Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces

• URL: http://arxiv.org/abs/2605.12809v1
• Date: Tue, 12 May 2026 23:01:29 GMT
• Title: Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
• Abstract summary: We introduce a flexible framework that infers token-level influence through a latent mediation approach for general prediction tasks.<n>Unlike prior methods where influence decomposes additively across tokens, influence computed over latent features is inherently non-decomposable.<n>Our framework enhances trust and enables model auditing, generalizing to high-stakes domain requiring transparent and accountable decisions.
• Score: 9.24259308424615
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: A critical step for reliable large language models (LLMs) use in healthcare is to attribute predictions to their training data, akin to a medical case study. This requires token-level precision: pinpointing not just which training examples influence a decision, but which tokens within them are responsible. While influence functions offer a principled framework for this, prior work is restricted to autoregressive settings and relies on an implicit assumption of token independence, rendering their identified influences unreliable. We introduce a flexible framework that infers token-level influence through a latent mediation approach for general prediction tasks. Our method attaches sparse autoencoders to any layer of a pretrained LLM to learn a basis of approximately independent latent features. Unlike prior methods where influence decomposes additively across tokens, influence computed over latent features is inherently non-decomposable. To address this, we introduce a novel method using Jacobian-vector products. Token-level influence is obtained by propagating latent attributions back to the input space via token activation patterns. We scale our approach using efficient inverse-Hessian approximations. Experiments on medical benchmarks show our approach identifies sparse, interpretable sets of tokens that jointly influence predictions. Our framework enhances trust and enables model auditing, generalizing to high-stakes domain requiring transparent and accountable decisions.

Related papers

• Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift [26.752668789722765]
  Token-Level Off-Policy Labeling (TOPL) is an off-policy training paradigm that reframes post-training as a token-level correctness prediction task.<n>We show TOPL achieves strong out-of-distribution generalization across 11 datasets against a diverse set of sequence-level and token-level baselines.
  arXiv  Detail & Related papers  (2026-07-20T03:57:22Z)
• Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models [53.15468578562038]
  We propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for Multimodal Large Language Models (MLLMs)<n>We first quantify the uncertainty from the model's failure to ground token predictions in the given image.<n>We then encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples.
  arXiv  Detail & Related papers  (2026-05-06T13:08:12Z)
• Support Tokens, Stability Margins, and a New Foundation for Robust LLMs [1.429795922604976]
  We re-interpret causal self-attention transformers, the backbone of modern foundation models.<n>A barrier constraint emerges on the self-attention parameters.<n>This reveals a boundary where attention becomes ill-conditioned.
  arXiv  Detail & Related papers  (2026-02-25T08:44:44Z)
• Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution [11.387100835483672]
  Training Data Attribution (TDA) methods identify which training data drive specific behaviors, particularly unintended ones.<n>Existing approaches like influence functions are both computationally expensive and attribute based on single test examples.<n>We leverage interpretable structures within the model during the attribution.<n>We show that incorporating interpretable structure within traditional TDA pipelines can enable more scalable, explainable, and better control of model behavior through data.
  arXiv  Detail & Related papers  (2026-02-16T16:02:09Z)
• TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior [30.782240245074433]
  Tokenizers provide the fundamental basis through which text is represented and processed by language models (LMs)<n>TokSuite is a collection of models and a benchmark that supports research into tokenization's influence on LMs.
  arXiv  Detail & Related papers  (2025-12-23T20:43:06Z)
• ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning [51.133569963553576]
  ssToken is a Self-modulated and Semantic-aware Token Selection approach.<n>We show that both self-modulated selection and semantic-aware selection alone outperform full-data fine-tuning.
  arXiv  Detail & Related papers  (2025-10-21T03:21:04Z)
• Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization [56.083511902353365]
  Reinforcement learning (RL) typically applies uniform credit across an entire generation of Large language models.<n>This work positions attention as a privileged substrate that renders the internal logic of LLMs as a mechanistic blueprint of reasoning itself.<n>We introduce three novel RL strategies that dynamically perform targeted credit assignment to critical nodes.
  arXiv  Detail & Related papers  (2025-10-15T13:49:51Z)
• Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models [16.540220733551823]
  Large Vision-Language Models (VLMs) enable strong multimodal reasoning but incur heavy inference costs from redundant visual tokens.<n> Attention-based methods rely on raw attention scores, which are often unstable across layers and heads.<n>We propose ours, a training-free framework built on a simple intuition.
  arXiv  Detail & Related papers  (2025-09-29T14:20:05Z)
• I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data? [76.15163242945813]
  Large language models (LLMs) have led many to conclude that they exhibit a form of intelligence.<n>We introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables.
  arXiv  Detail & Related papers  (2025-03-12T01:21:17Z)
• Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability [53.51560766150442]
  Critical tokens are elements within reasoning trajectories that significantly influence incorrect outcomes.<n>We present a novel framework for identifying these tokens through rollout sampling.<n>We show that identifying and replacing critical tokens significantly improves model accuracy.
  arXiv  Detail & Related papers  (2024-11-29T18:58:22Z)
• Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions [55.660255727031725]
  Influence functions explain the decisions of a model by identifying influential training examples. We conduct a comparison between influence functions and common word-saliency methods on representative tasks. We develop a new measure based on influence functions that can reveal artifacts in training data.
  arXiv  Detail & Related papers  (2020-05-14T00:45:23Z)
• Self-Attention Attribution: Interpreting Information Interactions Inside Transformer [89.21584915290319]
  We propose a self-attention attribution method to interpret the information interactions inside Transformer. We show that the attribution results can be used as adversarial patterns to implement non-targeted attacks towards BERT.
  arXiv  Detail & Related papers  (2020-04-23T14:58:22Z)

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.