相关论文: Bridging the Gap Between Training and Inference of…

Despite recent advances in natural language generation, it remains challenging to control attributes of generated text. We propose DExperts: Decoding-time Experts, a decoding-time method for controlled text generation that combines a…

We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story given its context. As controllable dimensions, we consider…

Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models…

Discriminative pre-trained language models (PLMs) learn to predict original texts from intentionally corrupted ones. Taking the former text as positive and the latter as negative samples, the PLM can be trained effectively for…

Pretrained Transformer-based language models (LMs) display remarkable natural language generation capabilities. With their immense potential, controlling text generation of such LMs is getting attention. While there are studies that seek to…

Large language models (LLMs) such as GPT-3 have demonstrated a strong capability to generate coherent and contextually relevant text. However, amidst their successes, a crucial issue persists: their generated outputs still lack commonsense…

It is increasingly important to evaluate how text generation systems based on large language models (LLMs) behave, such as their tendency to produce harmful output or their sensitivity to adversarial inputs. Such evaluations often rely on a…

Transformer-based language models have shown to be very powerful for natural language generation (NLG). However, text generation conditioned on some user inputs, such as topics or attributes, is non-trivial. Past approach relies on either…

Generative seq2seq dialogue systems are trained to predict the next word in dialogues that have already occurred. They can learn from large unlabeled conversation datasets, build a deeper understanding of conversational context, and…

Semantic control entails steering LM generations towards satisfying subtle non-lexical constraints, e.g., toxicity, sentiment, or politeness, attributes that can be captured by a sequence-level verifier. It can thus be viewed as sampling…

Although pre-trained language models encode generic knowledge beneficial for planning and control, they may fail to generate appropriate control policies for domain-specific tasks. Existing fine-tuning methods use human feedback to address…

Large language model (LLM)-powered agents can translate high-level user intents into plans and actions in an environment. Yet after observing an outcome, users may wonder: What if I had phrased my intent differently? We introduce a…

We describe our team's contribution to the STRICT-SMALL track of the BabyLM Challenge. The challenge requires training a language model from scratch using only a relatively small training dataset of ten million words. We experiment with…

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data…

ELECTRA, the generator-discriminator pre-training framework, has achieved impressive semantic construction capability among various downstream tasks. Despite the convincing performance, ELECTRA still faces the challenges of monotonous…

Teacher education requires deliberate practice with learners who exhibit identifiable strengths, weaknesses, and partial mastery. Large language models could support such practice by simulating students with known skill components, enabling…

Large Language Models (LLMs) often lack meaningful confidence estimates for their outputs. While base LLMs are known to exhibit next-token calibration, it remains unclear whether they can assess confidence in the actual meaning of their…

In this work, we introduce Mini-Gemini, a simple and effective framework enhancing multi-modality Vision Language Models (VLMs). Despite the advancements in VLMs facilitating basic visual dialog and reasoning, a performance gap persists…

We propose a novel approach to conformal prediction for generative language models (LMs). Standard conformal prediction produces prediction sets -- in place of single predictions -- that have rigorous, statistical performance guarantees. LM…

As language models (LMs) become capable of handling a wide range of tasks, their evaluation is becoming as challenging as their development. Most generation benchmarks currently assess LMs using abstract evaluation criteria like helpfulness…