TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models

• URL: http://arxiv.org/abs/2606.06902v1
• Date: Fri, 05 Jun 2026 04:34:50 GMT
• Title: TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models
• Abstract summary: We introduce TALAN (Task-Aligned Latent Adaptation Networks), a sequence-conditioned latent side path inserted into a transformer's residual stream.<n> TALAN compresses the active sequence into latent memory, remixes it into token-level perturbations, and writes them back through a controlled residual update.<n>Across four Qwen3-family backbones and four STEM/code benchmarks, TALAN improves matched LoRA and DoRA baselines.
• Score: 8.47008876232157
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Targeted post-training aims to improve reasoning, math, and code without degrading strengths. Low-rank adapters are efficient but task-global; activation interventions are input-aware but often require separate probes, vectors, or inference-time steering. We introduce TALAN (Task-Aligned Latent Adaptation Networks), a sequence-conditioned latent side path inserted into a transformer's residual stream and co-trained with a low-rank adapter in one SFT loop. TALAN compresses the active sequence into latent memory, remixes it into token-level perturbations, and writes them back through a controlled residual update. It is configured along six axes: insertion location, memory size, mixer, writeback rule, trainability scope, and gradient scale. Across four Qwen3-family backbones and four STEM/code benchmarks, TALAN improves matched LoRA and DoRA baselines. With LoRA, it yields a +1.41 point cross-model mean gain, positive on all four backbones and non-negative on all 16 model-benchmark cells. With DoRA, it yields a +1.85 point mean gain, positive on all backbones and on 13 of 16 cells. Paired seed checks support positive average effects but show nontrivial variance, so we treat them as sensitivity checks. Cost is small: <1% trainable parameters relative to the backbone and 1.01-1.02x inference overhead versus matched LoRA. A Llama-3.2-1B transfer probe is also positive under LoRA and rsLoRA across seven paired seeds, supporting a transfer beyond Qwen. Internal-state analyses suggest TALAN is a small complementary activation intervention. The matched adapter update is 80-1,700x larger than the TALAN perturbation, yet their directions have near-zero cosine; per-layer measurements show this small orthogonal perturbation propagates and amplifies through depth. TALAN offers a practical platform for studying steerable activation-level adaptation within standard adapter-based post-training.

Related papers

• Architecture-Dependent Causal Transfer of Activation States Across Large Language Models [51.56484100374058]
  Internal language activation states can be transferred causally between different large language models.<n>Injecting projected activations into a target model during generation produces a statistically significant, preregistered causal effect.<n>We conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
  arXiv  Detail & Related papers  (2026-08-17T09:53:27Z)
• Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning [2.749219725903528]
  Large language models generalize well to individual tasks but lack an inherent mechanism for learning them sequentially.<n>LoRA-based continual learning methods allocate a separate low-rank adapter per task, yet existing approaches either require task identity at inference or sum all adapters indiscriminately.<n>Recent gating-based solutions route inputs to the correct adapter but introduce trainable parameters that themselves need protection against forgetting.<n>Latent-LoRA is replay-free, requires no trainable routing component, and uses substantially fewer parameters per task.
  arXiv  Detail & Related papers  (2026-07-26T20:42:56Z)
• Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning [47.97857843162072]
  We study whether saliency signals originally developed for pruning can be reused to choose where a model should adapt.<n>We propose Super, a sparse parameter-efficient fine-tuning (PEFT) method that fixes a small trainable support.<n>We then introduce Supra, a hybrid adapter that combines this sparse update with LoRA.
  arXiv  Detail & Related papers  (2026-07-10T10:55:28Z)
• TaDA: Calibrated Probe Gating for Task-Domain LoRA Merging [6.356259006504384]
  We argue that task and domain adapters exhibit a consistent depth-dependent asymmetry across transformer architectures.<n>We propose a training-free algorithm that exploits this structure through calibrated probe-guided per-layer gating and per-component subspace-aware merging.<n>$textbfTaDA$ produces a standard rank-$r$ LoRA adapter with zero inference overhead.
  arXiv  Detail & Related papers  (2026-06-03T15:39:37Z)
• Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning [55.264863369127774]
  Current methods reduce each correct rollout to a single reward bit, ignoring the geometric structure shared among their hidden states.<n>We propose Hidden-Align, an auxiliary loss function that aligns the last-layer hidden states of correct rollouts at the anchor token during RL training, with zero overhead in both training and inference.<n>On eight mathematical reasoning benchmarks, Hidden-Align improves average pass@1 over the DAPO baseline by 3.8, 6.2, and 5.4 percentage points on Qwen3-1.7B, 4B, and 14B respectively, with consistent pass@k gains across all three scales.
  arXiv  Detail & Related papers  (2026-06-02T06:51:15Z)
• CRMA: A Spectrally-Bounded Backbone for Modular Continual Fine-Tuning of LLMs [0.0]
  We introduce CRMA, a residual adapter whose internal mixing matrix M is doubly-stochastic at every forward pass via Sinkhorn normalization.<n>On Mistral-7B across 5 domains 3 seeds, modular per-task LoRA mediates a backbone loss-relative drift from +42.96% +/- 5.5 (naive fine-tuning) to -0.17% +/- 0.17, with disjoint per-seed ranges, and improves prior-task holdout loss by 1.99% +/- 0.54 over a matched frozen-substrate baseline.
  arXiv  Detail & Related papers  (2026-05-29T21:50:23Z)
• Low-Rank Adaptation Reduces Catastrophic Forgetting in Sequential Transformer Encoder Fine-Tuning: Controlled Empirical Evidence and Frozen-Backbone Representation Probes [3.305265383862785]
  We present an empirical study of Low-Rank Adaptation (LoRA) in sequential transformer encoder finetuning with companion representation probes.<n>In five full-validation BERT-base reruns on an RTE->MRPC->CoLA->SST-2 sequence, full fine-tuning yields 19.9% +/- average forgetting, whereas standard LoRA (r, query/value modules) yields 0.6% +/-1.4%.
  arXiv  Detail & Related papers  (2026-03-29T14:14:36Z)
• Label-Free Cross-Task LoRA Merging with Null-Space Compression [50.63908869296697]
  We introduce Null-Space Compression (NSC) Merging, a label-free, output-agnostic method that sets merge weights from adapter geometry.<n>NSC achieves state-of-the-art performance across twenty heterogeneous vision tasks with balanced gains where prior methods overfit subsets of tasks.
  arXiv  Detail & Related papers  (2026-03-27T11:34:41Z)
• The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation [86.83038620308423]
  Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data.<n>We propose Guided Online Low-rank Directional adaptation (GOLD), which uses a lightweight adapter to project features onto the golden subspace and learns a compact scaling vector while the subspace is dynamically updated via AGOP.
  arXiv  Detail & Related papers  (2026-03-23T12:48:38Z)
• When Domain Pretraining Interferes with Instruction Alignment: An Empirical Study of Adapter Merging in Medical LLMs [0.6345523830122167]
  Large language models can exhibit surprising adapter interference when combining domain adaptation and instruction alignment.<n>We study a two-stage LoRA pipeline for medical LLMs, where domain-oriented pre-training (PT) and supervised fine-tuning (SFT) are trained separately and later merged.
  arXiv  Detail & Related papers  (2026-01-26T10:54:06Z)
• The Quest for Winning Tickets in Low-Rank Adapters [24.58659526975649]
  We investigate whether the Lottery Ticket Hypothesis extends to parameter-efficient fine-tuning.<n>Our key finding is that LTH holds within Low-Rank Adaptation (LoRA) methods.<n>We propose Partial-LoRA, a method that identifies saidworks and trains sparse low-rank adapters aligned with task-relevant subspaces of the pre-trained model.
  arXiv  Detail & Related papers  (2025-12-27T06:39:08Z)
• Don't Forget the Nonlinearity: Unlocking Activation Functions in Efficient Fine-Tuning [82.16625951603315]
  NoRA replaces fixed activations with learnable rational functions and applies structured low-rank updates to numerator and denominator coefficients.<n>On vision transformers trained on CIFAR-10 and CIFAR-100, NoRA matches or exceeds full fine-tuning while updating only 0.4% of parameters.<n>NoRA constrains adaptation to a low-dimensional functional subspace, implicitly regularizing update magnitude and direction.
  arXiv  Detail & Related papers  (2025-09-16T16:47:03Z)
• IPA: An Information-Preserving Input Projection Framework for Efficient Foundation Model Adaptation [56.72132739364876]
  We propose IPA, a feature-aware projection framework that explicitly preserves information in the reduced hidden space.<n> IPA consistently improves over LoRA and DoRA, achieving on average 1.5 points higher accuracy on commonsense reasoning.
  arXiv  Detail & Related papers  (2025-09-04T17:10:01Z)

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.