Buchumschlag

Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wang, Xinpeng, Hu, Chengzhi, Ma, Bolei, Röttger, Paul, Plank, Barbara
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
von: Wang, Xinpeng, et al.
Veröffentlicht: (2024)

Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation
von: Wang, Xinpeng, et al.
Veröffentlicht: (2024)

Large Language Models Are Not Robust Multiple Choice Selectors
von: Zheng, Chujie, et al.
Veröffentlicht: (2023)

Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
von: Wang, Xinpeng, et al.
Veröffentlicht: (2025)

Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior
von: Si, Shengyun, et al.
Veröffentlicht: (2025)

The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models
von: Ma, Bolei, et al.
Veröffentlicht: (2024)

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
von: Hammoud, Hasan Abed Al Kader, et al.
Veröffentlicht: (2025)

Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors
von: Xue, Mengge, et al.
Veröffentlicht: (2024)

Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning
von: Mondorf, Philipp, et al.
Veröffentlicht: (2024)

Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey
von: Mondorf, Philipp, et al.
Veröffentlicht: (2024)

Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study
von: Ma, Bolei, et al.
Veröffentlicht: (2024)

CoDAR: Continuous Diffusion Language Models are More Powerful Than You Think
von: Shen, Junzhe, et al.
Veröffentlicht: (2026)

A Closer Look at the Limitations of Instruction Tuning
von: Ghosh, Sreyan, et al.
Veröffentlicht: (2024)

Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
von: Röttger, Paul, et al.
Veröffentlicht: (2024)

Towards Robust Instruction Tuning on Multimodal Large Language Models
von: Han, Wei, et al.
Veröffentlicht: (2024)

Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ
von: Holtermann, Carolin, et al.
Veröffentlicht: (2024)

The Pluralistic Moral Gap: Understanding Judgment and Value Differences between Humans and Large Language Models
von: Russo, Giuseppe, et al.
Veröffentlicht: (2025)

LogicSkills: A Structured Benchmark for Formal Reasoning in Large Language Models
von: Rabern, Brian, et al.
Veröffentlicht: (2026)

SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety
von: Röttger, Paul, et al.
Veröffentlicht: (2024)

DELIA: Diversity-Enhanced Learning for Instruction Adaptation in Large Language Models
von: Zeng, Yuanhao, et al.
Veröffentlicht: (2024)

Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrong
von: Fu, Tairan, et al.
Veröffentlicht: (2025)

Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFT
von: Liu, Yesheng, et al.
Veröffentlicht: (2025)

Neuro-RIT: Neuron-Guided Instruction Tuning for Robust Retrieval-Augmented Language Model
von: Kim, Jaemin, et al.
Veröffentlicht: (2026)

Look Before You Leap: Problem Elaboration Prompting Improves Mathematical Reasoning in Large Language Models
von: Liao, Haoran, et al.
Veröffentlicht: (2024)

Leveraging Unstructured Text Data for Federated Instruction Tuning of Large Language Models
von: Ye, Rui, et al.
Veröffentlicht: (2024)

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
von: Liu, Chengzhi, et al.
Veröffentlicht: (2025)

Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
von: Zhong, Chengzhi, et al.
Veröffentlicht: (2024)

A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification
von: Fatemi, Sorouralsadat, et al.
Veröffentlicht: (2024)

CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics
von: Yin, Kai, et al.
Veröffentlicht: (2024)

Controllable Text Generation in the Instruction-Tuning Era
von: Ashok, Dhananjay, et al.
Veröffentlicht: (2024)

Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models
von: Huang, Yuheng, et al.
Veröffentlicht: (2023)

The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It
von: Bertolazzi, Leonardo, et al.
Veröffentlicht: (2025)

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
von: Xu, Jiashu, et al.
Veröffentlicht: (2023)

Not All Documents Are What You Need for Extracting Instruction Tuning Data
von: Zhang, Chi, et al.
Veröffentlicht: (2025)

Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation
von: Baumann, Joachim, et al.
Veröffentlicht: (2025)

Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
von: Bianchi, Federico, et al.
Veröffentlicht: (2023)

Instruction Tuning for Large Language Models: A Survey
von: Zhang, Shengyu, et al.
Veröffentlicht: (2023)

ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
von: Qin, Yang, et al.
Veröffentlicht: (2024)

Choices Speak Louder than Questions
von: Cho, Gyeongje, et al.
Veröffentlicht: (2025)

Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options
von: Góral, Gracjan, et al.
Veröffentlicht: (2024)