English
Related papers

Related papers: Surfacing Biases in Large Language Models using Co…

200 papers

The need for interpretability in deep learning has driven interest in counterfactual explanations, which identify minimal changes to an instance that change a model's prediction. Current counterfactual (CF) generation methods require…

Computation and Language · Computer Science 2025-12-11 Van Bach Nguyen , Christin Seifert , Jörg Schlötterer

Recently, high-performing code generation systems based on large language models have surfaced. They are trained on massive corpora containing much more natural text than actual executable computer code. This work shows that current code…

Artificial Intelligence · Computer Science 2023-05-10 Spyridon Mouselinos , Mateusz Malinowski , Henryk Michalewski

Many language generation models are now available for a wide range of generation tasks, including machine translation and summarization. Combining such diverse models may lead to further progress, but ensembling generation models is…

Computation and Language · Computer Science 2022-10-31 Jungo Kasai , Keisuke Sakaguchi , Ronan Le Bras , Hao Peng , Ximing Lu , Dragomir Radev , Yejin Choi , Noah A. Smith

Text generation is of great importance to many natural language processing applications. However, maximization-based decoding methods (e.g. beam search) of neural language models often lead to degenerate solutions -- the generated text is…

Computation and Language · Computer Science 2022-09-27 Yixuan Su , Tian Lan , Yan Wang , Dani Yogatama , Lingpeng Kong , Nigel Collier

Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a \emph{temporal smoothing bias}: transient acoustic cues may be underutilized in favor of temporally smooth context that is…

Sound · Computer Science 2026-04-20 Yanda Li , Yuhan Liu , Zirui Song , Yunchao Wei , Martin Takáč , Salem Lahlou

Applying language models to natural language processing tasks typically relies on the representations in the final model layer, as intermediate hidden layer representations are presumed to be less informative. In this work, we argue that…

Computation and Language · Computer Science 2023-05-03 Ariel Gera , Roni Friedman , Ofir Arviv , Chulaka Gunasekara , Benjamin Sznajder , Noam Slonim , Eyal Shnarch

While instruction-tuned language models have demonstrated impressive zero-shot generalization, these models often struggle to generate accurate responses when faced with instructions that fall outside their training set. This paper presents…

Computation and Language · Computer Science 2024-02-20 Taehyeon Kim , Joonkee Kim , Gihun Lee , Se-Young Yun

Large language models (LLMs) have achieved impressive performance on various natural language generation tasks. Nonetheless, they suffer from generating negative and harmful contents that are biased against certain demographic groups (e.g.,…

Machine Learning · Computer Science 2024-06-05 Tianci Liu , Haoyu Wang , Shiyang Wang , Yu Cheng , Jing Gao

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive…

Computation and Language · Computer Science 2025-06-17 Vinith M. Suriyakumar , Ayush Sekhari , Ashia Wilson

Despite significant progress, recent studies indicate that current large language models (LLMs) may still capture dataset biases and utilize them during inference, leading to the poor generalizability of LLMs. However, due to the diversity…

Computation and Language · Computer Science 2025-05-28 Zhouhao Sun , Xiao Ding , Li Du , Yunpeng Xu , Yixuan Ma , Yang Zhao , Bing Qin , Ting Liu

When generating text from probabilistic models, the chosen decoding strategy has a profound effect on the resulting text. Yet the properties elicited by various decoding strategies do not always transfer across natural language generation…

Computation and Language · Computer Science 2022-03-30 Gian Wiher , Clara Meister , Ryan Cotterell

Over-reliance on language priors is a major cause of hallucinations in Large Vision-Language Models (LVLMs), often leading to outputs that are linguistically plausible but visually inconsistent. Recent studies have explored contrastive…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Jianfei Zhao , Feng Zhang , Xin Sun , Lingxing Kong , Zhixing Tan , Chong Feng

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…

Machine Learning · Computer Science 2026-03-17 Manh Nguyen , Sunil Gupta , Hung Le

Large Language Models (LLMs) are now capable of generating highly fluent, human-like text. They enable many applications, but also raise concerns such as large scale spam, phishing, or academic misuse. While much work has focused on…

Computation and Language · Computer Science 2026-04-16 Swati Rallapalli , Shannon Gallagher , Ronald Yurko , Tyler Brooks , Chuck Loughin , Michele Sezgin , Violet Turri

Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable…

Computation and Language · Computer Science 2023-11-14 Etsuko Ishii , Yan Xu , Bryan Wilie , Ziwei Ji , Holy Lovenia , Willy Chung , Pascale Fung

Recent advancements in open-domain text generation, driven by the power of large pre-trained language models (LLMs), have demonstrated remarkable performance. However, assessing these models' generation quality remains a challenge. In this…

Computation and Language · Computer Science 2024-06-11 Sidi Lu , Hongyi Liu , Asli Celikyilmaz , Tianlu Wang , Nanyun Peng

Current techniques for detecting AI-generated text are largely confined to manual feature crafting and supervised binary classification paradigms. These methodologies typically lead to performance bottlenecks and unsatisfactory…

Computation and Language · Computer Science 2024-10-29 Xun Guo , Shan Zhang , Yongxin He , Ting Zhang , Wanquan Feng , Haibin Huang , Chongyang Ma

Controlled text generation allows for enforcing user-defined constraints on large language model outputs, an increasingly important field as LLMs become more prevalent in everyday life. One common approach uses energy-based decoding, which…

Computation and Language · Computer Science 2025-02-07 Patrick Pynadath , Ruqi Zhang

With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Phillip Howard , Anahita Bhiwandiwalla , Kathleen C. Fraser , Svetlana Kiritchenko

Code-switching, the interleaving of two or more languages within a sentence or discourse is pervasive in multilingual societies. Accurate language models for code-switched text are critical for NLP tasks. State-of-the-art data-intensive…

Computation and Language · Computer Science 2019-06-24 Bidisha Samanta , Sharmila Reddy , Hussain Jagirdar , Niloy Ganguly , Soumen Chakrabarti