Adaptation (LoRA) for precise medical knowledge retention.<n>Our approach maintains 92.1% accuracy on USMLE while reducing memory consumption by 64.7% and latency by 12.4% compared to baseline inference models.
arXiv Detail & Related papers (2025-04-25T14:28:29Z)
Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning [55.6623318085391]
Recent large language model (LLM) reasoning suffers from limited domain knowledge, susceptibility to hallucinations, and constrained reasoning depth. This paper presents the first investigation into integrating step-wise knowledge graph retrieval with step-wise reasoning. We propose KG-RAR, a framework centered on process-oriented knowledge graph construction, a hierarchical retrieval strategy, and a universal post-retrieval processing and reward model.
arXiv Detail & Related papers (2025-03-03T15:20:41Z)
Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective [90.86370957353911]
Chain-of-Reasoning (CoR) is a novel unified framework that integrates multiple reasoning paradigms. CoR generates multiple potential answers using different reasoning paradigms and synthesizes them into a coherent final solution. Experimental results demonstrate that CoR-Math-7B significantly outperforms current SOTA models.
arXiv Detail & Related papers (2025-01-19T16:53:26Z)
EPE-P: Evidence-based Parameter-efficient Prompting for Multimodal Learning with Missing Modalities [20.991711160707755]
Missing modalities are a common challenge in real-world multimodal learning scenarios, occurring during both training and testing. Existing methods for managing missing modalities often require the design of separate prompts for each modality or missing case. We propose Evidence-based. Efficient Prompting (EPE-P), a novel and parameter-efficient method for pretrained multimodal networks.
arXiv Detail & Related papers (2024-12-23T16:01:12Z)
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale [66.73529246309033]
multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. Existing instruction-tuning datasets only provide phrase-level answers without any intermediate rationales. We introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales.
arXiv Detail & Related papers (2024-12-06T18:14:24Z)
Patience Is The Key to Large Language Model Reasoning [0.0]
We propose a simple method by encouraging models to adopt a more patient reasoning style. We generate detailed reasoning processes as positive examples and simple answers as negative examples, thereby training the model to favor thoroughness in its responses. Our results demonstrate a performance increase of up to 6.7% on GSM8k with training just on a lightweight dataset.
arXiv Detail & Related papers (2024-11-20T07:20:48Z)
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning [64.36534512742736]
We investigate the effectiveness of test-time training (TTT) as a mechanism for improving models' reasoning capabilities. TTT significantly improves performance on ARC tasks, achieving up to 6x improvement in accuracy compared to base fine-tuned models. Our findings suggest that explicit symbolic search is not the only path to improved abstract reasoning in neural language models.
arXiv Detail & Related papers (2024-11-11T18:59:45Z)
Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability [67.77534983324229]
In this paper, we investigate the ability of Large Language Models to develop a unified compression method that discretizes uninformative tokens. Experiments show Selection-p achieves state-of-the-art performance across numerous classification tasks. It exhibits superior transferability to different models compared to prior work.
arXiv Detail & Related papers (2024-10-15T17:05:25Z)
Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration [74.09687562334682]
We introduce a novel training data attribution method called Debias and Denoise Attribution (DDA) Our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%. DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral.
arXiv Detail & Related papers (2024-10-02T07:14:26Z)
Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation [16.350747493026432]
The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs) We propose the textbfStrategic Chain-of-Thought (SCoT) to refine LLM performance by integrating strategic knowledge prior to generating intermediate reasoning steps. SCoT employs a two-stage approach within a single prompt: first eliciting an effective problem-solving strategy, which is then used to guide the generation of high-quality CoT paths and final answers.
arXiv Detail & Related papers (2024-09-05T06:28:05Z)
Analyzing Persuasive Strategies in Meme Texts: A Fusion of Language Models with Paraphrase Enrichment [0.23020018305241333]
This paper describes our approach to hierarchical multi-label detection of persuasion techniques in meme texts. The scope of the study encompasses enhancing model performance through innovative training techniques and data augmentation strategies.
arXiv Detail & Related papers (2024-07-01T20:25:20Z)
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs [54.05511925104712]
We propose a simple, effective, and data-efficient method called Step-DPO. Step-DPO treats individual reasoning steps as units for preference optimization rather than evaluating answers holistically. Our findings demonstrate that as few as 10K preference data pairs and fewer than 500 Step-DPO training steps can yield a nearly 3% gain in accuracy on MATH for models with over 70B parameters.
arXiv Detail & Related papers (2024-06-26T17:43:06Z)
Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models [122.19845578690466]
Step-Back Prompting enables LLMs to do abstractions to derive high-level concepts and first principles from instances containing specific details. Using the concepts and principles to guide reasoning, LLMs significantly improve their abilities in following a correct reasoning path towards the solution.
arXiv Detail & Related papers (2023-10-09T19:48:55Z)
Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning [10.51168925267033]
This paper presents a systematic overview of parameter-efficient fine-tuning methods, covering over 50 papers published between early 2019 and mid-2024. We provide a taxonomy that covers a broad range of methods and present a detailed method comparison. We also conduct an extensive head-to-head experimental comparison of 15 diverse PEFT methods, evaluating their performance and efficiency on models up to 11B parameters.
arXiv Detail & Related papers (2023-03-28T00:06:38Z)
Reframing Instructional Prompts to GPTk's Language [72.69833640335519]
We propose reframing techniques for model designers to create effective prompts for language models. Our results show that reframing improves few-shot learning performance by 14% while reducing sample complexity. The performance gains are particularly important on large language models, such as GPT3 where tuning models or prompts on large datasets is not feasible.
arXiv Detail & Related papers (2021-09-16T09:44:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.