Small Language Models

Also known as SLM

Overview

Researchers build small language models by training compact models from scratch, distilling larger teachers, or adapting open models with supervised fine-tuning, LoRA/QLoRA, preference optimization, and quantization. To extend their capabilities, systems combine them with retrieval, tools, structured reasoning, verification, or selective handoff to larger models, particularly for edge, private, and latency-sensitive use. Evaluations span reasoning and coding benchmarks such as GSM8K and SWE-bench, structured tasks such as Spider and BIRD text-to-SQL, and domains including medicine, law, and low-resource languages. Specialized small models can be efficient and competitive, but results depend on the task: grounding retrieved context, reliable multi-step reasoning, safety, and generalization remain challenges, alongside trade-offs among accuracy, latency, memory, energy, and cost.

Latest papers

296 papers30 papers in the last four weeks, down 14% on the four weeks before. 0.2% of all new papers.

Sep 29, 2026

IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence

We present IronLLM-0.6B, a 654M-parameter language model designed for efficient on-device inference. IronLLM-0.6B combines a hybrid attention architecture with X-MTP, a lightweight shared-KV multi-token prediction design that eliminates per-depth KV-cache replay and employs a lightweight verification head for rollback-free drafting, achieving a 1.48x decoding speedup. The model is pretrained on approximately 6.2 trillion tokens using a quality-oriented data pipeline and is further post-trained with Multi-Domain On-Policy Distillation to integrate capabilities from domain-specialized teachers. To better meet the low-latency requirements of on-device scenarios, IronLLM-0.6B adopts an Instruct-Only design. Evaluations show that IronLLM-0.6B achieves competitive performance relative to larger models such as Qwen3.5-0.8B and MiniCPM5-1B, while producing more concise responses on many tasks. We further present IronLLM-0.6B-Light, which replaces RMSNorm with Dynamic Tanh and simplifies several computationally expensive components to improve inference and quantization efficiency. Together, the IronLLM models provide an effective performance-efficiency trade-off for resource-constrained deployment.
Sep 27, 2026

Optimizing the Phi-2 Small Language Model for Real-time Chatbot Applications Using Parameter-Efficient Fine-Tuning (PEFT) with QLoRA Quantization

This study explores the optimization of the Phi-2 Small Language Models (SLMs) for real-time chatbot applications through Parameter-Efficient Fine-Tuning (PEFT) and Quantized Low-Rank Adaptation (QLoRA). QLoRA specifically refers to the integration of PEFT with LoRA alongside a 4-bit quantization process, aimed at enhancing computational efficiency. These models, initially designed for high performance with minimal computational overhead, are further refined to address the constraints of mobile and edge computing environments. By integrating PEFT with QLoRA, the research aims to reduce memory usage significantly while maintaining, or potentially improving, the accuracy of model responses in real-time interactions. The effectiveness of these techniques was evaluated using the ROUGE metric system, which showed notable improvements in the summarization tasks performed by the models. This approach not only confirms the feasibility of using SLMs in resource-restricted environments but also opens up new avenues for deploying advanced AI-driven applications in real-time settings. The study's findings have significant implications for the development of efficient, scalable, and accessible AI technologies, paving the way for broader adoption in various industries.
Sep 25, 2026

Can You Check That? The Checkability Boundary for Local LLM Network Automation

Sending every network-automation input to a third-party frontier LLM exports sensitive artifacts such as production configurations, topologies, and logs. Querying small language models (SLMs) locally avoids this egress, but SLM outputs can be error-prone for direct use. This work introduces checkability as a criterion for determining which tasks are suitable for local inference. A task is checkable when it exposes a cheap, deterministic test - an intrinsic check - that rejects outputs violating a necessary correctness condition. We instantiate this idea in Touchstone, a local-first pipeline that uses seven off-the-shelf SLMs (1-8B parameters) to generate candidates, uses task-specific intrinsic checks to reject responses, and escalates unresolved inputs to a frontier LLM. On conflict detection and intent translation tasks, Touchstone reaches 98.6% and 93.8% end-to-end accuracy while escalating only 16% and 17% of inputs, respectively. On TeleQnA, a knowledge-only control that has no task-specific intrinsic checks, Touchstone is unable to match the accuracy of the frontier baseline. Our results support a simple deployment rule: keep inference local when task semantics support precise, low-cost checks; escalate the rest.
Sep 25, 2026

PTC-Decoder: Towards Intelligent SLMs on Offline Resource-Constrained Edge Devices

Deploying small language models (SLMs) on offline, resource-constrained edge devices such as remote sensing satellites presents a fundamental challenge: their limited reasoning capacity hinders reliable execution of multi-step agent tasks requiring complex tool orchestration. Existing plan-solve paradigms rely on prompt-based enforcement, which our experiments show SLMs almost entirely disregard: weak models fail to invoke the plan. We propose PTC-Decoder (Plan-Tool Constrained Decoder), a training-free, plug-and-play decoder framework that combines (1) a Plan-to-Act paradigm, which elevates planning to an atomic tool and forces its invocation at the first inference step, and (2) TC-Decoder, a deterministic finite automaton that imposes token-level hard constraints on tool names while preserving freedom over parameter generation, thereby retaining SLM reasoning capability. Evaluated on 200 real remote-sensing satellite tasks across 7 SLMs, PTC-Decoder yields a statistically significant mean overall score gain of +1.21 (p<0.01), 95% CI [+1.13, +1.29]), with consistent improvements across models and other datasets. An ablation study that removes TC-Decoder causes substantial performance degradation across all quality metrics without reducing computational cost, confirming TC-Decoder as the primary driver. PTC-Decoder thus offers a lightweight yet effective solution for improving step-level reliability, with final-answer accuracy remaining an open challenge. In essence, we enforce plan adherence by constraining the permissible output vocabulary during inference, without requiring retraining.
Sep 24, 2026

Baseline Shape Decides the Verdict: A Controlled Re-Examination of Ternary Language Models at 60K Parameters

Ternary (1.58-bit) weights are attractive for microcontroller-class language models, but the sub-1M-parameter regime rests mainly on isolated, single-seed comparisons. One prominent example reports that a routed ternary block (convolution, diagonal SSM and sparse attention mixed by a per-token router) beats a parameter-matched full-precision transformer by 22% at 60K parameters, attributing this to inductive bias. We re-run it under one fixed recipe, three seeds per cell, 98 byte-level runs on one laptop. (i) Baseline shape dominates: at a 16M-byte budget, param-matched transformers span 22.6% in validation loss purely by depth/width choice - far more than any architecture effect we measure there - and the best-shaped transformer ties the routed model, so the published margin is at least partly a baseline-shape effect; the ordering of shapes reverses with budget, so no single fixed shape can be trusted. (ii) At 130M bytes the routed model does win, by 22.2-24.0% over the three transformer shapes we evaluate there - but a plain gated diagonal-SSM block beats it by a further 9.1%, and the routed model's own router puts most of its weight on its recurrent pathway, so the gain does not require routing. (iii) The ternary penalty differs by architecture at the larger budget (+5.3% best transformer vs. +19.5% routed, +28.1% gated SSM), but we cannot attribute that to architecture alone: our transformers keep learned positional embeddings in full precision, 11-22% of their parameters, so they are less quantized than the models they are compared with. (iv) A 90/10 full-precision-then-ternary schedule beats all-ternary training, but only at a stage-2 learning rate about 10x the pretraining peak; at a conventional fine-tuning rate it looks 15.3% worse, reversing the conclusion. The from-scratch baseline was not itself learning-rate tuned, which bounds (iii) and (iv). Code and run logs released.
Sep 23, 2026

The Path Matters: Evaluating Small Language Models Beyond Answer Accuracy in KGQA

Small language models (SLMs) are increasingly paired with knowledge graphs (KGs), yet end-to-end KG question answering conflates graph access, search, navigation, reasoning, and answer generation. This coupling makes it difficult both to determine whether an SLM can faithfully execute the reasoning path implied by a question and to attribute failures to navigation rather than to other stages of the pipeline. We isolate this capability by employing the THESEUS navigation and traceability framework and using frozen, off-the-shelf SLMs as local action policies. At each hop, the environment exposes the legal outgoing graph actions, and the model selects one executable graph action and decides whether to stop, without task-specific parameter updates, model-controlled beam search, or free-form answer generation. This controlled setting allows us to evaluate terminal-answer accuracy with Hits@1 together with path fidelity, using Path Edit Distance (PED) as the primary trajectory metric. Across the Kinship and MQuAKE-ST KGQAs, similarly sized local models differ substantially in answer accuracy and path fidelity, with the two metrics sometimes favoring different models. This model-dependent behavior also extends to prompting, as a single demonstrated trajectory can improve or degrade navigation depending on the model. These results motivate evaluating SLM graph reasoning beyond endpoint accuracy alone.
Sep 23, 2026

Does Step Law Transfer to Small-Scale Language Models? An Empirical Recalibration Below 59M Parameters

Step Law gives power-law formulas for the optimal peak learning rate eta* and batch size B* when pre-training language models. It was calibrated on models between 59M and 1B parameters; the small-model regime N < 59M was never tested empirically by its authors. This regime matters for single-GPU training, interpretability research, educational experiments, and settings where larger models are infeasible on memory or cost grounds. We test whether Step Law transfers to small language models. We consider three outcomes: H1, the original coefficients work directly; H2, the power-law form holds but with different coefficients; and H3, a power law does not describe the optima in this regime. All experiments use a single nanoGPT/TinyStories pipeline with a 2048-token BPE vocabulary, AdamW, and a warmup-cosine schedule. The optimum for each (N, D) cell is extracted from the loss surface L(eta, B) via a local quadratic approximation in log-log coordinates over the smoothed training loss. The final dataset contains 29 unique (N, D) cells and 935 analysis-ready runs. The main refit uses 25 cells (815 runs) in the working range 4 <= D/N <= 600. On the pooled data we accept H2: the functional form is preserved, but the coefficients differ from the original. We obtain eta*(N, D) = 0.0985 N^(-0.508) D^(0.238) (R^2 = 0.834) and B*(D) = 3.6 x 10^(-4) D^(0.931) (R^2 = 0.950). Step Law's structural claim that B* is independent of N is reproduced (p = 0.87), but the growth of B* with D is nearly twice as steep as in the original work. Direct transfer of Step Law systematically overestimates the optimal learning rate: the median ratio eta_SL / eta* is approximately 4.0x, with a range of 2.4x to 6.6x.
Sep 20, 2026

Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap

Small open-source large language models (LLMs) in the 0.6B-4B parameter range are increasingly deployed for structured output generation (JSON, function calling, data extraction), yet little is known about how constrained decoding (CD) interacts with model scale in this regime. We benchmark five models from three families across 14 structured-output tasks under three decoding conditions (native, Outlines, XGrammar). We introduce a two-axis evaluation that separates structural correctness (schema validity) from semantic correctness (content accuracy). We find that CD eliminates all structural failures across all models (schema validity: 78.6-92.9% to 100%), but content accuracy reveals a persistent semantic gap that is scale-dependent: type coercion failures are fully CD-rescuable, while instruction-semantic failures (e.g., multi-step function calling) remain CD-resistant. Schema conformance is necessary but not sufficient for semantic correctness; CD's reach ends exactly where schema conformance ends.
Sep 18, 2026

ufakzeka-1: Building and Evaluating a 151M-Parameter Turkish Language Model from Scratch

We describe ufakzeka-1, a 151M-parameter (182M with embeddings) decoder-only Turkish language model pretrained from scratch on 13.5B tokens of openly licensed text and instruction-tuned for chat, at a total cost of about $286 in cloud GPU, API and notebook time. The contribution is not the model's capability, which is what a model this size can be expected to have, but the record of building and measuring it: a Turkish byte-level tokenizer at 1.77 tokens per word, a three-stage pretraining schedule, a post-training mixture of openly licensed and generated data, and an evaluation battery of release gates, a rule-checked sweep of 5,508 conversations, judged conversations and hand tests, all with prompts held out from the training data, enforced by decontamination inside the data build and by a checked-in invariant script we run before each build. We report three findings that we believe transfer to other small-model efforts: a safety gate that had been "fixed" with training data written from its own questions read 64/64 while the honest figure was 34/64; training-seed variance was as large as the spread across every recipe we tried, so single-seed comparisons at this scale are uninformative; and data rounds repaired only what was absent from the data, while identity tracking over long context and multi-turn arithmetic did not move across any data change we tried, which we read as limits of the model size rather than gaps in the data, a reading the next, larger model will test. Weights, the data recipe, the evaluation code and the spend ledger are released under Apache-2.0.
Sep 18, 2026

Toward Personalized Sleep Guidance from Wearable Data Using Language Models

Sleep monitoring using wearable data has shown promise for personal health, yet large language model (LLM)-based summarization and question answering remain insufficient for personalized sleep guidance. Training specialized models, however, often requires costly expert annotation. Moreover, privacy and accessibility concerns motivate lightweight, local deployment for end users. We present a two-stage framework to address these challenges. Specifically, in Stage1, a multi-agent LLM pipeline reasons structured sleep guidance from unannotated wearable records, enabling scalable dataset construction. Stage2 distills guidance reasoning trajectories into small language models (SLMs) through supervised fine-tuning and integrates a training-free Best-of-NN selection strategy to enhance inference. Experimental results demonstrate our method outperforms commercial general and medical LLMs and open-source models. Human evaluation further supports the quality of the generated guidance and the feasibility of personalized sleep guidance with SLMs.
Sep 18, 2026

Samsone: A Family of Open Small Audio Language Models for On-Device Inference

The success of Large Audio Language Models has driven the development of massive multimodal networks exceeding billions of parameters. However, the demand for privacy-preserving, low-latency processing has shifted focus toward Small Audio Language Models (SALMs) capable of on-device execution. In this paper, we introduce Samsone, a family of SALMs designed for edge computing. Our core model, Samsone-134M, establishes a new state-of-the-art for its size class across multiple benchmarks. We further explore the scaling laws of SALMs by introducing Samsone-99M and Samsone-356M. Despite their compact footprint, the Samsone family delivers performance competitive with models orders of magnitude larger. To foster open research and reproducibility, we train Samsone on publicly available data. We release the training code, model weights, mobile-optimized checkpoints and provide an open-source Android application to demonstrate real-time on-device inference of Samsone.
Sep 13, 2026

Depth and Scale in the Sub-150M Regime: JugnuLM-53M vs JugnuLM-110M

We scale our conventional sub-150M pretraining recipe from 53.5M to 109.7M parameters, holding the method fixed (Qwen3-style decoder with grouped-query attention, RoPE, SwiGLU, RMSNorm, QK-Norm, and a z-loss; FineWeb-Edu data) and changing only the geometry to a deep-and-thin 23-layer x 576-hidden design. The larger model improves across the board -- BLiMP 78.1 -> 81.3, ARC-Easy 51.4 -> 52.5, WikiText-2 byte-perplexity 2.04 -> 1.95 -- and its 81.3% BLiMP essentially matches GPT-X2-125M (81.28) at about 12% fewer parameters. Notably the 110M model achieves this on fewer training tokens (about 8B vs 12B), so the gain is attributable to capacity and depth, not more data. Both models are deliberately conventional; this report is a clean scaling control and the baseline rung (R0) of an ablation study of what further improves models in this regime. An ablation ladder follows: value residuals (R1) and the Muon optimizer (R2) lift ARC-Easy by a cumulative +3.6 (52.5 -> 56.1) at a near-flat BLiMP and are kept; a diverse data blend (R3) and two logit-distillation settings (R4a/R4b) are not kept -- honest negatives. R3 pins ARC-Easy to FineWeb-Edu's educational filtering rather than raw diversity; distillation from a 1.7B teacher can reach the class-leading ARC-Easy (56.99, matching GPT-X2-125M) but only at a perplexity cost that dialing KD down then erases -- so R2 remains the best kept stack.
Sep 11, 2026

OrchSLM: Probing the Dynamics of Small Language Model Orchestration

Although large language models (LLMs) have demonstrated remarkable capabilities, their reliance on cloud-scale infrastructure poses fundamental challenges for deployment in agentic pipelines, including latency, privacy, connectivity, and substantial computational cost. Small language models (SLMs) offer a compelling alternative: recent studies suggest that many repetitive and narrowly scoped subtasks in agentic workloads may be better served by specialized SLMs than by monolithic LLMs. However, the limited capacity and context windows of SLMs can constrain long-horizon reasoning and interaction-heavy orchestration strategies such as iterative verification and debate. This motivates a complementary, non-interactive paradigm in which heterogeneous SLMs independently generate candidate solutions and a router orchestrates their cached samples without further model interaction. To further understand the mechanisms of such orchestration, we introduce OrchSLM, a routing framework that unifies existing non-interactive orchestration methods and exposes their underlying design choices as controllable parameters. Using OrchSLM as a systematic probe, we reveal how orchestration behavior emerges from diverse knobs, including the task structure, model-pool composition, and multi-agent consensus.
Sep 11, 2026

Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks

The proliferation of highly capable open-weight Small Language Models (SLMs) democratizes access to advanced cybersecurity capabilities, posing an escalating risk as these models can bypass proprietary API guardrails when deployed locally. However, SLMs deployed as autonomous agents often struggle with long-horizon, exploratory tasks like cybersecurity Capture The Flag (CTF) challenges due to context bloat and cognitive degradation from accumulated tool-call outputs. To understand and mitigate this cybersecurity threat, we introduce context segmentation, a two-level agentic framework that divides complex exploitation tasks into manageable, contextually isolated sub-problems. Evaluating on the picoCTF dataset using memory-constrained gemma-4 models, we demonstrate that for the E4B model, our strategy acts as an intelligent search, achieving competitive rewards with superior token efficiency compared to brute-force retries, and successfully solving 18.52% of tasks that standard agentic execution fails to complete. Code is available at https://github.com/9xeb/context-segmentation.
Sep 9, 2026

Looped GPT-BERT: Trading Parameters for Computation in Small Language Modeling

When training data are limited, increasing parameter count is not the only way to improve language-model performance. A small parameter set, when repeatedly applied, can also deliver comparable performance. We study Looped GPT-BERT in the BabyLM 2026 Strict-small setting, combining GPT-BERT's masked next-token and causal language-modeling objectives with depth-wise parameter sharing. We train on a preprocessed 7.48M-word English corpus and compare objective ratios, non-looped and looped architectures, and loop counts. Our final 4×124\times12 model uses four physical layers for twelve recurrent traversals and contains 12.18M parameters. The BabyLM 2026 leaderboard reports an Overall Average of 35.42 and an NLP Average of 48.48. Compared with public BabyLM 10M Strict-small GPT-2 and GPT-BERT baselines, it achieves comparable performance on selected linguistic and downstream metrics, including BLiMP and GLUE, with fewer parameters. The loop ablations show that additional recurrent computation can improve training and preserve strong performance on selected linguistic tasks, whereas poorer performance on other tasks may reveal an inherent limitation of the looped design: using only a few physical layers restricts the model's representational space.
Sep 8, 2026

From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls

In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, making small language models (SLMs) attractive for on-device deployment. For such models, a key design choice is how the available function surface is presented. Two approaches are to represent each function with a dedicated Functional Token (FT) or provide function schemas directly in the prompt. FTs enable compact inference but are restricted to functions learned during training, whereas Schema-in-Prompt (SIP) can generalize to unseen functions at the cost of longer prompts and higher inference overhead. We introduce a benchmark of 9,822 single-turn examples spanning 79 vehicle functions derived from Android Automotive, including held-out functions and requests requiring refusal. We compare both approaches under matched fine-tuning across four SLMs from 270M to 1.7B parameters. On functions seen during training, scaling provides limited benefit: the 270M model can match the 1.7B model, and the highest Seen accuracy in our main grid occurs at 0.6B. On held-out functions, FT achieves zero accuracy by construction, whereas SIP generalizes and improves substantially with scale. On out-of-scope requests, FT can invoke an unavailable function it was trained to emit, while SIP more reliably refuses based on the functions offered. This flexibility comes with a higher inference cost, chiefly the latency of processing the schema prompt. Our theoretical analysis formalizes why only SIP can predict functions withheld as training targets and why longer schema contexts increase inference cost. Overall, function-surface representation, rather than model scale alone, determines the capabilities and failure modes of SLM-based vehicle function calling.
Sep 7, 2026

Beyond Fluent Generation: A CPU Reliability Benchmark for MCP-Style Tool Calling in Sub-2B Small Language Models for Edge Deployment

Resource constrained single-board computers including Raspberry Pi, NVIDIA Jetson Nano, Arduino UNO Q, Orange Pi, and LattePanda motivate on-device small language model (SLM) agents that reduce cloud dependence, improve data locality, and tolerate intermittent connectivity. Model Context Protocol (MCP)-style tool invocation demands more than fluent generation: an agent must emit machine-readable JSON, select the correct tool, supply all required arguments, and avoid unintended actions. We establish a platform-agnostic CPU baseline by evaluating five open-weight models below two billion parameters Phi-1.5, Pythia-1.4B, TinyLlama-1.1B-Chat, Qwen2.5-0.5B, and Qwen2.5-1.5B on 100 prompts spanning weather retrieval, web search, calculation, email composition, and task creation, under greedy decoding and nucleus sampling. A recovery parser strips Markdown fences, extracts brace-delimited substrings, and scores parseability, tool-name correctness, argument completeness, and value agreement. Under this criterion, Qwen2.5-1.5B achieves 75% (greedy) and 79% (sampling); Qwen2.5-0.5B achieves 72% (greedy) but drops to 32% under sampling. Phi-1.5 scores 0%; Pythia and TinyLlama reach at most 7%. A strict post-hoc audit finds only 5 of 1,000 raw responses directly parseable as JSON, exposing near-total dependence on output recovery. A CPU resource probe shows Qwen2.5-1.5B requires 7,960 MiB and 30.782 s mean latency; Qwen2.5-0.5B uses 3,637 MiB and 10.627 s, revealing a reliability-resource trade-off for edge deployment. These results do not cover the named boards directly or a full MCP implementation. Safe deployment requires schema validation, constrained generation, least-privilege execution, and human escalation for consequential actions.
Sep 1, 2026

Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?

Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell commands, writing memory, selecting tools, ranking past turns. We ask whether off-the-shelf SLMs meet practitioner-defined thresholds and, when they fail, why, and whether quantization changes the answer. We build a benchmark of 4 such microtasks with fixed prompts and automatic metrics, each with a pre-specified threshold ττ anchored to a cheap non-LLM baseline and a CI-aware eligibility rule (a configuration passes only if its confidence bound clears ττ). Sweeping Qwen3 0.6/1.7/4/8B at their best (FP16, greedy, one frozen prompt, no tuning), we find an eligibility gap: 0 of 16 (4 tasks ×\times 4 models) configurations pass (verified by checking the raw outputs and parser behavior). A logprob decision-threshold diagnostic (T1/T3/T4; T2 via a context-length/cascade probe) separates the failures into capability deficits and failures that can be addressed by changing the decoding threshold (4 regimes). Quantization to 4-bit (RTN/GPTQ/AWQ) does damage that depends on model size and moves no configuration into eligibility (certified on the reconstructable hard-label tasks T1/T3, diagnostic/windowed robustness on T2/T4), so the gap tracks model size more than precision; it replicates on Llama-3.x (12/12 ineligible) and is robust to the anchor choice (a ττ-sweep) and to prompt wording (0/112 eligible across the original plus 3 neutral paraphrases per cell). The practical implication: place SLMs behind a baseline that meets the CI-backed threshold, and use the SLM only where the baseline fails to meet the threshold; e.g. a 4B re-ranker over a BM25 shortlist beats BM25 (+0.047+0.047 [0.020, 0.073], without itself certifying eligibility).
Sep 1, 2026

Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents

Prospective memory means carrying out a deferred intention at the right future cue while other work continues. Benchmarks now isolate it as an agent skill, yet frontier LLMs still struggle: the best published PM-Bench scaffold reaches only 65.1% Set-F1. We argue that this loop is schema-constrained state tracking rather than open-ended reasoning, and that small models can execute it when the action space is typed. We propose the Prospective Intention Store (PIS) that puts lifecycle logic in code and scoped language work on the model. The scaffold is agentic and training-free: no selector fine-tuning and no trajectory distillation. On PM-Bench, DeepSeek-Chat with PIS reaches 82.9% Set-F1. On Gemma-E2B, Set-F1 is only 4.2% without a store and at most 6.6% under seven retrospective memories, while PIS reaches 66.2%. PIS further reaches 70.1% Set-F1, where retrospective memory methods stay at most 54.4%. PIS sets a new state of the art on this benchmark and enables small models to surpass the published large-model scaffold.
Sep 1, 2026

Triple-Bottom-Line Sustainability of Language Models for Edge AI: A Comparison Between SLMs and Quantized LLMs

Edge-AI model selection is commonly driven by one isolated metric - accuracy, latency, memory, energy, or safety, even though a deployable language model must balance all five. Our work focuses on answering the question whether na- tively trained small language models (SLMs) or large language models (LLMs) compressed through post-training quantization offer the more sustainable edge- deployment trade-off. We introduce a reproducible Holistic Sustainability Score (HSS) organized around the triple bottom line: an economic pillar for capability and systems efficiency, an environmental pillar for operational GPU energy and a social pillar for harmful-prompt robustness. Five BF16 SLMs and five LLMs under different quantization approaches - BF16, INT8, NF4 4-bit, GPTQ 4-bit, and GGUF Q4 produce 30 measured configurations. Capability is assessed on five zero-shot benchmarks; efficiency uses latency, throughput, peak VRAM and energy; and safety is approximated by attack success rate on five harmful prompts. Qwen3-30B-A3B/GGUF Q4 ranks first in the combined pool (93.38), followed by Mistral-Small-24B/GGUF Q4 (92.40), while Phi-4-mini/BF16 is the highest- ranked SLM in that pool (89.49). Thus, the hypothesis that native SLMs must be the most sustainable edge choice is not supported universally; optimized quantized LLMs can win overall, while SLMs remain competitive through lower resource demand. Quantization is a systems-level choice rather than a monotonic precision- efficiency trade-off and HSS remains relative to its comparison pool and proxy definitions.
Aug 31, 2026

EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Language Models

For emerging scientific research domains, local Small Language Models (SLMs) are becoming more attractive, as they offer stronger privacy control and more stable deployment pipelines than Large Language Models. However, in practice, scientific question-answering on SLMs often operates under inevitable constraints: small literature collections, fragmented evidence, limited context window and reasoning abilities. We propose the Evidence-Grounded Typed Knowledge Graph (EGT-KG), a retrieval framework to improve information retrieval with local SLMs. We assessed three question-answering settings: a vanilla Retrieval-Augmented Generation (RAG) workflow and two EGT-KG workflows: an automatically generated relation schema (AS) and an expert-defined relation schema (ES). Our experiments were evaluated with a six-dimensional evaluation framework (S3CRF: Soundness, Correctness, Completeness, Conciseness, Relevance, Fluency) on a Biopolymer-bound Soil Composite literature benchmark, showing that EGT-KG outperforms the vanilla RAG method in most settings, with the best improvement from llama3:8b: a Final Score of 70.37 (+14.67%) and 68.82 (+12.14%) by AS/ES EGT-KG variants.
Aug 31, 2026

Calibrating Small Language Models for Claim Check-Worthiness Detection

Assessing claim check-worthiness is an essential first step in automated fact-checking pipelines. This work is motivated by a real deployment challenge at an early-stage startup: running large language models (LLMs) over every incoming claim is cost- and latency-prohibitive, yet smaller models sacrifice accuracy. We propose NN-PPI, a pointwise extension of Prediction-Powered Inference (PPI) that calibrates model predictions at inference time as a lightweight post-hoc layer, without re-training the underlying model. NN-PPI achieves weighted F1 gains ranging from 12% to 33.80% depending on the size and performance of the baseline model, bringing SLMs on par with larger LLMs. Beyond few-shot SLMs, NN-PPI further improves a production-deployed fine-tuned model, demonstrating that residual calibration is complementary to supervised fine-tuning. By recovering LLM-level accuracy from models that are an order of magnitude cheaper to serve, it makes accurate check-worthiness detection substantially cheaper to operate at scale. Our code and data can be found at https://anonymous.4open.science/r/arr-claim-worthiness-F237.
Aug 29, 2026

Free the Language Model From the Vision Encoder: Semantic Serialization as a Perception Interface for Small Language Models

End-to-end vision-language models (VLMs) bind visual competence to the scale of their language model: as the language model shrinks, perception and reasoning degrade together. We study an embodied scene question-answering (QA) interface in which vision never enters the language model. A frozen perception stack detects and ranges objects; a deterministic semantic serializer compiles the perceived state, errors included, into decision-aligned text; an unmodified text-only large language model (LLM) answers. On a visible-scope-matched, occlusion-audited campus-robot benchmark, under a prospectively frozen criterion, the serialized interface, using detectors fine-tuned in-domain within each fold, outperforms a zero-shot VLM whose language model has the same 7B scale (0.7892 vs 0.7462), with a larger margin at 3B (0.7673 vs 0.6913). Preregistered decoupling experiments show the gain survives paraphrase, attributing it to decision-aligned computation rather than answer-string leakage, while novel judgment vocabularies bound its scope. The advantage grows as the reader shrinks to 1.5B and reverses at 0.5B, and a ground-truth oracle locates the reader-capability floor. Under matched task supervision the interfaces converge: a VLM fine-tuned with low-rank adaptation (LoRA) overtakes the zero-shot system but only ties an equally supervised text reader (0.8441 vs 0.8396, no statistically resolved difference), and both routes remain perception-bound. Reported perception parameters are comparable to those of the VLM's vision tower, and total compute is not smaller.
Aug 26, 2026

Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Models

One common trade-off in the use of large language models involves reducing the size of the model while increasing the amount of computation at inference time, for example by using a wider beam search. In this paper, we examine the constrained case of this "model size vs. inference compute" trade-off, in which the model outputs are constrained by a strict grammar at inference time. Our results demonstrate that the constrained trade-off behaves differently from the unconstrained trade-off. We investigate the task of converting a prose query into an equivalent SQL query (text-to-SQL). Performance is evaluated on the Spider text-to-SQL benchmark, using the Qwen2.5-Instruct model family ranging in size from 0.5B to 7B parameters, all at 4-bit precision. We experiment with two approaches to varying inference compute: (i) beam search with a variable number of beams; and (ii) sample+vote, i.e., sampling several constrained outputs and then voting on their execution results, where the number of samples is varied. On the 1034-example development set, we find that: (a) both beam search and sample+vote improve accuracy, especially on smaller model sizes; (b) the "model size vs.\ inference compute" trade-off is not advantageous in this experiment, because moving to a larger model size typically results in higher accuracy than increasing inference compute on the same model size; (c) beam search outperforms sample+vote at a matched inference budget. This latter result is of particular interest since it contrasts with the findings of the unconstrained trade-off.
Aug 20, 2026

Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference

Small language models are usually built like large ones and then squeezed onto a CPU afterwards. We did the opposite: we fixed the target first, one user, one token at a time, 4-bit weights, ordinary CPU, and chose the architecture to suit it. The result keeps full attention in only 6 of its 18 blocks. The other 12 use short convolutions whose memory is two timesteps wide no matter how long the conversation gets, so two thirds of the network never re-reads a growing cache. Trained from scratch on 59.9B tokens, the model scores 47.31 on a five-task benchmark against a bar of 42.20 that was fixed before training began. It beats GPT-2 124M, Pythia-160M, OPT-125M and GPT-neo-125M, all trained on three to six times more data, and exceeds MobileLLM-125M's published score despite that model seeing a trillion tokens. Validation bits-per-byte is 0.8685. To check the architecture rather than the training recipe, we trained a conventional all-attention model of the same size on the same data, and wrote down the winning condition before scoring either. The hybrid won the chosen quality metric by 0.81%, matched it on downstream tasks, produced a 6.3% smaller 4-bit file, and decoded 1.76x faster at 2048 tokens of context, 2.08x against an external model of similar size. In every measurement the speed advantage is near zero at an empty context and grows with length, which is what the mechanism predicts and what a merely leaner model would not show. A simple bandwidth calculation predicts only 1.17x, so memory volume alone does not explain the gap. We also report what did not work: an unmitigated 4-bit quality cost, roughly half the convolution channels ending up inert and impossible to remove, and a vocabulary larger than this model size warrants.
Aug 19, 2026

TranslatePsy-AfriSLM: High-Quality Data Scaling For Low-Resource Machine Translation

The rapid progress in Artificial Intelligence has largely bypassed African languages, creating a digital divide that limits AI adoption on the continent. Recent open-source LLMs systematically underperform on African language machine translation, while the lack of large-scale, high-quality, open-source parallel data has constrained the development of competitive small language models (SLMs). We introduce TranslatePsy-AfriSLM, a collection of open-source machine translation resources for 19 Sub-Saharan African languages, including curated parallel data, African-specialized synthetic data, and a family of fine-tuned SLMs. Our empirical study shows that unified quality-estimation filtering removes up to 96% of training tokens without degrading quality, and that filtered synthetic data dominates the quality-efficiency Pareto frontier. Fine-tuned on the resulting data mixture, TranslatePsy-AfriSLMs outperform substantially larger systems, including TranslateGemma-27B and Qwen3.5-122B-A10B, with as few as 0.8B parameters.
Aug 19, 2026

Improving Natural-Language Combinatorial-Optimization Accuracy in Resource-Constrained Language Models via Formal Abstractions

Combinatorial scheduling poses a significant challenge for language models, requiring them to identify feasible solutions within exponentially large search spaces while satisfying complex constraints. This challenge is especially pronounced in resource-constrained settings, where larger language models are impractical and selection is limited to smaller models which often fail to preserve feasibility when scheduling directly from natural language. To address these limitations, we introduce SDDL, a neuro-symbolic framework that translates natural-language scheduling problems into compact, solver-aligned representations of tasks, resources, constraints, and objectives, while delegating low-level modeling and search to a deterministic compiler and external solver. On a 300-instance, multi-family subset of scheduling problems, SDDL improves independently verified feasibility for every resource-constrained model tested. The two strongest SDDL configurations reach 55.3% and 28.3%, up from direct-generation baselines of 23.7% and 1.3% and solver-code baselines of 21.7% and 7.0%, with a 0.0% median optimality gap among feasible schedules. By expressing problem structure rather than generating solutions or solver code, SDDL enables smaller models to approach the strongest evaluated direct- and solver-code configurations, including substantially larger frontier models.
Aug 18, 2026

Where A Small Language Model Helps in Invoice Categorisation, Understood Through Embedding Geometry

Categorising invoices into the correct General Ledger (GL) code underpins financial reporting and tax compliance. This is a skilled accounting judgement rather than a routine task: the correct category depends subtly on the nature of the purchasing business, the vendor and the invoice text. Whilst AI is increasingly being adopted across industries to automate tasks, including invoice categorisation, implementations built on in-house small language models (SLMs) can simultaneously reduce cost and improve data security, confidentiality, and interpretability. We investigate this approach by first analysing the pre-trained embedding geometry of a small sentence transformer (SBERT) and classic SLM (DeBERTa). The sentence-embedding space of this financial corpus is globally anisotropic but composed of locally isotropic clusters, extending prior token-level findings to sentence embeddings in a financial setting, and these clusters are strongly correlated with the vendor identity. SBERT fine-tuned on a single GPU reaches 0.96 accuracy on invoice classification, above both a zero-shot LLM and a vendor identity baseline, increasing performance for smaller, challenging categories and new clients. For this important generalisation problem, SBERT reaches 0.9 F1 with roughly 100 client-specific invoices, showing that an in-house SLM implementation is promising. Combining these results with geometric analysis shows that pre-trained embedding geometry is associated with classification performance and reveals a counterintuitive finding that a structured input that would help a human reader does not improve the SLM performance.
Aug 17, 2026

Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models

Small Language Models (SLMs) are increasingly deployed in resource-constrained, privacy-sensitive settings, where safety and bias failures can cause security and societal risks. However, existing AI safety\slash security\slash compliance benchmarks are designed for large language models that may not transfer reliably to SLMs. We therefore ask: Can these benchmarks effectively and reliably evaluate SLMs? To answer this question, we conduct a large-scale assessment of the effectiveness and robustness of these automated pipelines by evaluating five widely used benchmark suites across 26 open-source SLMs under a unified judging rubric, which assigns a score of 0, 1, or 0.5 to harmful, safe, or ambiguous/irrelevant responses, respectively. Across the benchmarks, ambiguous judgments dominate and correlate with prompt complexity and model architecture, indicating that {\em LLM-centric safety benchmarks are insufficient as standalone evidence for SLM safety assessment}. In general, the ambiguity rate increases with lexical density, output perplexity, and output length and decreases with lexical sophistication, self-coherence, and reply-prompt similarity. This reveals a capability-safety confound that mixes model capability with apparent safety. Since ambiguity is prevalent, aggregate mean-score leaderboards are mathematically brittle: model rankings change significantly under reasonable ambiguity treatments, even when the underlying outputs remain unchanged.
Aug 17, 2026

Structured Driving-State Narratives for Small Language Model-Based GNSS Spoofing Detection

Autonomous vehicles (AVs) depend on reliable Global Navigation Satellite System (GNSS) positioning. However, spoofed GNSS signals can induce plausible but incorrect vehicle states. This study develops a small language model (SLM)-based framework for detecting and classifying GNSS spoofing attacks by comparing vehicle behaviors independently derived from GNSS and other sensing sources. The framework converts independent driving states from GNSS and other sensing sources into structured semantic narratives that are provided to an SLM for spoofing detection and attack classification. The performance of the SLM-based framework is compared with large language models (LLMs) fine-tuned on identical training data and evaluated on the same test set. The evaluation considers five classes: no attack, overshoot attack, stopped attack, turn-by-turn attack, and wrong-turn attack. The framework is also evaluated with geographically unseen field data collected in Clemson, South Carolina, United States. Experimental results indicate that the evaluated SLMs achieve performance similar to the LLMs, achieving an average accuracy of 96.99%, precision of 99.05%, recall of 95.59%, and F1-score of 97.18%. In terms of computational efficiency and resource utilization, the SLMs demonstrate advantages over the LLMs by requiring lower inference latency and less GPU memory during both fine-tuning and inference. Evaluation using field data collected in a geographically distinct location further demonstrated its efficacy. The presented framework can detect and classify GNSS spoofing attacks in real-time while requiring relatively low computational and memory resources, and is therefore suitable for deployment on resource-constrained vehicular computing platforms.