相关论文: Intent-conditioned and Non-toxic Counterspeech Gen…

Threat detection in Natural Language Processing lacks consistent definitions and standardized benchmarks, and is often conflated with broader phenomena such as toxicity, hate speech, or offensive language. In this work, we introduce…

Pre-trained Language Models are widely used in many important real-world applications. However, recent studies show that these models can encode social biases from large pre-training corpora and even amplify biases in downstream…

Large Language Models demonstrate strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC), a degradation in performance as information is revealed progressively in multi-turn settings. Motivated…

Hierarchical reinforcement learning (HRL) proposes to solve difficult tasks by performing decision-making and control at successively higher levels of temporal abstraction. However, off-policy HRL often suffers from the problem of a…

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…

Audio captioning aims at generating natural language descriptions for audio clips automatically. Existing audio captioning models have shown promising improvement in recent years. However, these models are mostly trained via maximum…

As a key component to intuitive cognition and reasoning solutions in human intelligence, causal knowledge provides great potential for reinforcement learning (RL) agents' interpretability towards decision-making by helping reduce the…

Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances. However, most existing methods rely mainly on models internal parametric knowledge, without explicit…

Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…

While standard IR models are mainly designed to optimize relevance, real-world search often needs to balance additional objectives such as diversity and fairness. These objectives depend on inter-document interactions and are commonly…

Online presence on social media platforms such as Facebook and Twitter has become a daily habit for internet users. Despite the vast amount of services the platforms offer for their users, users suffer from cyber-bullying, which further…

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…

This paper proposes an inverse reinforcement learning (IRL) framework to accelerate learning when the learner-teacher \textit{interaction} is \textit{limited} during training. Our setting is motivated by the realistic scenarios where a…

Given the black-box nature and complexity of large transformer language models (LM), concerns about generalizability and robustness present ethical implications for domains such as hate speech (HS) detection. Using the content rich Social…

Generative adversarial imitation learning (GAIL) is a model-free algorithm that has been shown to provide strong results in imitating complex behaviors in high-dimensional environments. In this paper, we utilize the GAIL model for text…

During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal cognitive processing may not always manifest as explicit linguistic structures, it is instrumental…

Hate speech online remains an understudied issue for marginalized communities, particularly in the Global South, which includes developing societies with increasing internet penetration. In this paper, we aim to provide marginalized…

In this paper, we focus on generating training examples for few-shot intents in the realistic imbalanced scenario. To build connections between existing many-shot intents and few-shot intents, we consider an intent as a combination of a…

Social media has seen a worrying rise in hate speech in recent times. Branching to several distinct categories of cyberbullying, gender discrimination, or racism, the combined label for such derogatory content can be classified as toxic…

Recent advancements in language models have demonstrated remarkable in-context learning abilities, prompting the exploration of in-context reinforcement learning (ICRL) to extend the promise to decision domains. Due to involving more…