Can We Trust LLMs on Memristors? Diving into Reasoning Ability under Non-Ideality

• URL: http://arxiv.org/abs/2603.13725v1
• Date: Sat, 14 Mar 2026 03:02:15 GMT
• Title: Can We Trust LLMs on Memristors? Diving into Reasoning Ability under Non-Ideality
• Abstract summary: We investigate the impact of intrinsic non-idealities on Large Language Models (LLMs) reasoning.<n>We appraise three training-free strategies, including thinking mode, in-context learning, and module redundancy.<n>Our findings offer new insights into LLM reasoning under non-ideality and practical strategies to improve robustness.
• Score: 19.903894625956394
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Memristor-based analog compute-in-memory (CIM) architectures provide a promising substrate for the efficient deployment of Large Language Models (LLMs), owing to superior energy efficiency and computational density. However, these architectures suffer from precision issues caused by intrinsic non-idealities of memristors. In this paper, we first conduct a comprehensive investigation into the impact of such typical non-idealities on LLM reasoning. Empirical results indicate that reasoning capability decreases significantly but varies for distinct benchmarks. Subsequently, we systematically appraise three training-free strategies, including thinking mode, in-context learning, and module redundancy. We thus summarize valuable guidelines, i.e., shallow layer redundancy is particularly effective for improving robustness, thinking mode performs better under low noise levels but degrades at higher noise, and in-context learning reduces output length with a slight performance trade-off. Our findings offer new insights into LLM reasoning under non-ideality and practical strategies to improve robustness.

Related papers

• How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices [81.85465545346266]
  Diffusion language models (DLMs) have emerged as a promising alternative to the long-dominant autoregressive (AR) paradigm.<n>Yet, current open-source DLMs often underperform their AR counterparts in speed, limiting their real-world utility.<n>This work presents a systematic study of DLM efficiency, identifying key issues in prior evaluation methods.
  arXiv  Detail & Related papers  (2025-10-21T10:00:32Z)
• Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts [19.518525241726916]
  Encode-Think-Decode (ETD) is a method that enhances the reasoning capabilities of a base model by training it to iterate over a small subset of reasoning-relevant layers during the mid-training stage.<n>ETD models yield substantial gains on 17 reasoning benchmarks, including +28.4% relative accuracy improvement on GSM8K and +36% on MATH with the OLMo-2 1B Base model.
  arXiv  Detail & Related papers  (2025-10-08T15:58:35Z)
• Pushing LLMs to Their Logical Reasoning Bound: The Role of Data Reasoning Intensity [59.27594125465172]
  We introduce Data Reasoning Intensity (DRI), a novel metric that quantifies the latent logical reasoning complexity of samples.<n>We then introduce a re-cognizing optimization strategy that systematically enhances the logical reasoning intensity of training data.
  arXiv  Detail & Related papers  (2025-09-29T14:20:04Z)
• Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning [56.496001894673235]
  Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs)<n>Our analysis reveals that puzzling phenomena like aha moments", length-scaling'' and entropy dynamics are not disparate occurrences but hallmarks of an emergent reasoning hierarchy.
  arXiv  Detail & Related papers  (2025-09-03T18:52:49Z)
• Are Large Brainwave Foundation Models Capable Yet? Insights from Fine-tuning [41.40603531008809]
  We evaluate current Large Brainwave Foundation Models (LBMs) through systematic fine-tuning experiments.<n>Our analysis shows that state-of-the-art LBMs achieve only marginal improvements (0.9%-1.2%) over traditional deep architectures.
  arXiv  Detail & Related papers  (2025-07-01T21:21:42Z)
• Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation [7.262231066394782]
  Quantization has emerged as a mainstream method for compressing Large Language Models (LLMs)<n>We present the first systematic investigation of how quantization affects the robustness of LLMs in code generation tasks.<n>Our findings challenge conventional wisdom by demonstrating that quantized LLMs often exhibit superior robustness compared to their full-precision counterparts.
  arXiv  Detail & Related papers  (2025-06-28T06:32:25Z)
• SlimLLM: Accurate Structured Pruning for Large Language Models [36.84275777364218]
  structured pruning is an effective solution to compress the parameters of large language models.<n>We propose an effective and fast structured pruning method named SlimLLM for large language models.
  arXiv  Detail & Related papers  (2025-05-28T03:01:28Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [86.76714527437383]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• Leveraging the true depth of LLMs [46.81174316936993]
  Large Language Models (LLMs) demonstrate remarkable capabilities at the cost of high compute requirements.<n>Recent studies have demonstrated that intermediate layers in LLMs can be removed or reordered without substantial accuracy loss.<n>We propose a novel method that groups consecutive layers into pairs evaluated in parallel.
  arXiv  Detail & Related papers  (2025-02-05T00:26:27Z)
• Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning [65.23593936798662]
  We show that fine-tuning with LLM-generated data improves target task performance and reduces non-target task degradation.<n>This is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2025-01-24T08:18:56Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)

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.