Image de couverture de livre

Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals unreliable Multi-Turn Behavior in LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lachenmaier, Clara, Bultmann, Hannah, Zarrieß, Sina
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions
par: Lachenmaier, Clara, et autres
Publié: (2025)

LLMs Struggle to Reject False Presuppositions when Misinformation Stakes are High
par: Sieker, Judith, et autres
Publié: (2025)

GerPS-Compare: Comparing NER methods for legal norm analysis
par: Bachinger, Sarah T., et autres
Publié: (2024)

SemCSE-Multi: Multifaceted and Decodable Embeddings for Aspect-Specific and Interpretable Scientific Domain Mapping
par: Brinner, Marc, et autres
Publié: (2025)

When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
par: Dongre, Vardhan, et autres
Publié: (2026)

Surprisal and Metaphor Novelty Judgments: Moderate Correlations and Divergent Scaling Effects Revealed by Corpus-Based and Synthetic Datasets
par: Momen, Omar, et autres
Publié: (2026)

Evaluating Students' Open-ended Written Responses with LLMs: Using the RAG Framework for GPT-3.5, GPT-4, Claude-3, and Mistral-Large
par: Jauhiainen, Jussi S., et autres
Publié: (2024)

You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments
par: Shu, Bangzhao, et autres
Publié: (2023)

Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs
par: Sinha, Aditya, et autres
Publié: (2026)

Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation
par: Liu, Geng, et autres
Publié: (2026)

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
par: Jaipersaud, Brandon, et autres
Publié: (2025)

KnowGPT: Knowledge Graph based Prompting for Large Language Models
par: Zhang, Qinggang, et autres
Publié: (2023)

MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs
par: Sirdeshmukh, Ved, et autres
Publié: (2025)

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning
par: Ning, Yansong, et autres
Publié: (2025)

Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method
par: Zhao, Yukun, et autres
Publié: (2023)

What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say "I Don't Know"
par: Lee, Joosung, et autres
Publié: (2026)

Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
par: Xu, Jun, et autres
Publié: (2025)

Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies
par: Varshney, Prasoon, et autres
Publié: (2025)

Do Large Language Models Know How Much They Know?
par: Prato, Gabriele, et autres
Publié: (2025)

The Chameleon Nature of LLMs: Quantifying Multi-Turn Stance Instability in Search-Enabled Language Models
par: Ratnakar, Shivam, et autres
Publié: (2025)

How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study
par: Sun, Moran, et autres
Publié: (2026)

Models That Know How Evaluations Are Designed Score Safer
par: Deckenbach, Katharina, et autres
Publié: (2026)

Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors
par: Wang, Jian, et autres
Publié: (2025)

Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty
par: Machcha, Sravanthi, et autres
Publié: (2026)

Mining for Species, Locations, Habitats, and Ecosystems from Scientific Papers in Invasion Biology: A Large-Scale Exploratory Study with Large Language Models
par: D'Souza, Jennifer, et autres
Publié: (2025)

MedMT-Bench: Can LLMs Memorize and Understand Long Multi-Turn Conversations in Medical Scenarios?
par: Yang, Lin, et autres
Publié: (2026)

What Do LLMs Know About Alzheimer's Disease? Multi-loss Fine-Tuning and Probing for AD Detection
par: Jiang, Lei, et autres
Publié: (2026)

Forget What You Know about LLMs Evaluations -- LLMs are Like a Chameleon
par: Cohen-Inger, Nurit, et autres
Publié: (2025)

NanoKnow: How to Know What Your Language Model Knows
par: Gu, Lingwei, et autres
Publié: (2026)

LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked
par: Phute, Mansi, et autres
Publié: (2023)

DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs
par: Mousavi, Seyed Mahed, et autres
Publié: (2024)

Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
par: Li, Yubo, et autres
Publié: (2025)

KnowRL: Teaching Language Models to Know What They Know
par: Kale, Sahil, et autres
Publié: (2025)

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
par: Fan, Siqi, et autres
Publié: (2025)

Self-Anchoring Calibration Drift in Large Language Models: How Multi-Turn Conversations Reshape Model Confidence
par: Harshavardhan
Publié: (2026)

How Hypocritical Is Your LLM judge? Listener-Speaker Asymmetries in the Pragmatic Competence of Large Language Models
par: Sieker, Judith, et autres
Publié: (2026)

Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction
par: Chen, Xingwu, et autres
Publié: (2026)

Measuring Reasoning Quality in LLMs: A Multi-Dimensional Behavioral Framework
par: Şenol, Ali, et autres
Publié: (2026)

Discourse Diversity in Multi-Turn Empathic Dialogue
par: Zhan, Hongli, et autres
Publié: (2026)

Adaptive Stopping for Multi-Turn LLM Reasoning
par: Zhou, Xiaofan, et autres
Publié: (2026)