English
Related papers

Related papers: Beyond Hidden-Layer Manipulation: Semantically-Awa…

200 papers

Logit Lens is a widely adopted method for mechanistic interpretability of transformer-based language models, enabling the analysis of how internal representations evolve across layers by projecting them into the output vocabulary space.…

Computer Vision and Pattern Recognition · Computer Science 2025-04-24 Ryota Takatsuki , Sonia Joseph , Ippei Fujisawa , Ryota Kanai

We present a new family of logit-Q dynamics for efficient learning in stochastic games by combining the log-linear learning (also known as logit dynamics) for the repeated play of normal-form games with Q-learning for unknown Markov…

Computer Science and Game Theory · Computer Science 2025-03-17 Ahmed Said Donmez , Onur Unlu , Muhammed O. Sayin

Language agnostic and semantic-language information isolation is an emerging research direction for multilingual representations models. We explore this problem from a novel angle of geometric algebra and semantic space. A simple but highly…

Computation and Language · Computer Science 2021-09-13 Ziyi Yang , Yinfei Yang , Daniel Cer , Eric Darve

Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques that mitigate such biases. In this work, we perform an…

Computation and Language · Computer Science 2022-04-05 Nicholas Meade , Elinor Poole-Dayan , Siva Reddy

One of the current trends in robotics is to employ large language models (LLMs) to provide non-predefined command execution and natural human-robot interaction. It is useful to have an environment map together with its language…

Robotics · Computer Science 2025-01-09 Evgenii Kruzhkov , Sven Behnke

We present a new approach that bridges binary analysis techniques with machine learning classification for the purpose of providing a static and generic evaluation technique for opaque predicates, regardless of their constructions. We use…

Cryptography and Security · Computer Science 2019-09-05 Ramtine Tofighi-Shirazi , Irina Asăvoae , Philippe Elbaz-Vincent , Thanh-Ha Le

Natural language understanding (NLU) models often rely on dataset biases rather than intended task-relevant features to achieve high performance on specific datasets. As a result, these models perform poorly on datasets outside the training…

Computation and Language · Computer Science 2023-01-05 Yougang Lyu , Piji Li , Yechang Yang , Maarten de Rijke , Pengjie Ren , Yukun Zhao , Dawei Yin , Zhaochun Ren

Traditional knowledge distillation focuses on aligning the student's predicted probabilities with both ground-truth labels and the teacher's predicted probabilities. However, the transition to predicted probabilities from logits would…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Penghui Yang , Chen-Chen Zong , Sheng-Jun Huang , Lei Feng , Bo An

Recent advancements in Vision-Language Models (VLMs) have enabled complex multimodal tasks by processing text and image data simultaneously, significantly enhancing the field of artificial intelligence. However, these models often exhibit…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Hoin Jung , Taeuk Jang , Xiaoqian Wang

Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with…

Artificial Intelligence · Computer Science 2026-01-30 Jinhao Pan , Chahat Raj , Anjishnu Mukherjee , Sina Mansouri , Bowen Wei , Shloka Yada , Ziwei Zhu

Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rely on uniform layerwise pruning strategies, which can lead to…

Computation and Language · Computer Science 2025-06-04 Yuli Chen , Bo Cheng , Jiale Han , Yingying Zhang , Yingting Li , Shuhao Zhang

As large language models become increasingly capable, there is growing concern that they may develop reasoning processes that are encoded or hidden from human oversight. To investigate whether current interpretability techniques can…

Artificial Intelligence · Computer Science 2025-12-09 Ching Fang , Samuel Marks

Understanding biases and stereotypes encoded in the weights of Large Language Models (LLMs) is crucial for developing effective mitigation strategies. However, biased behaviour is often subtle and non-trivial to isolate, even when…

Computation and Language · Computer Science 2026-02-03 Sekh Mainul Islam , Nadav Borenstein , Siddhesh Milind Pawar , Haeun Yu , Arnav Arora , Isabelle Augenstein

Large Language Models (LLMs) achieve excellent performance in natural language reasoning tasks through pre-training on vast unstructured text, enabling them to understand the logic in natural language and generate logic-consistent…

Computation and Language · Computer Science 2025-11-12 Songze Li , Zhiqiang Liu , Zhaoyan Gong , Xiaoke Guo , Zhengke Gui , Huajun Chen , Wen Zhang

Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practices remain unclear. In this work, we conduct a comprehensive…

Computation and Language · Computer Science 2025-10-14 Zhaochen Yu , Ling Yang , Jiaru Zou , Shuicheng Yan , Mengdi Wang

While advances in fairness and alignment have helped mitigate overt biases exhibited by large language models (LLMs) when explicitly prompted, we hypothesize that these models may still exhibit implicit biases when simulating human…

Computation and Language · Computer Science 2025-01-30 Yuxuan Li , Hirokazu Shirado , Sauvik Das

Language Representation Models (LRMs) trained with real-world data may capture and exacerbate undesired bias and cause unfair treatment of people in various demographic groups. Several techniques have been investigated for applying…

Computation and Language · Computer Science 2023-11-14 Chloe Qinyu Zhu , Rickard Stureborg , Brandon Fain

Time-varying linear state-space models are powerful tools for obtaining mathematically interpretable representations of neural signals. For example, switching and decomposed models describe complex systems using latent variables that evolve…

Recent advancements in large language models (LLMs) have shown their potential across both general and domain-specific tasks. However, there is a growing concern regarding their lack of sensitivity, factual incorrectness in responses,…

Computation and Language · Computer Science 2025-12-01 Vivek Kumar , Pushpraj Singh Rajawat , Eirini Ntoutsi

Due to the presence of political echo chambers, it becomes imperative to detect and remove subjective bias and emotionally charged language from both the text and images of political articles. However, prior work has focused on solely the…

Computers and Society · Computer Science 2025-06-24 Cedric Bernard , Xavier Pleimling , Amun Kharel , Chase Vickery