Memristor-based analog compute-in-memory architectures promise efficient deployment of Large Language Models, yet their intrinsic non-idealities degrade reasoning performance across benchmarks. The study evaluates how these non-idealities affect LLM reasoning and tests three training-free mitigation strategies: thinking mode, in-context learning, and module redundancy. Findings show shallow layer redundancy boosts robustness, thinking mode helps only at low noise, and in-context learning shortens output with a modest performance cost.
arXiv:2608. 20202v1 Announce Type: new Abstract: Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions.
Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions. However, existing memory benchmarks mainly evaluate whether information is correctly extracted, stored, and retrieved, while largely overlooking how retrieved memories reshape model reasoning and affect performance on the current task.
The paper introduces Ladder Side Tuning (LST), a parameter‑efficient fine‑tuning method that adds a lightweight side network to large language models. LST matches QLoRA’s compute scaling while halving peak memory usage, enabling 7B‑parameter models to be fine‑tuned on a single 12 GB GPU with 2k‑token contexts without gradient checkpointing. The authors also present xLadder, a depth‑extended variant that increases effective depth through cross‑connections, allowing deeper reasoning without extra memory overhead.
arXiv:2606. 06574v1 Announce Type: new Abstract: Large language models (LLMs) perform inference by following a fixed depth and order, non-recurrent execution of all layers.
arXiv:2506. 21833v2 Announce Type: replace Abstract: Forward-mode automatic differentiation (FmAD) and zero-order (ZO) optimization are increasingly proposed as memory-efficient, backpropagation-free alternatives for large language model (LLM) fine-tuning, yet their benefits are typically evaluated only against standard backpropagation (BP), omitting memory-efficient variants such as activation checkpointing.
RetroThinker is a multi-stage post‑training framework that enhances SpeechLLMs by enabling them to self‑verify and forward‑correct Chain‑of‑Thought reasoning steps during inference. It combines supervised fine‑tuning on curated retrospective thinking data with length‑based direct preference optimization to improve reasoning while the user speaks. On the GSM8K benchmark, RetroThinker achieves an 11% absolute accuracy gain over non‑retrospective baselines while maintaining comparable latency.
arXiv:2609.24417v1 Announce Type: new Abstract: Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are...
arXiv:2610.08630v1 Announce Type: new Abstract: Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, u...
arXiv:2605.06165v2 Announce Type: replace Abstract: As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contribut...
arXiv:2607.05969v3 Announce Type: replace Abstract: Latent memory, which stores past knowledge fragments as per-layer hidden states, has emerged as a promising paradigm (e.g., MemoryLLM and M+) for l...
arXiv:2606. 17803v1 Announce Type: new Abstract: Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process.
The paper introduces rEDMRec, a method that compresses a large language model’s reasoning about user preferences and item comparisons into a compact, editable memory. This memory, organized into four channels—long‑term preference, short‑term context, item perception, and counterfactual hard‑negative comparisons—can be updated by an LLM controller and queried by a lightweight student LLM for ranking, eliminating the need to re‑run the expensive teacher model for each request. Experiments on ML‑1M, Amazon Beauty, and Steam datasets show that rEDMRec consistently outperforms zero‑shot, few‑shot, RAG, and GraphRAG baselines, achieving up to a 13.3% improvement in HR@1 on ML‑1M.