Cover Image

Interpreting Language Reward Models via Contrastive Explanations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Junqi, Bewley, Tom, Mishra, Saumitra, Lecue, Freddy, Veloso, Manuela
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
by: Hedström, Anna, et al.
Published: (2025)

Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions
by: Kariyappa, Sanjay, et al.
Published: (2024)

ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values
by: Bewley, Tom, et al.
Published: (2026)

Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift
by: Amoukou, Salim I., et al.
Published: (2026)

Sequential Harmful Shift Detection Without Labels
by: Amoukou, Salim I., et al.
Published: (2024)

Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs
by: Hamman, Faisal, et al.
Published: (2024)

The Effect of Data Poisoning on Counterfactual Explanations
by: Artelt, André, et al.
Published: (2024)

Counterfactual Metarules for Local and Global Recourse
by: Bewley, Tom, et al.
Published: (2024)

Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
by: Hamman, Faisal, et al.
Published: (2023)

Interval Abstractions for Robust Counterfactual Explanations
by: Jiang, Junqi, et al.
Published: (2024)

Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation
by: Jiang, Junqi, et al.
Published: (2023)

CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling
by: Liu, Dengcan, et al.
Published: (2026)

Robust Counterfactual Explanations in Machine Learning: A Survey
by: Jiang, Junqi, et al.
Published: (2024)

RobustX: Robust Counterfactual Explanations Made Easy
by: Jiang, Junqi, et al.
Published: (2025)

Zero-Shot Reinforcement Learning from Low Quality Data
by: Jeen, Scott, et al.
Published: (2023)

Zero-Shot Reinforcement Learning Under Partial Observability
by: Jeen, Scott, et al.
Published: (2025)

Representation Consistency for Accurate and Coherent LLM Answer Aggregation
by: Jiang, Junqi, et al.
Published: (2025)

A Visual Tool for Interactive Model Explanation using Sensitivity Analysis
by: Schuler, Manuela
Published: (2025)

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
by: Bui, Ngoc, et al.
Published: (2025)

KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking
by: Zhang, Jiawei, et al.
Published: (2024)

The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
by: Hsu, Hsiang, et al.
Published: (2026)

Interpreting Inflammation Prediction Model via Tag-based Cohort Explanation
by: Meng, Fanyu, et al.
Published: (2024)

CELL your Model: Contrastive Explanations for Large Language Models
by: Luss, Ronny, et al.
Published: (2024)

IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
by: Beigi, Mohammad, et al.
Published: (2026)

Recourse under Model Multiplicity via Argumentative Ensembling (Technical Report)
by: Jiang, Junqi, et al.
Published: (2023)

LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations
by: Wang, Qianli, et al.
Published: (2024)

Causality-Aware Local Interpretable Model-Agnostic Explanations
by: Cinquini, Martina, et al.
Published: (2022)

Explanation-Guided Adversarial Training for Robust and Interpretable Models
by: Chen, Chao, et al.
Published: (2026)

Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
by: Canizales, Ronaldo, et al.
Published: (2026)

Learning Mathematical Rules with Large Language Models
by: Gorceix, Antoine, et al.
Published: (2024)

Who Judges the Judge? LLM Jury-on-Demand: Building Trustworthy LLM Evaluation Systems
by: Li, Xiaochuan, et al.
Published: (2025)

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
by: Wang, Chaoqi, et al.
Published: (2025)

Efficient Process Reward Modeling via Contrastive Mutual Information
by: Lee, Nakyung, et al.
Published: (2026)

Global Concept Explanations for Graphs by Contrastive Learning
by: Teufel, Jonas, et al.
Published: (2024)

Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes
by: Maghsoudi, Maryam, et al.
Published: (2026)

reward-lens: A Mechanistic Interpretability Library for Reward Models
by: Nadaf, Mohammed Suhail B
Published: (2026)

Are Logistic Models Really Interpretable?
by: Dervovic, Danial, et al.
Published: (2024)

Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
by: Zhang, Feng, et al.
Published: (2026)

TACENR: Task-Agnostic Contrastive Explanations for Node Representations
by: Papanikou, Vasiliki, et al.
Published: (2026)

Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability
by: Yan, Ge, et al.
Published: (2025)