LiSeCo is a lightweight, gradient‑free method that controls language generation by directly intervening on the hidden activations of a token in embedding space. It uses control‑theoretic techniques to steer the generation trajectory away from undesired semantic regions and into a predefined allowed region, ensuring fine‑grained attribute control. The approach is computationally efficient, minimally impacts generation time, and is shown to be effective on tasks such as toxicity, sentiment, and bilingual language steering while preserving text quality.
By Emily Cheng, Carmen Amo Alonso
The paper introduces KESA, a knowledge‑enhanced approach for sentence‑level sentiment analysis that incorporates sentiment knowledge through two auxiliary tasks: sentiment word cloze and conditional sentiment prediction. These tasks use prior sentiment polarity to guide the selection of sentiment words and the prediction of overall sentiment, respectively, and explore label combination methods to unify multiple label types. Experiments show that KESA consistently outperforms pre‑trained models and complements existing knowledge‑enhanced post‑training methods.
By Qinghua Zhao, Shuai Ma, Shuo Ren
The paper introduces Retrieval-Augmented Decoding (RAD), a decoding-time method that improves the truthfulness of large language models without retraining. RAD uses a small reference set of up to ten annotated examples to build a grounding space of context embeddings and next-token logits, which it retrieves and aggregates during inference to shape the model’s output. Experiments on four open-ended generation benchmarks and four different LLMs show that RAD consistently outperforms strong baselines and generalizes well across tasks.
By Manh Nguyen, Sunil Gupta, Hung Le
arXiv:2606.18389v2 Announce Type: replace
Abstract: Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated dat...
By Jan Cegin, Daniil Gurgurov, Yusser Al Ghussin, Simon Ostermann
arXiv:2606. 08408v1 Announce Type: cross Abstract: We extend activation steering to diffusion language models (DLMs) and study a novel problem that arose due to the inference mechanism of DLMs: Modifying a text in-place to manifest a different concept.
By Ryandito Diandaru, Ikhlasul Akmal Hanif, Fadli Aulawi Al Ghiffari, Ahmed Elshabrawy, Alham Fikri Aji
arXiv:2607. 17524v1 Announce Type: cross Abstract: We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task.
By Zitong Huang, Gustavo Lucas Carvalho, Deqing Fu, Robin Jia