Cover Image

Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Yanbei, Keleg, Amr, Diandaru, Ryandito, Lau, Jey Han, Frermann, Lea, Fang, Biaoyan, Koto, Fajri
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

WHoW: A Cross-domain Approach for Analysing Conversation Moderation
by: Chen, Ming-Bin, et al.
Published: (2024)

CIG: Measuring Conversational Information Gain in Deliberative Dialogues with Semantic Memory Dynamics
by: Chen, Ming-Bin, et al.
Published: (2026)

Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in Indonesia
by: Koto, Fajri
Published: (2024)

LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones?
by: Keleg, Amr
Published: (2025)

Moderation Matters:Measuring Conversational Moderation Impact in English as a Second Language Group Discussion
by: Gao, Rena, et al.
Published: (2025)

KALE: An Artwork Image Captioning System Augmented with Heterogeneous Graph
by: Jiang, Yanbei, et al.
Published: (2024)

PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning
by: Jiang, Yanbei, et al.
Published: (2025)

Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations
by: Irawan, Patrick Amadeus, et al.
Published: (2025)

Could We Have Had Better Multilingual LLMs If English Was Not the Central Language?
by: Diandaru, Ryandito, et al.
Published: (2024)

Estimating the Level of Dialectness Predicts Interannotator Agreement in Multi-dialect Arabic Datasets
by: Keleg, Amr, et al.
Published: (2024)

Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task
by: Jiang, Yanbei, et al.
Published: (2025)

Connecting the Dots in News Analysis: Bridging the Cross-Disciplinary Disparities in Media Bias and Framing
by: Vallejo, Gisela, et al.
Published: (2023)

AMIR-GRPO: Inducing Implicit Preference Signals into GRPO
by: Yari, Amir Hossein, et al.
Published: (2026)

Unveiling Cultural Blind Spots: Analyzing the Limitations of mLLMs in Procedural Text Comprehension
by: Yari, Amir Hossein, et al.
Published: (2025)

Revisiting Common Assumptions about Arabic Dialects in NLP
by: Keleg, Amr, et al.
Published: (2025)

Parallel Tokenizers: Rethinking Vocabulary Design for Cross-Lingual Transfer
by: Kautsar, Muhammad Dehan Al, et al.
Published: (2025)

Narrative Media Framing in Political Discourse
by: Otmakhova, Yulia, et al.
Published: (2025)

Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages
by: Yari, Amir Hossein, et al.
Published: (2025)

Möbius-topological auxiliary function for $f$ electrons
by: Hu, Biaoyan
Published: (2025)

IndoBias: A Dual Track Culturally Grounded Benchmark for LLMs Bias Evaluation in Indonesian Languages
by: Hanif, Ikhlasul Akmal, et al.
Published: (2026)

Low-Resource Safety Failures Are Action Failures, Not Representation Failures
by: Aziz, Rashad, et al.
Published: (2026)

Reasoning Like Experts: Leveraging Multimodal Large Language Models for Drawing-based Psychoanalysis
by: Ma, Xueqi, et al.
Published: (2025)

Who Wrote the Book? Detecting and Attributing LLM Ghostwriters
by: Shetty, Anudeex, et al.
Published: (2026)

Automated Business Process Analysis: An LLM-Based Approach to Value Assessment
by: De Michele, William, et al.
Published: (2025)

Place Matters: Comparing LLM Hallucination Rates for Place-Based Legal Queries
by: Curran, Damian, et al.
Published: (2025)

Simulating LLM-to-LLM Tutoring for Multilingual Math Feedback
by: Tonga, Junior Cedric, et al.
Published: (2025)

Culturally-Nuanced Story Generation for Reasoning in Low-Resource Languages: The Case of Javanese and Sundanese
by: Pranida, Salsabila Zahirah, et al.
Published: (2025)

IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces
by: Koto, Fajri, et al.
Published: (2024)

Listen, Correct, and Feed Back: Spoken Pedagogical Feedback Generation
by: Liang, Junhong, et al.
Published: (2026)

Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models
by: Mekky, Ali, et al.
Published: (2026)

Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation
by: Hidayat, Naila Shafirni, et al.
Published: (2025)

A Critical Look at Meta-evaluating Summarisation Evaluation Metrics
by: Dai, Xiang, et al.
Published: (2024)

Factual Dialogue Summarization via Learning from Large Language Models
by: Zhu, Rongxin, et al.
Published: (2024)

CMA-R:Causal Mediation Analysis for Explaining Rumour Detection
by: Tian, Lin, et al.
Published: (2024)

MoDEM: Mixture of Domain Expert Models
by: Simonds, Toby, et al.
Published: (2024)

Interaction Matters: An Evaluation Framework for Interactive Dialogue Assessment on English Second Language Conversations
by: Gao, Rena, et al.
Published: (2024)

Evaluating Evidence Attribution in Generated Fact Checking Explanations
by: Xing, Rui, et al.
Published: (2024)

REL: Working out is all you need
by: Simonds, Toby, et al.
Published: (2024)

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
by: Shetty, Anudeex, et al.
Published: (2024)

Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
by: Gao, Shengxiang, et al.
Published: (2025)