LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2609.00284v1 Announce Type: cross Abstract: Emerging 6G wireless networks are expected to operate across diverse deployment scenarios, where variations in network topology, user mobility, traff...
arXiv:2609.00351v1 Announce Type: cross Abstract: Large language models can hide hidden behaviors that activate only under narrow conditions, such as backdoor triggers, sleeper-agent deployment cues,...
The paper introduces CRAFT, a data‑centric fine‑tuning approach that aligns small language models (SLMs) for pre‑hoc reasoning in AI‑native 6G radio access networks (RAN). By automatically generating verified (input, trace, label) triplets and fine‑tuning with low‑rank adaptation, CRAFT achieves high accuracy and F1 scores on TRACTOR and IC xApp datasets while avoiding parse failures that plague RL methods like GRPO. It also reduces energy consumption by 59% compared to GRPO baselines, offering a more sustainable path to auditable AI in 6G RAN.
arXiv:2609.01244v1 Announce Type: new Abstract: Every supervised fine-tuning run forces the same chain of decisions, such as learning rate, batch size, LoRA or full fine-tuning, how many epochs, whic...
The paper introduces a two‑stage training framework that combines Supervised Fine‑Tuning (SFT) and Direct Preference Optimization (DPO) to improve multimodal disaster severity assessment. It creates two datasets—ReasoningSet for validated rationales and PreferenceSet for paired rationales—using a single Human‑in‑the‑Loop workflow. Experiments on InternVL‑3‑8B and LLaVA‑1.5‑7B show that SFT boosts classification accuracy and Macro‑F1, while DPO further enhances interpretability and alignment with human judgment.
arXiv:2609.00565v1 Announce Type: cross Abstract: Cultural fine-tuning has become the de facto paradigm for building culture-aware large language models (LLMs), yet existing optimization exclusively...
arXiv:2608.00207v2 Announce Type: replace Abstract: Large Language Models (LLMs) perform strongly in English medical tasks but degrade substantially in Arabic, a gap widely attributed to limited trai...
arXiv:2609.01014v1 Announce Type: new Abstract: Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enroll...
arXiv:2609.01433v1 Announce Type: new Abstract: Concept erasure aims to suppress unsafe, privacy-sensitive, or undesirable generations in text-to-image diffusion models while preserving benign semant...
The paper introduces a scalable framework that uses finetuned large language models (LLMs) to translate unstructured textual resources into structured event logs for process mining. By creating a new text-to-log dataset and finetuning LLMs on it, the authors demonstrate that the resulting models produce high‑fidelity event logs, outperforming few‑shot or zero‑shot prompting methods. This approach enables previously unused organizational data, such as incident tickets and manuals, to be incorporated into process mining workflows.
CopyShield is a benchmark that compares three copyright‑defense methods—contrastive decoding, Direct Preference Optimization (DPO), and activation intervention—across two large language models (LLaMA‑3.1‑8B and Mistral‑7B‑v0.3). The study uses controlled memorization of five public‑domain books to measure literal leakage, calibrated non‑literal leakage, utility, and degeneracy, finding that each intervention level yields distinct compliance‑utility trade‑offs. Results show contrastive decoding limits degeneracy but hits a suppression floor, DPO nearly eliminates literal leakage yet causes paraphrase‑loop degeneracy, and activation intervention blocks most non‑literal queries before generation, with human evaluation highlighting coherence and perceived copyright risk differences.
The paper investigates why supervised fine‑tuning (SFT) of large language models leads to increased hallucinations of factual information. It proposes a self‑distillation SFT approach that regularizes output‑distribution drift to preserve pre‑training knowledge, and shows that freezing parameter groups can reduce hallucinations when new knowledge is unnecessary. Experiments attribute the main cause to interference among overlapping semantic representations, which self‑distillation mitigates, and an associative‑memory model explains the forgetting dynamics.
The paper investigates how different training strategies affect the prompt sensitivity of large language models. It reproduces and compares methods such as refined data construction and robustness objectives, finding that while robustness fine‑tuning improves over standard fine‑tuning and in‑context learning, the prompt gap remains large (40–57%). Notably, newer techniques like CoIN and PPCL often underperform a simple data‑construction approach that uses one template per batch, and diagnostics suggest that mixed‑template batches force the optimizer to reconcile conflicting updates rather than learn a prompt‑agnostic representation.
The study evaluates large language models (LLMs) as rerankers in conversational movie recommendation, comparing proprietary, open-weight, and fine-tuned LLMs against collaborative-filtering and sequential baselines on the ReDial benchmark. Results show that the best proprietary LLM achieves an NDCG@10 of 0.1497 with a shared semantic candidate pool, outperforming non-LLM baselines, while open-weight LLMs do not surpass a tuned shallow autoencoder under the same protocol. The analysis also highlights that reranker performance is highly sensitive to candidate generation, pool size, scoring policy, and decoding temperature, suggesting these factors should be reported as standard evaluation fields.
The paper introduces DroneCATS-Agent, a modular framework that places a multimodal large language model (MLLM) at the core of a drone’s control loop, allowing the model to decide actions solely from prompts. It presents the DroneCATS benchmark, evaluating MLLMs on four tasks—approaching, tracking, searching, and multi‑drone commanding—without fine‑tuning or function‑calling. Results show that while small open models can navigate reliably, they often fail by mismanaging protocol termination, highlighting a gap between perception and action planning in current MLLMs.
The paper introduces the Prospective Intention Store (PIS), a method that places lifecycle logic in code and confines language tasks to a typed action space, enabling small models to perform prospective memory tasks more effectively. Using PIS, a small model (DeepSeek-Chat) achieves 82.9% Set‑F1 on PM‑Bench, surpassing the previous best of 65.1%. On Gemma‑E2B, PIS boosts Set‑F1 from 4.2% (without a store) to 66.2%, and reaches 70.1% Set‑F1, outperforming retrospective memory approaches that max out at 54.4%.
The paper introduces Iterative MBR Distillation for Error Span Detection (ESD) in machine translation, a self‑evolution framework that replaces human annotations with pseudo‑labels generated by a large language model. By iteratively applying Minimum Bayes Risk decoding, the method produces high‑quality error spans without costly human effort. Experiments on WMT Metrics Shared Task datasets show that models trained solely on these pseudo‑labels outperform both unadapted baselines and supervised models trained on human data at system and span levels, while keeping sentence‑level performance competitive.
The paper investigates a privacy‑hallucination tradeoff in differentially private (DP) language models. It shows that DP pre‑training or fine‑tuning increases hallucinations compared to non‑DP models, especially as the privacy budget becomes stricter. The authors attribute this to DP mechanisms flattening output distributions, and demonstrate that controlling the frequency of facts in training data can mitigate hallucination risks.
The study investigates whether post‑training methods—GRPO, SFT, and DPO—improve language models’ ability to follow prompt evidence that conflicts with memorized knowledge. By comparing nine training variants across different scales and families, the authors find that grounding gains are modest for GRPO, moderate for Conflict‑SFT, and near‑ceiling for DPO, but all largely rely on the same causal attention‑head set present in the starting checkpoint. Removing the starting‑model grounding direction suppresses these gains, while adding it back recovers a significant portion of DPO’s improvement, indicating that existing model machinery drives most of the observed gains.
The paper introduces SARTM, a framework that adapts the Segment Anything Model (SAM) for RGB‑thermal (RGB‑T) semantic segmentation. It fine‑tunes SAM with LoRA layers, incorporates language guidance, and employs a Cross‑Modal Knowledge Distillation module to bridge modality gaps. The approach also modifies the segmentation head and adds an auxiliary semantic head, achieving superior performance on MFNET, PST900, and FMB benchmarks.