English
Related papers

Related papers: Recontextualization Mitigates Specification Gaming…

200 papers

Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast,…

Machine Learning · Computer Science 2026-05-26 Martin Marek , Dongkyu Cho , Shikai Qiu , Rumi Chunara , Pavel Izmailov , Andrew Gordon Wilson

Computationally efficient contextual bandits are often based on estimating a predictive model of rewards given contexts and arms using past data. However, when the reward model is not well-specified, the bandit algorithm may incur…

Machine Learning · Computer Science 2021-06-14 Sanath Kumar Krishnamurthy , Vitor Hadad , Susan Athey

Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in their chain-of-thought reasoning. This makes the detection…

Computation and Language · Computer Science 2025-07-15 Miles Turpin , Andy Arditi , Marvin Li , Joe Benton , Julian Michael

Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly learn relevant knowledge from the given context. An intuitive…

Reward hacking -- where RL agents exploit gaps in misspecified reward functions -- has been widely observed, but not yet systematically studied. To understand how reward hacking arises, we construct four RL environments with misspecified…

Machine Learning · Computer Science 2022-02-15 Alexander Pan , Kush Bhatia , Jacob Steinhardt

Automatic generation of high-quality commit messages for code commits can substantially facilitate software developers' works and coordination. However, the semantic gap between source code and natural language poses a major challenge for…

Computation and Language · Computer Science 2021-06-22 Lun Yiu Nie , Cuiyun Gao , Zhicong Zhong , Wai Lam , Yang Liu , Zenglin Xu

Instruction tuning is a widely used approach to improve the instruction-following ability of large language models (LLMs). Instruction-tuning datasets typically include a mixture of context-augmented and context-free examples, yet prior…

Computation and Language · Computer Science 2026-01-09 Hyunji Lee , Seunghyun Yoon , Yunjae Won , Hanseok Oh , Geewook Kim , Trung Bui , Franck Dernoncourt , Elias Stengel-Eskin , Mohit Bansal , Minjoon Seo

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Computation and Language · Computer Science 2023-10-24 Lingyu Gao , Debanjan Ghosh , Kevin Gimpel

The lack of contextual information in text data can make the annotation process of text-based emotion classification datasets challenging. As a result, such datasets often contain labels that fail to consider all the relevant emotions in…

Computation and Language · Computer Science 2023-11-08 Daniel Yang , Aditya Kommineni , Mohammad Alshehri , Nilamadhab Mohanty , Vedant Modi , Jonathan Gratch , Shrikanth Narayanan

In-context learning (ICL) has transformed the use of large language models (LLMs) for NLP tasks, enabling few-shot learning by conditioning on labeled examples without finetuning. Despite its effectiveness, ICL is prone to errors,…

Computation and Language · Computer Science 2025-03-21 Mario Sanz-Guerrero , Katharina von der Wense

Incorporating external context can significantly enhance the response quality of Large Language Models (LLMs). However, real-world contexts often mix relevant information with disproportionate inappropriate content, posing reliability…

Computation and Language · Computer Science 2025-09-08 Rushi Wang , Jiateng Liu , Cheng Qian , Yifan Shen , Yanzhou Pan , Zhaozhuo Xu , Ahmed Abbasi , Heng Ji , Denghui Zhang

Pre-trained vision language models still fall short of human visual cognition. In an effort to improve visual cognition and align models with human behavior, we introduce visual stimuli and human judgments on visual cognition tasks,…

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Artificial Intelligence · Computer Science 2025-11-12 Qianxi He , Qingyu Ren , Shanzhe Lei , Xuhong Wang , Yingchun Wang

It is incredibly easy for a system designer to misspecify the objective for an autonomous system ("robot''), thus motivating the desire to have the robot learn the objective from human behavior instead. Recent work has suggested that people…

Artificial Intelligence · Computer Science 2019-07-02 Smitha Milli , Anca D. Dragan

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Computation and Language · Computer Science 2025-04-07 Jaymari Chua , Chen Wang , Lina Yao

We propose a novel reinforcement learning framework for post training large language models that does not rely on human in the loop feedback. Instead, our approach uses cross attention signals within the model itself to derive a self…

Artificial Intelligence · Computer Science 2025-04-18 Andrew Kiruluta , Andreas Lemos , Priscilla Burity

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…

Computation and Language · Computer Science 2023-11-07 Zeming Chen , Gail Weiss , Eric Mitchell , Asli Celikyilmaz , Antoine Bosselut

Just because some purely recurrent models suffer from being hard to optimize and inefficient on today's hardware, they are not necessarily bad models of language. We demonstrate this by the extent to which these models can still be improved…

Computation and Language · Computer Science 2023-04-19 Gábor Melis

Reinforcement learning has the potential to automate the acquisition of behavior in complex settings, but in order for it to be successfully deployed, a number of practical challenges must be addressed. First, in real world settings, when…

Machine Learning · Computer Science 2020-11-11 Kelvin Xu , Siddharth Verma , Chelsea Finn , Sergey Levine

Reinforcement learning has seen wide success in finetuning large language models to better align with instructions via human feedback. The so-called algorithm, Reinforcement Learning with Human Feedback (RLHF) demonstrates impressive…

Computation and Language · Computer Science 2023-02-13 Tianjun Zhang , Fangchen Liu , Justin Wong , Pieter Abbeel , Joseph E. Gonzalez
‹ Prev 1 3 4 5 6 7 10 Next ›