arXiv Computation and Language
User Feedback Provides a Unique Signal that LLMs Can not Detect
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
Hugging Face Trending Papers
Aug 26
From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations
Large language models (LLMs) frequently produce confident yet factually incorrect responses when user inputs contain misleading premises, a phenomenon we attribute to fact perturbations in the input....
arXiv AI
Aug 20
Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions
The paper introduces a fine-grained method called interactions to analyze prompt sensitivity in large language models (LLMs). By decomposing output scores into nonlinear interactions, the authors show that subtle prompt changes can destabilize these interactions even when overall outputs stay unchanged. They propose an Interaction-based Prompt Sensitivity (IPS) metric and use it to evaluate 50 open-source LLMs, finding that supervised fine‑tuning, larger model scales, dense architectures, and few‑shot learning all reduce prompt sensitivity, primarily by stabilizing low‑order interactions.
arXiv Computation and Language
Aug 27
From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations
The paper introduces DEDUCE, a three‑stage framework that turns large language models into proactive error correctors by detecting input fact errors, devising correction strategies, and delivering reliable answers. It also presents MisFactQA, a dataset of factual errors, and new metrics for robustness evaluation. Experiments on TruthfulQA, FalseQA, and MisFactQA show significant gains in accuracy and error correction across Qwen, LLaMA, and Gemma models.
arXiv Machine Learning
Aug 27
iFlip: Iterative Feedback-driven Counterfactual Example Refinement
iFlip is an iterative refinement method for generating counterfactual examples using large language models. It incorporates three feedback types—model confidence, feature attribution, and natural language—to guide successive edits. Experiments show iFlip outperforms five state‑of‑the‑art baselines, achieving a 57.8% higher validity rate and improving model performance through counterfactual data augmentation.
arXiv AI
Jul 1
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
arXiv:2606. 32029v1 Announce Type: cross Abstract: While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.
arXiv AI
Jul 10
Adaptive Generation of Bias-Eliciting Questions for LLMs
arXiv:2510. 12857v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions of users worldwide.