Tracing Logit Trajectories Across Layer Depth: Dataset-Level Explainability for Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Sentence-level explanations miss the bigger picture of how a black-box model behaves across data . a dataset-level analysis that traces the intermediate structure of decision formation is needed . |
| Approach: | They propose a method that aggregates logit updates into a reproducible dataset-level trajectory pattern. |
| Outcome: | The proposed model enables depth-wise explainability across 6 languages and 5 NLP tasks. |
Similar Papers
TRACE: Training and Inference-Time Interpretability Analysis for Language Models (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing tools for interpretability analysis of transformer models are post hoc, rely on scalar metrics or require nontrivial integration effort. |
| Approach: | They propose a modular toolkit for training and inference-time interpretability analysis of transformer models. |
| Outcome: | Experiments with autoregressive transformers show that TRACE reveals developmental phenomena overlooked by traditional scalar metrics such as loss or accuracy. |
Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing explainability methods for Large Language Models treat hidden states as static points in activation space, but they are saturated with polysemantic features. |
| Approach: | They propose a framework that shifts analysis from static activations to layer-wise geometric displacement. |
| Outcome: | The proposed framework outperforms existing explainability methods on commonsense reasoning, question answering, and toxicity detection benchmarks. |
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models generate tokens by updating high-dimensional representations and decoding from them at each timestep. |
| Approach: | They propose a framework that allows reasoning correction and length control based on derived ideal trajectories. |
| Outcome: | The proposed model can predict correctness and length control based on ideal trajectories. |
Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) excel in generating coherent texts, but their ability to comprehend the author’s thoughts remains uncertain. |
| Approach: | They conduct a comprehensive survey of narrative understanding tasks, examining their key features, definitions, taxonomy, associated datasets, evaluation metrics, and limitations. |
| Outcome: | The proposed framework could be extended to address novel narrative understanding tasks. |
Bridging Internal Consistency and External Alignment: A Causal and Dynamic Interpretability Framework for LLM Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing interpretability methods focus on internal and external aspects of the model . existing explanations often focus on surface correlations or static dependencies . |
| Approach: | They propose a causal and dynamic interpretability framework for Large Language Models . they characterize backdoor-adjusted causal effects of generated prefix and prompt . |
| Outcome: | The proposed framework provides a unified causal view of internal consistency and external alignment in LLM generation dynamics. |
A Survey of the State of Explainable AI for Natural Language Processing (2020.aacl-main)
Copied to clipboard
| Challenge: | Recent years have seen significant advances in the quality of state-of-the-art models, but they have come at the expense of models becoming less interpretable. |
| Approach: | This survey examines the current state of Explainable AI within the domain of NLP . they detail the operations and explainability techniques currently available for generating explanations for NLP models . |
| Outcome: | This survey examines the state of explainable AI (XAI) within the domain of natural language processing . it focuses on the operations and explainability techniques currently available for NLP models . |
FOL-Traces: Verified First-Order Logic Reasoning Traces at Scale (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches to evaluate language models fail to provide structural clarity and verifiable inference. |
| Approach: | They propose to use a large-scale dataset of programmatically verified reasoning traces to evaluate structured logical inference. |
| Outcome: | The proposed model achieves 45.7% accuracy on masked operation prediction and 27% on two-step completion. |
TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Evaluating large vision-language models has focused on final-answer correctness, but this metric is often insufficient and misleading. |
| Approach: | They propose a framework that decomposes complex multimodal tasks into Auxiliary Reasoning Sets (ARS) ARS decomposition reveals how consistently a model reasons across sub-questions with structured dependencies. |
| Outcome: | a new framework improves diagnostic evaluation of large vision-language models . it decomposes complex multimodal tasks into auxiliary reasoning sets with structured dependencies . the framework pinpoints reasoning failures and exposes errors overlooked by standard evaluation . |
Neuron-level Interpretation of Deep NLP Models: A Survey (2022.tacl-1)
Copied to clipboard
| Challenge: | Existing work on deep neural networks has focused on representation analysis, but recent work focused on analyzing neurons within these models. |
| Approach: | They propose to analyze neural networks to uncover linguistic concepts captured by the network . they propose to use a granular approach to analyze neurons within these models . |
| Outcome: | The proposed method combines methods to discover and understand neurons in a network with evaluation methods. |
RuleEdit: Towards Rule-Level Knowledge Generalization to Mitigate Over-Editing in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge editing methods focus on instance-level editing, which is prone to knowledge degradation and general ability deterioration due to redundant instance-specific modifications. |
| Approach: | They propose a rule-level editing method that generalizes rule-derived knowledge to update rule-based instances. |
| Outcome: | The proposed method improves portability and performance over baselines for LLaMA-2-7B on RULEmix. |