13 accepted papers
Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models' susceptibility to data poisoning during preference learning. Data p…
Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation with semantically equivalent but differently phrased prompts, and exi
The task of multi-objective alignment aims at balancing and controlling the different alignment objectives, e.g., helpfulness, harmlessness and honesty) of large language models to meet the personalized requirements of different users. However, previous methods tend to train multiple models to deal…
Multimodal reasoning stands as a pivotal capability for large vision-language models (LVLMs). The integration with Domain-Specific Languages (DSL), offering precise visual representations, equips these models with the opportunity to execute more accurate reasoning in complex and professional domains…
Supervised fine-tuning (SFT) on instruction-following corpus is a crucial approach toward the alignment of large language models (LLMs). However, the performance of LLMs on standard knowledge and reasoning benchmarks tends to suffer from deterioration at the latter stage of the SFT process, echoing…
Multilingual large language models trained on non-parallel data yield impressive translation capabilities. Existing studies demonstrate that incidental sentence-level bilingualism within pre-training data contributes to the LLM's translation abilities. However, it has also been observed that LLM's t…
Multi-turn response selection aims to retrieve a response for a dialogue context from a candidate pool and negative sampling is the key to its retrieval performance. However, previous methods of negative samples tend to yield false negatives due to the one-to-many property in open-domain dialogue, w…
Previous research has demonstrated the potential of multi-task learning to foster a conversational agent’s ability to acquire a variety of skills. However, these approaches either suffer from interference among different datasets (also known as negative transfer), or fail to effectively reuse knowle…
Logical data-to-text generation is a representative task in measuring the capabilities of both language generation and complex reasoning. Despite the introduction of reasoning skills in generation, existing works still rely on neural language models to output the final table description. However, du…
Grounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses. Existing studies focus on how to synthesize a response with proper knowledge, yet neglect that the same knowledge could be expressed di…
Knowledge-grounded conversation (KGC) shows great potential in building an engaging and knowledgeable chatbot, and knowledge selection is a key ingredient in it. However, previous methods for knowledge selection only concentrate on the relevance between knowledge and dialogue context, ignoring the f…
Knowledge-grounded dialogue (KGC) shows excellent potential to deliver an engaging and informative response. However, existing approaches emphasize selecting one golden knowledge given a particular dialogue context, overlooking the one-to-many phenomenon in dialogue. As a result, existing paradigm l…
With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable ability is mainly obtained by fitting a large model with hun…