Copertina

No Need for Explanations: LLMs can implicitly learn from mistakes in-context

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Alazraki, Lisa, Mozes, Maximilian, Campos, Jon Ander, Yi-Chern, Tan, Rei, Marek, Bartolo, Max
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Reverse Engineering Human Preferences with Reinforcement Learning
di: Alazraki, Lisa, et al.
Pubblicazione: (2025)

Meta-Reasoning Improves Tool Use in Large Language Models
di: Alazraki, Lisa, et al.
Pubblicazione: (2024)

Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study
di: Agrawal, Aryan, et al.
Pubblicazione: (2025)

Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate
di: Chern, Steffi, et al.
Pubblicazione: (2024)

StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking
di: Rozanov, Nikolai, et al.
Pubblicazione: (2024)

Fine-tuning with RAG for Improving LLM Learning of New Skills
di: Ibrahim, Humaid, et al.
Pubblicazione: (2025)

Scaling Small Agents Through Strategy Auctions
di: Alazraki, Lisa, et al.
Pubblicazione: (2026)

An Empathetic AI Coach for Self-Attachment Therapy
di: Alazraki, Lisa, et al.
Pubblicazione: (2022)

Factors affecting the in-context learning abilities of LLMs for dialogue state tracking
di: Hegde, Pradyoth, et al.
Pubblicazione: (2025)

Improving the OOD Performance of Closed-Source LLMs on NLI Through Strategic Data Selection
di: Stacey, Joe, et al.
Pubblicazione: (2025)

Learning is Forgetting: LLM Training As Lossy Compression
di: Conklin, Henry C., et al.
Pubblicazione: (2026)

Halu-J: Critique-Based Hallucination Judge
di: Wang, Binjie, et al.
Pubblicazione: (2024)

Long-context LLMs Struggle with Long In-context Learning
di: Li, Tianle, et al.
Pubblicazione: (2024)

Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs
di: Fragkathoulas, Christos, et al.
Pubblicazione: (2024)

Can LLMs Generate Good Stories? Insights and Challenges from a Narrative Planning Perspective
di: Wang, Yi, et al.
Pubblicazione: (2025)

Concept-aware Data Construction Improves In-context Learning of Language Models
di: Štefánik, Michal, et al.
Pubblicazione: (2024)

A word association network methodology for evaluating implicit biases in LLMs compared to humans
di: Abramski, Katherine, et al.
Pubblicazione: (2025)

Humans can learn to detect AI-generated texts, or at least learn when they can't
di: Milička, Jiří, et al.
Pubblicazione: (2025)

Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque
di: Corral, Ander, et al.
Pubblicazione: (2024)

LLMs can be easily Confused by Instructional Distractions
di: Hwang, Yerin, et al.
Pubblicazione: (2025)

Digital Socrates: Evaluating LLMs through Explanation Critiques
di: Gu, Yuling, et al.
Pubblicazione: (2023)

The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement
di: Kamp, Jonathan, et al.
Pubblicazione: (2024)

Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
di: Tan, Daniel, et al.
Pubblicazione: (2025)

Distilling Text Style Transfer With Self-Explanation From LLMs
di: Zhang, Chiyu, et al.
Pubblicazione: (2024)

How well can LLMs Grade Essays in Arabic?
di: Ghazawi, Rayed, et al.
Pubblicazione: (2025)

Prediction hubs are context-informed frequent tokens in LLMs
di: Nielsen, Beatrix M. G., et al.
Pubblicazione: (2025)

What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering
di: Maar, Jim, et al.
Pubblicazione: (2026)

Training Language Models with Language Feedback at Scale
di: Scheurer, Jérémy, et al.
Pubblicazione: (2023)

Understanding Likelihood Over-optimisation in Direct Alignment Algorithms
di: Shi, Zhengyan, et al.
Pubblicazione: (2024)

Combating Adversarial Attacks with Multi-Agent Debate
di: Chern, Steffi, et al.
Pubblicazione: (2024)

Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies
di: Kamp, Jonathan, et al.
Pubblicazione: (2025)

XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs
di: Chen, Zichen, et al.
Pubblicazione: (2023)

Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs
di: Rei, Ricardo, et al.
Pubblicazione: (2025)

LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought
di: Jiang, Zhuoxuan, et al.
Pubblicazione: (2024)

LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
di: Jiang, Ziyan, et al.
Pubblicazione: (2024)

Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks
di: Wang, Chonghua, et al.
Pubblicazione: (2024)

BeHonest: Benchmarking Honesty in Large Language Models
di: Chern, Steffi, et al.
Pubblicazione: (2024)

Is Depth All You Need? An Exploration of Iterative Reasoning in LLMs
di: Wu, Zongqian, et al.
Pubblicazione: (2025)

LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals
di: Toker, Gilat, et al.
Pubblicazione: (2026)

AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios
di: Alazraki, Lisa, et al.
Pubblicazione: (2025)