arXiv Computation and Language

MechSparse: Mechanism-Guided Sparse PEFT Selection Is Task-Shaped

arXiv Machine Learning
Oct 3

MECHVAR: Variance-Guided Mechanism Discrimination for Autonomous Machine Learning Experiment Selection

MECHVAR is a lightweight, auditable rule for selecting experiments from a finite library to discriminate between candidate mechanisms. It chooses probes by maximizing the posterior‑weighted variance of predicted responses, a score that aligns with the Box–Hill pairwise‑KL criterion and links to expected information gain when separations are small. Experiments on a 25‑block audit and a Digits loop show MECHVAR outperforming confirmation‑first strategies and matching or exceeding EIG in identification accuracy while being far faster to compute.

By Yifan Guo
arXiv AI
Sep 17

Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Vision-Language Models for Harmful Meme Detection

The paper investigates why large vision‑language models sometimes misclassify harmful memes, attributing failures to either missing internal evidence or poor routing of evidence to the output. Using sparse autoencoders, role‑conditioned probes, and causal interventions on Gemma‑3 and Qwen3.5, the authors show that sparse readouts consistently outperform native predictions across six harmful content benchmarks, revealing a readout gap that is largely due to routing rather than representation. The study also demonstrates that calibration‑only routing recovers most of the performance gap and that the issue persists across languages and is not solely driven by OCR signals.

By Girish A. Koushik, Diptesh Kanojia, Helen Treharne
arXiv Machine Learning
Nov 5

The Alignment Tax Is Graded: Task-Selective Capability Loss Under Length-Normalized DPO with SFT Retention

The study empirically investigates how length‑normalized Direct Preference Optimization (DPO) with a Structured Fine‑Tuning (SFT) retention term (RPO objective) affects downstream capabilities of a Qwen3.5‑4B model fine‑tuned with sparse LoRA on structured financial‑filing tasks. Results show that the alignment tax is graded and task‑selective: extraction performance is largely preserved, JSON extraction degrades modestly, and router‑based tasks suffer severe loss, with most degradation attributed to suppression of rejected completions. The analysis uses 8 seeds, artifact‑aware scoring, and TOST equivalence testing to quantify these effects across different reward margins and precision settings.

By Ye Yuan
arXiv Machine Learning
Jun 5

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models

arXiv:2606. 05378v1 Announce Type: new Abstract: We test whether a single screen-and-ablate recipe -- identify attention-head circuits by task-pattern selectivity, then verify by causal ablation against a matched-random null -- produces consistent mechanistic claims across model families.

By Yongzhong Xu
arXiv Machine Learning
Oct 5

The Conflict Between Logic and Memory: Training Conditions for Optimizer-Dependent Rule Acquisition

The paper investigates how different optimizers acquire distinct generalizing relations in single‑hidden‑layer ReLU networks. By manipulating nuisance‑connected weights and performing a strict‑parity sweep, the authors show that training conditions reshape both shared failures and relative optimizer advantages, with specific interventions improving accuracy on hard stages. The study also compares optimizer behavior across tasks and an external architecture (CIFAR‑10).

By Gongyue Zhang, Honghai Liu
arXiv Machine Learning
Aug 7

PoolBench: A Benchmark for Pooling Strategies in Concept Representation Evaluation for Decoder-Only LLMs

arXiv:2608. 05162v1 Announce Type: cross Abstract: Pooling is a consequential but under-examined design choice in decoder-only concept representation work: practitioners must collapse token-level hidden states into a passage-level vector, yet no shared protocol exists for comparing this choice across concepts, models, and tasks.

By Ayushi Agarwal