Image de couverture de livre

CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sreedhar, Makesh Narsimhan, Rebedea, Traian, Ghosh, Shaona, Zeng, Jiaqi, Parisien, Christopher
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Unsupervised Extraction of Dialogue Policies from Conversations
par: Sreedhar, Makesh Narsimhan, et autres
Publié: (2024)

Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models
par: Sreedhar, Makesh Narsimhan, et autres
Publié: (2025)

Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
par: Ghosh, Shaona, et autres
Publié: (2025)

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

Towards Inference-time Category-wise Safety Steering for Large Language Models
par: Bhattacharjee, Amrita, et autres
Publié: (2024)

Training a General Purpose Automated Red Teaming Model
par: Padmakumar, Aishwarya, et autres
Publié: (2026)

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
par: Fujinuma, Yoshinari, et autres
Publié: (2026)

AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
par: Ghosh, Shaona, et autres
Publié: (2024)

"Înţelegi Româneşte?'' A Recipe for Romanian Vision-Language Models
par: Masala, Mihai, et autres
Publié: (2026)

Semi-Supervised Learning for Large Language Models Safety and Content Moderation
par: Dinuta, Eduard Stefan, et autres
Publié: (2025)

Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering
par: Negoita, Vlad, et autres
Publié: (2025)

Improving Legal Judgement Prediction in Romanian with Long Text Encoders
par: Masala, Mihai, et autres
Publié: (2024)

HelpSteer2: Open-source dataset for training top-performing reward models
par: Wang, Zhilin, et autres
Publié: (2024)

GIT-CXR: End-to-End Transformer for Chest X-Ray Report Generation
par: Sîrbu, Iustin, et autres
Publié: (2025)

What We Talk About When We Talk About LMs: Implicit Paradigm Shifts and the Ship of Language Models
par: Zhu, Shengqi, et autres
Publié: (2024)

SmellBench: Evaluating LLM Agents on Architectural Code Smell Repair
par: Dinu, Ion George, et autres
Publié: (2026)

Personalized Topic Selection Model for Topic-Grounded Dialogue
par: Fan, Shixuan, et autres
Publié: (2024)

SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs
par: Ghosh, Shaona, et autres
Publié: (2025)

Still "Talking About Large Language Models": Some Clarifications
par: Shanahan, Murray
Publié: (2024)

What if Red Can Talk? Dynamic Dialogue Generation Using Large Language Models
par: Nananukul, Navapat, et autres
Publié: (2024)

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis
par: Bennion, Jonathan, et autres
Publié: (2025)

MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification
par: Sirbu, Iustin, et autres
Publié: (2025)

Empathy by Design: Aligning Large Language Models for Healthcare Dialogue
par: Umucu, Emre, et autres
Publié: (2025)

What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices
par: Noels, Sander, et autres
Publié: (2025)

DocTalk: Scalable Graph-based Dialogue Synthesis for Enhancing LLM Conversational Capabilities
par: Lee, Jing Yang, et autres
Publié: (2025)

Industry-Aligned Granular Topic Modeling
par: Moon, Sae Young, et autres
Publié: (2026)

BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses
par: Zeng, Weihao, et autres
Publié: (2024)

AbsenceBench: Language Models Can't Tell What's Missing
par: Fu, Harvey Yiyun, et autres
Publié: (2025)

Aligning Dialogue Agents with Global Feedback via Large Language Model Multimodal Reward Decomposition
par: Lee, Dong Won, et autres
Publié: (2025)

OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs
par: Masala, Mihai, et autres
Publié: (2024)

An Unsupervised Dialogue Topic Segmentation Model Based on Utterance Rewriting
par: Hou, Xia, et autres
Publié: (2024)

CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentation
par: Sun, Sijin, et autres
Publié: (2026)

What Don't You Understand? Using Large Language Models to Identify and Characterize Student Misconceptions About Challenging Topics
par: Parker, Michael J., et autres
Publié: (2026)

"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models
par: Halevy, Karina, et autres
Publié: (2024)

Unsupervised Mutual Learning of Discourse Parsing and Topic Segmentation in Dialogue
par: Xu, Jiahui, et autres
Publié: (2024)

What Are They Talking About? A Benchmark of Knowledge-Grounded Discussion Summarization
par: Zhou, Weixiao, et autres
Publié: (2025)

Addressing Topic Granularity and Hallucination in Large Language Models for Topic Modelling
par: Mu, Yida, et autres
Publié: (2024)

Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue
par: Bhagtani, Kratika, et autres
Publié: (2026)

Def-DTS: Deductive Reasoning for Open-domain Dialogue Topic Segmentation
par: Lee, Seungmin, et autres
Publié: (2025)

We Need to Talk About Classification Evaluation Metrics in NLP
par: Vickers, Peter, et autres
Publié: (2024)