LLMs fail to capture embodied cognition and cultural variation in demonstrative use, unlike humans who show language-specific proximal-distal and perspective-taking patterns.
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Recent advancements in the Generative Reward Model (GRM) have demonstrated its potential to enhance the reasoning abilities of LLMs through Chain-of-Thought (CoT) prompting. Despite these gains, existing implementations of GRM suffer from two critical limitations. First, CoT prompting is applied indiscriminately to all inputs regardless of their inherent complexity. This introduces unnecessary computational costs for tasks amenable to fast, direct inference. Second, existing approaches primarily rely on voting-based mechanisms to evaluate CoT outputs, which often lack granularity and precision in assessing reasoning quality. In this paper, we propose E-GRM, an efficient generative reward modeling framework grounded in model-internal uncertainty. E-GRM leverages the convergence behavior of parallel model generations to estimate uncertainty and selectively trigger CoT reasoning only when needed, without relying on handcrafted features or task-dependent signals. To improve reward fidelity, we introduce a lightweight discriminative scorer trained with a hybrid regression--ranking objective to provide fine-grained evaluation of reasoning paths. Experiments on multiple reasoning benchmarks show that E-GRM substantially reduces inference cost while consistently improving answer accuracy, demonstrating that model-internal uncertainty is an effective and general signal for efficient reasoning-aware reward modeling.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 4years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Supervised fine-tuning of LLMs often fails to fully internalize all training instances due to five recurring causes including missing prerequisites and data conflicts, as diagnosed via a new framework across multiple models.
STRIDE-ED improves empathetic dialogue by modeling it as strategy-conditioned multi-stage reasoning supported by refined training data and multi-objective RL.
The paper claims a selective fine-tuning method that identifies and freezes core parameters to mitigate catastrophic forgetting in LLMs while improving domain adaptation, shown in experiments with GPT-J and LLaMA-3.
citing papers explorer
-
Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives
LLMs fail to capture embodied cognition and cultural variation in demonstrative use, unlike humans who show language-specific proximal-distal and perspective-taking patterns.
-
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models
Supervised fine-tuning of LLMs often fails to fully internalize all training instances due to five recurring causes including missing prerequisites and data conflicts, as diagnosed via a new framework across multiple models.
-
STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems
STRIDE-ED improves empathetic dialogue by modeling it as strategy-conditioned multi-stage reasoning supported by refined training data and multi-objective RL.
-
Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization
The paper claims a selective fine-tuning method that identifies and freezes core parameters to mitigate catastrophic forgetting in LLMs while improving domain adaptation, shown in experiments with GPT-J and LLaMA-3.