conftrace_

model faithfulness

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

sample-based explanation (1) hessian-free method (1) rationale generator (1) unsupervised selective rationalization (1) layer-level sparsity (1) reasoning faithfulness (1) faithfulness analysis (1) reasoning analysis (1) reasoning distillation (1) semantic evaluation (1)

Papers

Beyond Neuron-Level Sparsity: Achieving Faithful and Interpretable LLMs with Mixture of Decoders AAAI 2026 Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? EMNLP 2025 Unsupervised Selective Rationalization with Noise Injection ACL 2023 On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation ACL 2021