paper-with-me

홈 › Papers

Calibrate to Discriminate: Improve In-Context Learning with Label-Free Comparative Inference

2024-10-03 · Wei Cheng, Tianlu Wang, Yanmin Ji, Fan Yang, Keren Tan, Yiyu Zheng

While in-context learning with large language models (LLMs) has shown impressive performance, we have discovered a unique miscalibration behavior where both correct and incorrect predictions are assigned the same level of confidence. We refer to this phenomenon as indiscriminate miscalibration. We found that traditional calibration metrics, such as Expected Calibrated Errors (ECEs), are unable to capture this behavior effectively. To address this issue, we propose new metrics to measure the severity of indiscriminate miscalibration. Additionally, we develop a novel in-context comparative inference method to alleviate miscalibrations and improve classification performance. Through extensive experiments on five datasets, we demonstrate that our proposed method can achieve more accurate and calibrated predictions compared to regular zero-shot and few-shot prompting.

📄 PDF Abstract BibTeX arXiv:2410.02210

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context Learning

Similar Papers 제목 키워드 기반

Calibration without Ground Truth

2026-01-27 · Yuqing Kong, Mingyu Song, Yizhou Wang, Yifan Wu arxiv

Villalobos et al. [2024] predict that publicly available human text will be exhausted within the next decade. Thus, improving models without access to ground-truth labels becomes increasingly important. We propose a labe…

Calibrating LLM-Based Evaluator

2023-09-23 · Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang 외

Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to hum…

In-Context LearningLanguage ModelingLanguage ModellingText Generation

When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models

2026-09-04 · Gnaneswar Villuri, Hashmath Shaik, Alex Doboli arxiv

A 0.6B language model, asked to verify 1,200 logical conclusions (half valid, half corrupted by a single semantic edit), answers YES every time. Judged by behavior it discriminates nothing; linear probes on its hidden st…

Margin-calibrated Classifier Guidance for Property-driven Synthesis Planning

2026-05-13 · Najwa Laabid, Vikas Garg arxiv

Synthesis planning seeks an efficient sequence of chemical reactions that produce a target molecule. Typically, a pretrained single-step (autoregressive) retrosynthesis model is repeatedly invoked to generate such a sequ…

When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning

2026-07-08 · Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang, Hoang Anh Duy Le 외 arxiv

Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, widely used critic-free RL methods rely on uniform credit assignment, broadcas…

Reinforcement Learning