Cover Image

Language steering in latent space to mitigate unintended code-switching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Goncharov, Andrey, Kondusov, Nikolai, Zaytsev, Alexey
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When an LLM is apprehensive about its answers -- and when its uncertainty is justified
by: Sychev, Petr, et al.
Published: (2025)

Complexity-aware fine-tuning
by: Goncharov, Andrey, et al.
Published: (2025)

Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting
by: Proskura, Polina, et al.
Published: (2024)

MedSyn: LLM-based Synthetic Medical Text Generation Framework
by: Kumichev, Gleb, et al.
Published: (2024)

ALIEN: Aligned Entropy Head for Improving Uncertainty Estimation of LLMs
by: Zabolotnyi, Artem, et al.
Published: (2025)

AtteSTNet -- An attention and subword tokenization based approach for code-switched text hate speech detection
by: Shingi, Geet, et al.
Published: (2021)

Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair
by: Borisov, Maksim, et al.
Published: (2025)

Toward universal steering and monitoring of AI models
by: Beaglehole, Daniel, et al.
Published: (2025)

Enhancing the Reliability of Medical AI through Expert-guided Uncertainty Modeling
by: Khalin, Aleksei, et al.
Published: (2026)

A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering
by: Scalena, Daniel, et al.
Published: (2024)

The evaluation of a code-switched Sepedi-English automatic speech recognition system
by: Phaladi, Amanda, et al.
Published: (2024)

Can sparse autoencoders be used to decompose and interpret steering vectors?
by: Mayne, Harry, et al.
Published: (2024)

Holistic Uncertainty Estimation For Open-Set Recognition
by: Erlygin, Leonid, et al.
Published: (2024)

Can SAEs reveal and mitigate racial biases of LLMs in healthcare?
by: Ahsan, Hiba, et al.
Published: (2025)

Efficient semantic uncertainty quantification in language models via diversity-steered sampling
by: Park, Ji Won, et al.
Published: (2025)

Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
by: Li, Pengyi, et al.
Published: (2025)

Label Attention Network for Temporal Sets Prediction: You Were Looking at a Wrong Self-Attention
by: Kovtun, Elizaveta, et al.
Published: (2023)

Uniting contrastive and generative learning for event sequences models
by: Yugay, Aleksandr, et al.
Published: (2024)

Your Transformer is Secretly Linear
by: Razzhigaev, Anton, et al.
Published: (2024)

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning
by: Rukhovich, Alexey, et al.
Published: (2025)

Learn Your Reference Model for Real Good Alignment
by: Gorbatovski, Alexey, et al.
Published: (2024)

Uncertainty Estimation for the Open-Set Text Classification systems
by: Erlygin, Leonid, et al.
Published: (2026)

Foundation for unbiased cross-validation of spatio-temporal models for species distribution modeling
by: Koldasbayeva, Diana, et al.
Published: (2025)

Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones
by: Zhmoginov, Andrey, et al.
Published: (2025)

Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts
by: Koishekenov, Yeskendir, et al.
Published: (2025)

A comparison of latent semantic analysis and correspondence analysis of document-term matrices
by: Qi, Qianqian, et al.
Published: (2021)

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

On Creating an English-Thai Code-switched Machine Translation in Medical Domain
by: Pengpun, Parinthapat, et al.
Published: (2024)

Parameter-Efficient Neural CDEs via Implicit Function Jacobians
by: Kuleshov, Ilya, et al.
Published: (2025)

ESQA: Event Sequences Question Answering
by: Abdullaeva, Irina, et al.
Published: (2024)

Contextually Guided Transformers via Low-Rank Adaptation
by: Zhmoginov, Andrey, et al.
Published: (2025)

Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities
by: Li, Pengyi, et al.
Published: (2026)

Where is the signal in tokenization space?
by: Geh, Renato Lui, et al.
Published: (2024)

C-ing Clearly: Enhanced Binary Code Explanations using C code
by: Poncu, Teodor, et al.
Published: (2025)

Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency
by: Goel, Aman, et al.
Published: (2025)

Linear probes rely on textual evidence: Results from leakage mitigation studies in language models
by: Boxo, Gerard, et al.
Published: (2025)

Logit-KL Flow Matching: Non-Autoregressive Text Generation via Sampling-Hybrid Inference
by: Sevriugov, Egor, et al.
Published: (2024)

RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression
by: Behnam, Payman, et al.
Published: (2025)

The Unreasonable Ineffectiveness of the Deeper Layers
by: Gromov, Andrey, et al.
Published: (2024)

code_transformed: The Influence of Large Language Models on Code
by: Xu, Yuliang, et al.
Published: (2025)