From Correlation to Cause: A Five-Stage Methodology for Feature Analysis in Transformer Language Models

• URL: http://arxiv.org/abs/2605.22462v1
• Date: Thu, 21 May 2026 13:25:16 GMT
• Title: From Correlation to Cause: A Five-Stage Methodology for Feature Analysis in Transformer Language Models
• Abstract summary: We propose a five-stage methodology for causal feature analysis in transformer language models.<n>We demonstrate it end-to-end on GPT-2 small performing the Indirect Object Identification (IOI) task.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a five-stage methodology for causal feature analysis in transformer language models (probe design, feature extraction, causal validation, robustness testing, and deployment integration) and demonstrate it end-to-end on GPT-2 small performing the Indirect Object Identification (IOI) task. Activation patching recovers the canonical IOI circuit (layer-9 head 9 alone gives recovery +1.02). A sparse autoencoder recovers per-name selective features with effect sizes of 30 to 50 activation units. Causal validation finds these features specifically but only partially causal: ablating fifteen of them leaves the model accurate on 98% of prompts. Two NLA-inspired evaluations strengthen this picture: the fifteen selective features explain only 31% of activation variance versus the SAE's 99.7%, and selectivity ratio anticorrelates with causal force (r = -0.56). Robustness testing under three distribution shifts finds that the circuit transfers cleanly but feature ablation effects degrade substantially, exposing a gap between detection robustness and causal robustness. A cost-based deployment evaluation (assumed $50/FN, $0.42/FP, 2% error rate) finds an optimal monitor configuration yielding $8.96 per 1000 queries against a $1000 baseline, a 99.1% saving. Optimal composition strategy varies with cost ratio and base rate. The conjunction of stages produces findings no single stage would.

Related papers

• TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models [3.7851234061033856]
  We propose TAP-Path, a task-adaptive compression framework that restructures a pretrained Virchow2 encoder rather than distilling it into a separate student.<n>Across three task-head optimization seeds, TAP-Path achieved $87.98 pm 0.067%$ test accuracy, $81.26 pm 0.49% balanced accuracy, and $82.38 pm 0.48%$ macro-F1 on a 32-class histopathology benchmark.<n>Results show that task-adaptive structural and token sparsification can improve the accuracy-efficiency trade-off of large pathology foundation models.
  arXiv  Detail & Related papers  (2026-09-03T16:43:36Z)
• When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL [10.399451281089318]
  We study PPO-trained agents using MiniGrid as core evaluation and MuJoCo as boundary stress test.<n>Our audit finds two dominant one-shot failure modes -- reward flooding and semantic/API misunderstanding.<n>We propose diagnostic-driven iterative refinement, where training diagnostics and a failure-mode taxonomy guide targeted reward-function revision.
  arXiv  Detail & Related papers  (2026-05-27T17:57:43Z)
• Reading Task Failure Off the Activations: A Sparse-Feature Audit of GPT-2 Small on Indirect Object Identification [0.0]
  We report a small, reproducible audit of sparse-autoencoder (SAE) features of GPT-2 small fire differently on failed versus successful trials.<n>On 300 prompts, GPT-2 small reaches 79.7% accuracy; 146 of the 24,576 features in the layer-8 residual-stream SAE release of Bloom (2024) clear a Holm-corrected significance threshold.<n>The strongest single correlate of failure -- feature 17,491, d=+2.93, Neuronpedia label 'cryptographic keys' -- is essentially silent except when the prompt's transferred object is 'the keys'
  arXiv  Detail & Related papers  (2026-05-21T16:55:27Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• Adaptive Consensus in LLM Ensembles via Sequential Evidence Accumulation: Automatic Budget Identification and Calibrated Commit Signals [0.0]
  DASE produces a commit-type routing partition that generalises across benchmarks.<n> Adaptive stopping, not injection bandwidth, drives accuracy.<n>Injection-based methods exhibit an inverted-U accuracy-vs-inference trajectory.
  arXiv  Detail & Related papers  (2026-05-05T19:24:10Z)
• One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness [12.183451602438753]
  We show that simple lexical constraints (banning a single punctuation character or common word) cause instruction-tuned LLMs to collapse their responses.<n>We show that base models show no systematic collapse under identical constraints, with effects that are small, noisy, and bidirectional.
  arXiv  Detail & Related papers  (2026-04-14T17:40:01Z)
• Evaluating Small Language Models for Front-Door Routing: A Harmonized Benchmark and Synthetic-Traffic Experiment [0.05586191108738562]
  Small language models (SLMs) have sufficient reasoning capability for sub-second, zero-marginal-cost, self-hosted task classification.<n>Study 1 is a harmonized offline benchmark of Phi-3.5-mini, Qwen2.5-1.5B, and Qwen-2.5-3B on identical Azure T4 hardware, serving stack, quantization, and a fixed 60-case corpus.<n>Study 2 is a pre-registered four-arm randomized experiment under synthetic traffic with an effective sample size of 60 unique cases per arm.
  arXiv  Detail & Related papers  (2026-03-26T15:57:46Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Scalable Multi-Task Low-Rank Model Adaptation [43.22544779625565]
  Scaling multi-task low-rank adaptation (LoRA) to a large number of tasks induces catastrophic performance degradation.<n>We find that existing solutions, like regularization and dynamic routing, fail at scale because they are constrained by a fundamental trade-off.<n>We propose mtLoRA, a scalable solution with three novel designs.
  arXiv  Detail & Related papers  (2026-03-02T06:57:11Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks [49.0793012627959]
  We present VAPO, a novel framework tailored for reasoning models within the value-based paradigm.<n>VAPO attains a state-of-the-art score of $mathbf60.4$.<n>In direct comparison under identical experimental settings, VAPO outperforms the previously reported results of DeepSeek-R1-Zero-Qwen-32B and DAPO by more than 10 points.
  arXiv  Detail & Related papers  (2025-04-07T14:21:11Z)
• Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection [52.716143424856185]
  We propose LiMA (Less input is More faithful for Attribution), which reformulates the attribution of important regions as an optimization problem for submodular subset selection.<n>LiMA identifies both the most and least important samples while ensuring an optimal attribution boundary that minimizes errors.<n>Our method also outperforms the greedy search in attribution efficiency, being 1.6 times faster.
  arXiv  Detail & Related papers  (2025-04-01T06:58:15Z)
• ERNIE-SPARSE: Learning Hierarchical Efficient Transformer Through Regularized Self-Attention [48.697458429460184]
  Two factors, information bottleneck sensitivity and inconsistency between different attention topologies, could affect the performance of the Sparse Transformer. This paper proposes a well-designed model named ERNIE-Sparse. It consists of two distinctive parts: (i) Hierarchical Sparse Transformer (HST) to sequentially unify local and global information, and (ii) Self-Attention Regularization (SAR) to minimize the distance for transformers with different attention topologies.
  arXiv  Detail & Related papers  (2022-03-23T08:47:01Z)

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.